WO2017159784A9 - Condition monitoring system and wind power generation device - Google Patents

Condition monitoring system and wind power generation device Download PDF

Info

Publication number
WO2017159784A9
WO2017159784A9 PCT/JP2017/010659 JP2017010659W WO2017159784A9 WO 2017159784 A9 WO2017159784 A9 WO 2017159784A9 JP 2017010659 W JP2017010659 W JP 2017010659W WO 2017159784 A9 WO2017159784 A9 WO 2017159784A9
Authority
WO
WIPO (PCT)
Prior art keywords
waveform data
vibration waveform
value
evaluation value
unit
Prior art date
Application number
PCT/JP2017/010659
Other languages
French (fr)
Japanese (ja)
Other versions
WO2017159784A1 (en
Inventor
隆 長谷場
鈴木　洋介
高橋　亨
Original Assignee
Ntn株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from JP2016053679A external-priority patent/JP6639288B2/en
Priority claimed from JP2017049838A external-priority patent/JP6824076B2/en
Priority claimed from JP2017049833A external-priority patent/JP6820771B2/en
Application filed by Ntn株式会社 filed Critical Ntn株式会社
Priority to CN201780018017.1A priority Critical patent/CN108780025B/en
Priority to US16/085,878 priority patent/US11460005B2/en
Priority to EP17766780.5A priority patent/EP3431952B1/en
Publication of WO2017159784A1 publication Critical patent/WO2017159784A1/en
Publication of WO2017159784A9 publication Critical patent/WO2017159784A9/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M99/00—Subject matter not provided for in other groups of this subclass

Definitions

  • the present invention relates to a state monitoring system that monitors the state of a machine element that constitutes a device, and particularly relates to a state monitoring system that monitors the state of a machine element that constitutes a wind turbine generator.
  • a wind turbine generator power generation is performed by rotating a main shaft connected to a blade that receives wind power, rotating the main shaft by a speed increaser, and then rotating a rotor of the power generator.
  • Each of the main shaft, the speed increaser and the rotating shaft of the generator is rotatably supported by a rolling bearing, and a condition monitoring system (CMS: Condition Monitoring System) for diagnosing such a bearing abnormality is known.
  • CMS Condition Monitoring System
  • whether or not the bearing is damaged is diagnosed using vibration waveform data measured by a vibration sensor fixed to the bearing.
  • Patent Document 1 discloses a diagnostic system for performing a deterioration diagnosis of a computer to be diagnosed.
  • the diagnostic system described in Patent Literature 1 stores information received from an information collection unit that collects information about a computer in a storage circuit, and reads the information stored in the storage circuit to create a trend graph. Composed.
  • a moving average is obtained based on the created trend graph. If the moving average value is equal to or less than a preset threshold value, the computer is diagnosed as normal, and if the moving average value is equal to or greater than the threshold value, the computer is abnormal. Diagnose.
  • Patent Document 2 Japanese Patent Laid-Open No. 7-159469
  • Patent Document 2 measures the internal state of a device under measurement.
  • Patent Document 3 discloses an abnormality diagnosis device for diagnosing abnormalities in rotating parts and sliding parts used in mechanical equipment.
  • This abnormality diagnosis device performs frequency analysis of signals generated from rotating parts to obtain frequency components of actual measurement data, and from the frequency components of the actual measurement data, a frequency corresponding to an abnormal frequency of vibration caused by abnormality of the rotating parts. Extract ingredients. Then, the presence / absence of an abnormality of the rotating component is diagnosed by comparing and collating the extracted frequency component with a threshold value.
  • the threshold is individually set for each of the fundamental wave and the harmonic frequency of the abnormal frequency in order to reduce the influence of ambient noise and improve the accuracy of diagnosis of the presence or absence of abnormality.
  • the operating conditions change from moment to moment depending on the environment such as the wind condition indicating how the wind blows.
  • operating conditions such as vibration, spindle rotation speed, power generation amount, and wind speed also change from moment to moment. For example, when the wind is strong, the load applied to the mechanical elements of the wind turbine generator is larger than when the wind is weak, and therefore the vibration is increased.
  • the load applied to the machine element also changes depending on the wind direction, the vibration also changes.
  • the vibration waveform data measured by the vibration sensor changes from moment to moment according to changes in the operating conditions of the wind turbine generator.
  • the present invention has been made to solve such a problem, and a first object thereof is to provide a state monitoring system and a wind power generator that realize an accurate abnormality diagnosis.
  • a second object of the present invention is to provide a technique for setting a threshold value for diagnosing the presence or absence of an abnormality in a machine element constituting a wind power generator in a state monitoring system and a wind power generator equipped with the same. .
  • a state monitoring system is a state monitoring system for monitoring the state of a machine element constituting the apparatus, and includes a vibration sensor for measuring a vibration waveform of the machine element, and diagnosing abnormality of the machine element And a processing device.
  • the processing device includes an evaluation value calculation unit and a diagnosis unit.
  • the evaluation value calculation unit continuously calculates an evaluation value characterizing the effective value of the vibration waveform data output from the vibration sensor within a predetermined time.
  • the diagnosis unit diagnoses an abnormality of the machine element based on the transition of the temporal change in the evaluation value.
  • the evaluation value calculation unit is configured to calculate the lowest effective value of the vibration waveform data within a predetermined time as the evaluation value.
  • a state monitoring system includes a vibration sensor for measuring a vibration waveform of a machine element, and a processing device for diagnosing an abnormality of the machine element.
  • the processing device includes a diagnosis unit and a setting unit.
  • the diagnosis unit is configured to diagnose an abnormality of the machine element by comparing the effective value of the vibration waveform data output from the vibration sensor with a threshold value.
  • the setting unit is configured to set a threshold value.
  • the setting unit includes a first calculation unit that calculates a moving average value of effective values of n (n is an integer of 2 or more) vibration waveform data output from the vibration sensor, and an effective value of the n vibration waveform data.
  • a second calculation unit that calculates a standard deviation; and a third calculation unit that calculates a threshold based on the moving average value calculated by the first calculation unit and the standard deviation calculated by the second calculation unit.
  • a state monitoring system includes a vibration sensor for measuring a vibration waveform of a machine element, and a processing device for diagnosing an abnormality of the machine element.
  • the processing device includes an evaluation value calculation unit and a diagnosis unit.
  • the evaluation value calculation unit is configured to continuously calculate an evaluation value characterizing the vibration waveform data output from the vibration sensor within a predetermined time.
  • the diagnosis unit uses the vibration waveform data to diagnose abnormalities in machine elements by starting measurement of vibration waveform data triggered by a change in the tendency of the evaluation value calculated by the evaluation value calculation unit over time. Configured to do.
  • the threshold for diagnosing the presence / absence of abnormality of the mechanical elements constituting the wind turbine generator can be set appropriately, accurate abnormality diagnosis can be realized.
  • vibration waveform data when an abnormality has occurred in a mechanical element constituting the apparatus can be acquired reliably and appropriately, so that an accurate abnormality diagnosis can be realized.
  • FIG. 1 It is the figure which showed schematically the structure of the wind power generator to which the state monitoring system which concerns on Embodiment 1 was applied. It is a functional block diagram which shows the structure of the data processor shown in FIG. 1 functionally. It is the figure which showed the time change of the effective value of the vibration waveform data of the bearing stored in a memory
  • 10 is a flowchart for explaining a control process for diagnosing a bearing abnormality in the state monitoring system according to the second embodiment.
  • 10 is a flowchart illustrating a control process for diagnosing a bearing abnormality in the state monitoring system according to the third embodiment.
  • It is a functional block diagram which shows functionally the structure of the data processor in the state monitoring system which concerns on Embodiment 4.
  • FIG. It is a figure explaining operation
  • 15 is a flowchart for explaining threshold setting processing in the state monitoring system according to the fourth embodiment. It is a flowchart explaining the control processing for diagnosing the abnormality of the bearing 60 in the state monitoring system which concerns on embodiment.
  • 10 is a functional block diagram functionally showing the configuration of a data processing device in a state monitoring system according to a fifth embodiment. It is a figure explaining operation
  • 10 is a flowchart illustrating a control process for storing bearing vibration waveform data in a state monitoring system according to a fifth embodiment. 10 is a flowchart for explaining a control process for generating a measurement trigger for vibration waveform data of a bearing in a state monitoring system according to a fifth embodiment.
  • FIG. 14 is a flowchart illustrating a control process for generating a measurement trigger for vibration waveform data of a bearing in a state monitoring system according to a sixth embodiment.
  • 18 is a flowchart for explaining a control process for generating a measurement trigger for vibration waveform data of a bearing in the state monitoring system according to the seventh embodiment.
  • FIG. 20 is a functional block diagram functionally showing the configuration of a data processing device in a state monitoring system according to an eighth embodiment. It is a conceptual diagram which shows the relationship between the vibration waveform data of a bearing in a fixed time, and a segment. It is a figure for demonstrating a feature-value vector. It is a figure for demonstrating the basic concept of OC-SVM.
  • FIG. 1 is a diagram schematically showing a configuration of a wind turbine generator to which a state monitoring system according to Embodiment 1 of the present invention is applied.
  • a wind turbine generator 10 includes a main shaft 20, a blade 30, a speed increaser 40, a generator 50, a main shaft bearing (hereinafter simply referred to as “bearing”) 60, and vibration.
  • a sensor 70 and a data processing device 80 are provided.
  • the step-up gear 40, the generator 50, the bearing 60, the vibration sensor 70, and the data processing device 80 are stored in the nacelle 90, and the nacelle 90 is supported by the tower 100.
  • the main shaft 20 enters the nacelle 90 and is connected to the input shaft of the speed increaser 40 and is rotatably supported by the bearing 60.
  • the main shaft 20 transmits the rotational torque generated by the blade 30 receiving the wind force to the input shaft of the speed increaser 40.
  • the blade 30 is provided at the tip of the main shaft 20 and converts wind force into rotational torque and transmits it to the main shaft 20.
  • the bearing 60 is fixed in the nacelle 90 and supports the main shaft 20 in a freely rotatable manner.
  • the bearing 60 is composed of a rolling bearing, and is composed of, for example, a self-aligning roller bearing, a tapered roller bearing, a cylindrical roller bearing, or a ball bearing. These bearings may be single row or double row.
  • the vibration sensor 70 is fixed to the bearing 60.
  • the vibration sensor 70 measures the vibration waveform of the bearing 60 and outputs the measured vibration waveform data to the data processing device 80.
  • the vibration sensor 70 is constituted by, for example, an acceleration sensor using a piezoelectric element.
  • the speed increaser 40 is provided between the main shaft 20 and the generator 50, and increases the rotational speed of the main shaft 20 to output to the generator 50.
  • the speed increaser 40 is configured by a gear speed increasing mechanism including a planetary gear, an intermediate shaft, a high speed shaft, and the like.
  • a plurality of bearings that rotatably support a plurality of shafts are also provided in the speed increaser 40.
  • the generator 50 is connected to the output shaft of the speed increaser 40 and generates power by the rotational torque received from the speed increaser 40.
  • the generator 50 is constituted by, for example, an induction generator.
  • a bearing for rotatably supporting the rotor is also provided in the generator 50.
  • the data processing device 80 is provided in the nacelle 90 and receives vibration waveform data of the bearing 60 from the vibration sensor 70.
  • the data processing device 80 diagnoses the abnormality of the bearing 60 using the vibration waveform data of the bearing 60 according to a preset program.
  • FIG. 2 is a functional block diagram functionally showing the configuration of the data processing device 80 shown in FIG.
  • the data processing device 80 includes a low-pass filter (hereinafter referred to as “LPF (Low Pass Filter)”) 110, an effective value calculation unit 120, a storage unit 130, and an evaluation value calculation unit 140. And a diagnosis unit 150 and a threshold setting unit 160.
  • LPF Low Pass Filter
  • the LPF 110 receives vibration waveform data of bearing 60 from vibration sensor 70.
  • the LPF 110 passes a signal component lower than a predetermined frequency (for example, 400 Hz) in the received vibration waveform data, and blocks the high frequency component.
  • a predetermined frequency for example, 400 Hz
  • the effective value calculation unit 120 receives the vibration waveform data of the bearing 60 from the LPF 110.
  • the effective value calculation unit 120 calculates an effective value (also referred to as “RMS (Root Mean Square) value”) of the vibration waveform data of the bearing 60, and stores the calculated effective value of the vibration waveform data in the storage unit 130. Output to.
  • RMS Root Mean Square
  • the storage unit 130 stores the effective value of the vibration waveform data of the bearing 60 calculated by the effective value calculating unit 120 every moment.
  • the storage unit 130 is configured by, for example, a readable / writable nonvolatile memory.
  • the storage unit 130 is configured to store an effective value of vibration waveform data of the bearing 60 at least within a predetermined time. For example, when the storage unit 130 receives the vibration waveform data of the bearing 60 from the effective value calculation unit 120 at a predetermined time interval, the effective value of the oldest vibration waveform data among the effective values of the vibration waveform data within a predetermined time. And an effective value of newly inputted vibration waveform data is added.
  • the storage unit 130 updates the effective value of the vibration waveform data of the bearing 60 within a predetermined time at predetermined time intervals. As will be described later, the effective value of the vibration waveform data of the bearing 60 stored in the storage unit 130 within a predetermined time is read, and the abnormality of the bearing 60 is diagnosed using the read effective value.
  • the evaluation value calculating unit 140 calculates an evaluation value that characterizes the read effective value of the vibration waveform data within the predetermined time.
  • the evaluation value calculation unit 140 is configured to calculate the evaluation value continuously in time. That is, the evaluation value calculation unit 140 updates the evaluation value at a predetermined time interval. Details of the evaluation value calculation in the evaluation value calculation unit 140 will be described later.
  • the threshold value setting unit 160 sets a threshold value used for diagnosing the presence or absence of abnormality of the bearing 60 in the diagnosis unit 150.
  • the threshold setting unit 160 outputs the set threshold to the diagnosis unit 150. Details of threshold setting in the threshold setting unit 160 will be described later.
  • the diagnosis unit 150 receives an evaluation value from the evaluation value calculation unit 140 and a threshold value from the threshold value setting unit 160.
  • the diagnosis unit 150 diagnoses an abnormality in the bearing 60 by comparing the evaluation value with a threshold value. Specifically, when the evaluation value is larger than the threshold value, the diagnosis unit 150 diagnoses that the bearing 60 is abnormal. On the other hand, when the evaluation value is less than or equal to the threshold value, the diagnosis unit 150 diagnoses that the bearing 60 is normal.
  • FIG. 3 is a diagram showing temporal changes in the effective value of the vibration waveform data of the bearing 60 stored in the storage unit 130.
  • FIG. 3 shows an example of a temporal change in the effective value of the vibration waveform data of the bearing 60 when the rotation speed of the main shaft 20 is low (for example, 100 rpm or less).
  • FIG. 3 assumes a case where the bearing 60 is replaced from an abnormal product to a new product at a certain time t. That is, a period before time t indicates an abnormality occurrence period in which an abnormality has occurred in the bearing 60, and a period after time t indicates a normal period in which the bearing 60 is in a normal state.
  • the effective value of the vibration waveform data during the abnormality occurrence period and the effective value of the vibration waveform data during the normal period both change greatly.
  • the vibration of the bearing 60 is reduced. Therefore, the vibration waveform data output from the vibration sensor 70 is greatly affected by noise and changes greatly.
  • an attempt is made to set a threshold for diagnosing the presence or absence of an abnormality in the bearing 60 based on the temporal change in the effective value of the vibration waveform data shown in FIG.
  • the threshold value is set so as to be less than all of the effective values of the vibration waveform data in the abnormality occurrence period, most of the effective values of the vibration waveform data in the normal period exceed the threshold value. As a result, although the bearing 60 is in a normal state, the bearing 60 is erroneously diagnosed as being abnormal.
  • an evaluation value characterizing the effective value of the vibration waveform data within a predetermined time is calculated, and the abnormality of the bearing 60 is diagnosed using the calculated evaluation value.
  • the evaluation value can be calculated by statistically processing the effective value of the vibration waveform data within a certain time.
  • the statistical process for example, a moving average process can be used.
  • FIG. 4 is a diagram showing a temporal change in the moving average value of the effective value of the vibration waveform data within a certain period.
  • FIG. 4 is obtained by performing a moving averaging process on the temporal change of the effective value of the vibration waveform data shown in FIG.
  • a moving averaging process a fixed time is set as a time corresponding to 24 effective values, and a simple moving average value of 24 effective values is calculated.
  • the moving average value shown in FIG. 4 When the temporal change of the moving average value shown in FIG. 4 is compared with the temporal change of the effective value of the vibration waveform data shown in FIG. 3, the moving average value has a smaller magnitude of change than the effective value. Thus, it can be seen that the influence of noise is reduced.
  • the threshold value is set so as to be lower than all the moving average values during the abnormality occurrence period, some of the moving average values during the normal period exceed the threshold value. As a result, as in FIG. 3, the bearing 60 is erroneously diagnosed as being abnormal even though the bearing 60 is in a normal state.
  • the evaluation value calculation unit 140 calculates the minimum value of the vibration waveform data within the certain time as an evaluation value characterizing the effective value of the vibration waveform data within the certain time.
  • FIG. 5 is a diagram showing a temporal change of the minimum value of the effective value of the vibration waveform data within a predetermined time calculated by the evaluation value calculation unit 140.
  • the minimum value of the effective value within a fixed time is continuously calculated with respect to the temporal change of the effective value of the vibration waveform data shown in FIG.
  • the fixed time is set to the same length as the fixed time when the moving average value in FIG. 4 is calculated (that is, a length corresponding to 24 effective values).
  • the effective value of the vibration waveform data of the bearing 60 is in a state where the magnitude of noise is added to the magnitude of the vibration of the original bearing 60. According to this, it can be understood that the minimum value of the effective value of the vibration waveform data within a certain time is the smallest value of the influence of noise among the effective values of the vibration waveform data within the certain time. Therefore, by setting this minimum value as the evaluation value, even when the vibration of the bearing 60 is small, the influence of noise on the effective value of the vibration waveform data of the bearing 60 can be effectively reduced. As a result, a more accurate abnormality diagnosis can be realized.
  • the threshold setting unit 160 sets the threshold based on the temporal change of the lowest effective value of the vibration waveform data within a certain time calculated by the evaluation value calculating unit 140.
  • the threshold can be set to a value that is smaller than the transition of the temporal change of the lowest value during the abnormality occurrence period and larger than the transition of the temporal change of the lowest value during the normal period. This indicates that the presence or absence of an abnormality in the bearing 60 can be diagnosed by comparing the minimum value of the effective value of the vibration waveform data within a certain time with a threshold value.
  • the threshold value setting unit 160 when the temporal change of the minimum value in each of the abnormality occurrence period and the normal period as shown in FIG. 5 is acquired, the temporal change of the lowest value in the abnormality occurrence period. A predetermined number of minimum values are extracted from the above, and an average value of the extracted predetermined number of minimum values is calculated.
  • the threshold setting unit 160 also extracts a predetermined number of minimum values from the temporal change of the minimum value in the normal period, and calculates the average value of the extracted predetermined minimum values.
  • the threshold setting unit 160 calculates a ratio between the average value in the normal period and the average value in the abnormality occurrence period, and sets the coefficient to a value smaller than the calculated ratio. Then, the threshold value is calculated by multiplying the set coefficient by the average value in the normal period.
  • FIG. 6 is a flowchart illustrating a control process for diagnosing an abnormality of the bearing 60 in the state monitoring system according to the first embodiment.
  • the control process shown in FIG. 6 is repeatedly executed by the data processing device 80 at predetermined time intervals.
  • the data processing device 80 receives vibration waveform data of the bearing 60 from the vibration sensor 70 in step S01.
  • the data processing device 80 determines whether or not a predetermined operation state is established in the wind turbine generator 10.
  • the predetermined operation state is an operation state when the wind power generator 10 is performing a rated operation, and the rotational speed, power generation amount, power generation of the main shaft 20, the speed increaser 40, and the generator 50 during the rated operation. This includes the torque, wind direction, and wind speed of the rotating shaft of the machine 50.
  • the LPF 110 performs a filtering process on the vibration waveform data of the bearing 60.
  • the effective value calculation unit 120 calculates the effective value of the vibration waveform data of the bearing 60.
  • the storage unit 130 stores the effective value of the vibration waveform data calculated by the effective value calculation unit 120 in step S05.
  • the evaluation value calculation unit 140 determines whether or not the number of effective values of the vibration waveform data stored in the storage unit 130 satisfies the specified number in step S06.
  • the specified number is equal to the number of effective values of vibration waveform data that are temporally continuous within a fixed time.
  • NO the number of effective values of the vibration waveform data stored in the storage unit 130 is less than the specified number (when NO is determined in S06)
  • the subsequent processes S06 to S09 are skipped.
  • the evaluation value calculation unit 140 proceeds to step S07 and is stored in the storage unit 130.
  • the effective value of the specified number of vibration waveform data is read, and the lowest effective value of the read specified number of vibration waveform data is calculated.
  • the evaluation value calculation unit 140 outputs the calculated minimum value to the diagnosis unit 150.
  • the diagnosis unit 150 compares the minimum value calculated in step S07 with the threshold value in step S08. When the minimum value is less than or equal to the threshold (NO in S08), the diagnosis unit 150 diagnoses that the bearing 60 is normal and skips the subsequent process S09. On the other hand, when the lowest value calculated in step S07 is larger than the threshold value (when YES is determined in S08), diagnosis unit 150 diagnoses that bearing 60 is abnormal in step S09.
  • the evaluation value characterizing the effective value of the vibration waveform data of the bearing 60 within a certain time the lowest value of the effective value of the vibration waveform data within the certain time is used. Even when the rotation speed of the spindle 20 is low and the effective value of the vibration waveform data is small, an evaluation value with reduced influence of noise can be obtained. Thereby, normal abnormality diagnosis of the bearing 60 can be realized using the evaluation value.
  • the configuration for diagnosing the abnormality of the bearing 60 by comparing the evaluation value and the threshold value has been described.
  • the abnormality diagnosis of the bearing 60 using the evaluation value is not limited to the above configuration.
  • Embodiments 2 and 3 other configuration examples of abnormality diagnosis using evaluation values will be described.
  • FIG. 7 is a flowchart for explaining a control process for diagnosing abnormality of the bearing 60 in the state monitoring system according to the second embodiment.
  • the control processing shown in FIG. 7 is repeatedly executed by the data processing device 80 at predetermined time intervals.
  • FIG. 7 is compared with FIG. 6, the state monitoring system according to the second embodiment executes step S08A instead of step S08 after the processing of steps S01 to S07 similar to FIG.
  • the diagnosis unit 150 determines the minimum value time in step S08A.
  • the presence / absence of abnormality of the bearing 60 is diagnosed based on the rate of change, that is, the amount of change in unit time.
  • the evaluation value calculation unit 140 calculates the temporal change rate of the lowest value based on the difference between the lowest value calculated in step S07 and the lowest value calculated immediately before this lowest value. Calculate. Then, the evaluation value calculation unit 140 compares the calculated minimum value temporal change rate with a threshold value. When the temporal change rate of the minimum value is equal to or less than the threshold (when NO in S08A), the diagnosis unit 150 diagnoses that the bearing 60 is normal and skips the subsequent process S09. On the other hand, when the temporal change rate of the minimum value is larger than the threshold value (when YES is determined in S08A), diagnosis unit 150 diagnoses that bearing 60 is abnormal in step S09.
  • the evaluation value characterizing the effective value of the vibration waveform data of the bearing 60 within a predetermined time is used as the evaluation value to characterize the bearing using the minimum value of the effective value of the vibration waveform data within the predetermined time. Diagnose 60 abnormalities. Therefore, also in the second embodiment, the same effect as in the first embodiment can be obtained.
  • the threshold value used in step S08A of FIG. 7 is a value larger than the temporal change rate of the lowest value in the normal period and smaller than the temporal change rate of the lowest value in the abnormality occurrence period in the threshold setting unit 160. Can be set to
  • the threshold setting unit 160 calculates the average value of the temporal change rate of the lowest value in the abnormality occurrence period, and calculates the average value of the temporal change rate of the lowest value in the normal period. Calculate. Then, the threshold setting unit 160 calculates the ratio of the average value of the temporal change rate of the lowest value in the normal period and the average value of the temporal change rate of the lowest value in the abnormality occurrence period, A coefficient is set to a value smaller than the calculated ratio. The threshold value setting unit 160 calculates the threshold value by multiplying the set coefficient by the average value of the temporal change rate of the lowest value in the normal period.
  • FIG. 8 is a flowchart for explaining a control process for diagnosing an abnormality of the bearing 60 in the state monitoring system according to the third embodiment.
  • the control processing shown in FIG. 8 is repeatedly executed by the data processing device 80 at predetermined time intervals.
  • FIG. 8 is compared with FIG. 6, the state monitoring system according to the third embodiment executes step S08B instead of step S08 after the processing of steps S01 to S07 similar to FIG.
  • the diagnosis unit 150 determines that the minimum value is large in step S08B.
  • the presence or absence of an abnormality in the bearing 60 is diagnosed based on the height and the temporal change rate.
  • the diagnosis unit 150 compares the lowest value calculated in step S07 with the first threshold value.
  • the diagnosis unit 150 diagnoses that the bearing 60 is normal and skips the subsequent process S09.
  • the diagnosis unit 150 further compares the temporal change rate of the lowest value with the second threshold.
  • the temporal change rate of the minimum value is equal to or less than the second threshold value (when NO in S08B)
  • the diagnosis unit 150 diagnoses that the bearing 60 is normal and skips the subsequent process S09.
  • diagnosis unit 150 diagnoses that bearing 60 is abnormal in step S09.
  • the minimum value of the effective value of the vibration waveform data within a certain time is larger than the first threshold value, and the temporal change rate of the minimum value is higher than the second threshold value. If so, the bearing 60 is diagnosed as abnormal. Thus, even when the temporal change rate of the minimum value is larger than the second threshold value, the magnitude of the vibration of the bearing 60 is small when the minimum value is equal to or smaller than the first threshold value. Therefore, it can be determined that the degree of influence of noise is large. In such a case, by diagnosing that the bearing 60 is normal, it is possible to diagnose the abnormality of the bearing 60 based on the evaluation value from which the influence of noise superimposed on the vibration waveform data is appropriately eliminated. Therefore, also in the third embodiment, the same effect as in the first embodiment can be obtained.
  • the first threshold value used in step S08B in FIG. 8 is smaller than the transition of the temporal change of the minimum value in the abnormality occurrence period and has the minimum value in the normal period as described in the first embodiment. It can be set to a value larger than the temporal change. Further, as described in the second embodiment, the second threshold value is set to a value that is larger than the temporal change rate of the lowest value in the normal period and smaller than the temporal change rate of the lowest value in the abnormality occurrence period. can do.
  • the vibration sensor 70 is installed in the bearing 60 that is one of the mechanical elements constituting the wind power generator 10, and the abnormality of the bearing 60 is diagnosed.
  • the point that the machine element to be diagnosed is not limited to the bearing 60 will be described.
  • a vibration sensor is installed in a bearing provided in the speed increaser 40 or in the generator 50 together with or in place of the bearing 60, and the speed increaser 40 is obtained by the same method as in each of the above embodiments.
  • An abnormality of a bearing provided in the generator 50 or in the generator 50 can be diagnosed.
  • data processing device 80 corresponds to an example of “processing device” in the present invention, and includes storage unit 130, evaluation value calculation unit 140, diagnosis unit 150, and threshold setting unit.
  • Reference numeral 160 corresponds to one embodiment of the “storage unit”, “evaluation value calculation unit”, “diagnosis unit”, and “setting unit” in the present invention.
  • FIG. 9 is a functional block diagram functionally showing the configuration of the data processing device 80 in the state monitoring system according to Embodiment 4 of the present invention.
  • data processing device 80 includes a bandpass filter (hereinafter referred to as “BPF (Band Pass Filter)”) 112, an effective value calculation unit 120, a storage unit 130, and a threshold setting unit 160. And a diagnostic unit 150.
  • BPF Band Pass Filter
  • the BPF 112 receives vibration waveform data of the bearing 60 from the vibration sensor 70.
  • the BPF 112 performs a filtering process on the vibration waveform data of the bearing 60.
  • the BPF 112 is, for example, a high pass filter (HPF (High Pass Filter)).
  • HPF High Pass Filter
  • the HPF passes a signal component higher than a predetermined frequency with respect to the received vibration waveform data, and blocks a low frequency component.
  • the HPF is provided to remove a direct current component included in the vibration waveform data of the bearing 60. Note that the HPF may be omitted if the output of the vibration sensor 70 does not include a DC component.
  • the BPF 112 may further include an envelope processing unit between the vibration sensor 70 and the HPF.
  • the envelope processing unit receives vibration waveform data of the bearing 60 from the vibration sensor 70
  • the envelope processing unit performs envelope processing on the received vibration waveform data to generate an envelope waveform of the vibration waveform data of the bearing 60.
  • Various known methods can be applied to the envelope processing calculated in the envelope processing unit.
  • the vibration waveform data of the bearing 60 received from the vibration sensor 70 is rectified into an absolute value, and a low-pass filter (LPF) is obtained. (Low Pass Filter)), the envelope waveform of the vibration waveform data of the bearing 60 is generated.
  • LPF low-pass filter
  • the HPF when the HPF receives the envelope waveform of the vibration waveform data of the bearing 60 from the envelope processing unit, the HPF passes a signal component higher than a predetermined frequency for the received envelope waveform, and blocks the low frequency component. . That is, the HPF is configured to remove a direct current component included in the envelope waveform and extract an alternating current component of the envelope waveform.
  • the BPF 112 may further include an LPF.
  • the LPF passes a signal component lower than a predetermined frequency with respect to the received vibration waveform data, and blocks the high frequency component.
  • the effective value calculation unit 120 receives the vibration waveform data of the bearing 60 subjected to the filter processing from the BPF 112. The effective value calculation unit 120 calculates an effective value (RMS value) of the vibration waveform data of the bearing 60 and outputs the calculated effective value of the vibration waveform data to the storage unit 130.
  • RMS value effective value
  • the effective value of the vibration waveform of the bearing 60 calculated by the effective value calculation unit 120 is the effective value of the raw vibration waveform that has not been subjected to the envelope processing, for example, separation occurs in a part of the bearing ring of the bearing 60.
  • the increase in the value is small for the impulse-like vibration in which the vibration increases only when the rolling element passes through the peeled portion, it occurs when the surface of the contact portion between the race ring and the rolling element is rough or poorly lubricated. For continuous vibrations, the value increases.
  • the effective value of the alternating current component of the envelope waveform calculated by the effective value calculating unit 120 is the continuous value generated when the raceway surface is rough or poorly lubricated.
  • the increase in value is small for vibration, and the increase is large for impulse vibration.
  • the storage unit 130 stores the effective value of the vibration waveform data of the bearing 60 calculated by the effective value calculating unit 120 every moment.
  • the storage unit 130 is configured by, for example, a readable / writable nonvolatile memory.
  • the storage unit 130 is configured to store effective values of vibration waveform data of at least the latest n bearings (n is an integer of 2 or more). In the following description, the effective value of the vibration waveform data is simply referred to as “vibration waveform data”.
  • the threshold setting unit 160 sets a threshold used for diagnosing the presence or absence of an abnormality in the bearing 60.
  • the threshold setting unit 160 outputs the set threshold to the diagnosis unit 150. Details of threshold setting in the threshold setting unit 160 will be described later.
  • the diagnosis unit 150 diagnoses the abnormality of the bearing 60 based on the threshold set by the threshold setting unit 160. Specifically, the diagnosis unit 150 compares the read vibration waveform data with the threshold set by the threshold setting unit 160. When it is determined that the vibration waveform data exceeds the threshold value, the diagnosis unit 150 issues an alarm for notifying the abnormality of the bearing 60. Further, the diagnosis unit 150 diagnoses the abnormality of the bearing 60 based on the transition of the temporal change of the measured vibration waveform data.
  • the threshold setting unit 160 includes a moving average calculation unit 162 (first calculation unit), a standard deviation calculation unit 164 (second calculation unit), and a threshold calculation unit 166 (third calculation unit). And a threshold storage unit 168.
  • FIG. 10 is a diagram for explaining the operation of the threshold setting unit 160.
  • storage unit 130 receives vibration waveform data of bearing 60 from effective value calculation unit 120 at predetermined time intervals.
  • D1 to Dn + 2 in FIG. 10 represent vibration waveform data given to the storage unit 130 at predetermined time intervals.
  • the threshold setting unit 160 sequentially reads vibration waveform data for a specified period from the vibration waveform data stored in the storage unit 130, performs moving average calculation processing, standard deviation calculation processing, and threshold calculation processing. Is calculated.
  • the processing for calculating the threshold value is desirably performed when vibration waveform data is sufficiently accumulated in the storage unit 130.
  • the moving average calculation unit 162 calculates the moving average value of the latest read vibration waveform data of the n bearings 60.
  • the latest vibration waveform data D1 to Dn of the n bearings 60 up to time tn are read from the storage unit 130
  • the average value MAn of the n vibration waveform data D1 to Dn is calculated.
  • an average value MAn + 1 of the n pieces of vibration waveform data D2 to Dn + 1 is calculated.
  • an average value MAn + 2 of the n vibration waveform data D3 to Dn + 2 is calculated.
  • the moving average value may be a simple moving average value or a weighted moving average value. In this way, the moving average calculation unit 162 calculates the moving average value MA using the latest vibration waveform data of the n bearings 60.
  • the standard deviation calculator 164 calculates the standard deviation ⁇ of the vibration waveform data of the n bearings 60.
  • the threshold calculation unit 166 calculates a threshold using the moving average value MA calculated by the moving average calculation unit 162 and the standard deviation ⁇ calculated by the standard deviation calculation unit 164.
  • the threshold Th is expressed by the following equation (1).
  • Th MA + k ⁇ ⁇ (1)
  • the threshold value Thn is calculated using the moving average value MAn and the standard deviation ⁇ at time tn
  • the threshold value Thn + 1 is calculated using the moving average value MAn + 1 and the standard deviation ⁇ at time tn + 1
  • the movement at the time tn + 2 is performed.
  • the threshold value Thn + 2 is calculated using the average value MAn + 2 and the standard deviation ⁇ .
  • the threshold value calculation unit 166 calculates the threshold value Th, and stores the calculated threshold value Th in the threshold value storage unit 168.
  • Threshold value Th includes a seasonal variation component. Therefore, the diagnosis unit 150 is configured to use the threshold value Th of the current season and the past simultaneous period among the threshold values Th stored in the threshold value storage unit 168. That is, the diagnosis unit 150 is configured to use a threshold value Th set based on past vibration waveform data under the same operating conditions as the vibration waveform data.
  • the diagnosis unit 150 performs the diagnosis of the abnormality of the bearing 60 using the threshold Th corresponding to a change in operating conditions such as seasonal factors.
  • the threshold value Th is set by performing statistical processing on n pieces of vibration waveform data, and thus changes according to a change in operating conditions of the wind turbine generator 10. That is, the threshold value Th can reflect a change in operating conditions of the wind turbine generator 10.
  • the comparison result shows that the operating conditions of the wind power generator 10 change.
  • the influence can be reduced.
  • FIG. 11 is a graph showing an example of the threshold set by the threshold setting unit 160.
  • FIG. 11 shows an effective value of vibration waveform data measured by the vibration sensor 70 in a measurement period of about one year from February 1 of a certain year to February 26 of the following year, and a moving average of the vibration waveform data. The time change with a value and a threshold is shown.
  • FIG. 11 represents the effective value of the vibration waveform data of the bearing 60.
  • a broken line in FIG. 11 indicates a temporal change in the moving average value MA of the effective values of the n pieces of vibration waveform data.
  • n 120.
  • the solid line in FIG. 11 shows the temporal change of the threshold value set using the moving average value MA and the standard deviation ⁇ of the effective values of the n pieces of vibration waveform data.
  • the effective value of the vibration waveform data changes greatly during the measurement period.
  • the effective value is relatively large from December to January, while the effective value is relatively small from July to August. In this way, the effective value changes greatly due to the operating conditions that change from season to season.
  • the threshold value In order to make an accurate diagnosis even in a period in which the effective value is relatively small, it is conceivable to set the threshold value to a constant value based on the effective value in the period. However, if this is done, an effective value that exceeds the threshold frequently occurs during a period in which the effective value is relatively large, and accurate diagnosis becomes difficult.
  • the threshold value is set based on the moving average value calculated from the effective value of the vibration waveform data of the bearing 60 recorded in the past certain period.
  • the threshold is set using the effective value of the vibration waveform data at the time when it is determined that the past bearing 60 is normal. Therefore, if the abnormality is diagnosed based on the threshold value set for the same past operating conditions (for example, the same period in the past), the threshold value is relatively low during the period in which the effective value is relatively small. On the other hand, the threshold value becomes relatively large during the period when the effective value becomes relatively large. Thus, since the threshold value reflects the change in the operating condition of the wind turbine generator 10, an accurate abnormality diagnosis can be realized.
  • FIG. 12 is a flowchart for explaining threshold setting processing in the state monitoring system according to the fourth embodiment.
  • the setting process shown in FIG. 12 is executed by the data processing device 80 (FIG. 9) by designating a data range (period) used for threshold calculation.
  • the data processing device 80 designates a range of data used for threshold calculation in step S11.
  • the data range may be automatically set, for example, the same month one year ago, or may be configured to be given by communication or the like as a parameter from the outside.
  • the threshold value setting unit 160 sequentially reads the vibration waveform data stored in the storage unit 130 from the head of the designated data range in step S12.
  • the threshold setting unit 160 determines whether or not the number of effective values of the read vibration waveform data is n or more in step S13. When the number of effective values of the read vibration waveform data is less than n (NO in S13), the subsequent processes S14 to S17 are skipped.
  • the threshold setting unit 160 proceeds to step S14, and reads the latest n read data. Calculates the moving average value of the effective value of vibration waveform data.
  • step S15 the threshold setting unit 160 calculates a standard deviation of effective values of the latest n pieces of vibration waveform data read out. Then, in step S16, the threshold setting unit 160 sets a threshold using the moving average value calculated in step S14 and the standard deviation calculated in step S15. The threshold setting unit 160 sequentially stores the set thresholds in the threshold storage unit 168 (FIG. 9) in step S17. The threshold value is stored together with the time information of the data used for the calculation, and is used for selecting the threshold value used for the diagnosis.
  • the threshold setting unit 160 determines whether or not the processing has been completed for all vibration waveform data in the target period in step S18. If the process has not been completed (NO in S18), the process returns to S12.
  • FIG. 13 is a flowchart for explaining a control process for diagnosing an abnormality of the bearing 60 in the state monitoring system according to the fourth embodiment.
  • the control processing shown in FIG. 13 is repeatedly executed by the data processing device 80 at predetermined time intervals.
  • the data processing device 80 receives the vibration waveform data of the bearing 60 from the vibration sensor 70 in step S51.
  • the BPF 112 performs a filtering process on the vibration waveform data of the bearing 60 in step S ⁇ b> 52.
  • the effective value calculator 120 calculates the effective value of the vibration waveform data of the bearing 60.
  • the storage unit 130 stores the effective value of the vibration waveform data calculated by the effective value calculation unit 120 in step S54.
  • step S55 the diagnosis unit 150 reads the threshold value set based on the effective value of the past vibration waveform data under the same operation condition as the effective value of the vibration waveform data from the threshold value storage unit 168 in the threshold value setting unit 160. .
  • the diagnosis unit 150 reads out the threshold values set for the current season and the past simultaneous period.
  • step S56 the data processing device 80 compares the effective value of the vibration waveform data calculated in step S53 with the threshold value read in step S55.
  • the diagnosis unit 150 diagnoses that the bearing 60 is normal and skips the subsequent processing S57.
  • the diagnosis unit 150 diagnoses that the bearing 60 is abnormal in step S57 and issues an alarm.
  • the vibration sensor 70 is installed in the bearing 60 that is one of the mechanical elements constituting the wind power generator 10, and the abnormality of the bearing 60 is diagnosed.
  • the mechanical element is not limited to the bearing 60.
  • a vibration sensor is installed in a bearing provided in the speed increaser 40 or in the generator 50 together with or in place of the bearing 60, and the speed increaser 40 is obtained by the same method as in the fourth embodiment.
  • An abnormality of a bearing provided in the generator 50 or in the generator 50 can be diagnosed.
  • the data processing device 80 corresponds to an example of the “processing device” in the present invention
  • the threshold setting unit 160 and the diagnosis unit 150 are each the “setting unit” in the present invention.
  • the moving average calculation unit 162, the standard deviation calculation unit 164, the threshold value calculation unit 166, and the threshold value storage unit 168 are respectively the “first calculation unit” and the “second calculation unit” in the present invention. ”,“ Third arithmetic unit ”, and“ storage unit ”.
  • FIG. 14 is a functional block diagram functionally showing the configuration of the data processing device 80 in the state monitoring system according to Embodiment 5 of the present invention.
  • the data processing device 80 includes a BPF 112, an effective value calculation unit 120, a storage unit 130, a vibration waveform data output unit 170, a diagnosis unit 150, an evaluation value calculation unit 140, a measurement trigger. Generator 180.
  • the BPF 112 receives vibration waveform data of the bearing 60 from the vibration sensor 70.
  • the BPF 112 includes, for example, an HPF.
  • the HPF passes a signal component higher than a predetermined frequency with respect to the received vibration waveform data, and blocks a low frequency component.
  • the HPF is provided to remove a direct current component included in the vibration waveform data of the bearing 60. Note that the HPF may be omitted if the output of the vibration sensor 70 does not include a DC component.
  • the BPF 112 may include an LPF in addition to the HPF or instead of the HPF.
  • the LPF passes a signal component lower than a predetermined frequency for the received vibration waveform data.
  • an envelope processing unit may be provided between the vibration sensor 70 and the BPF 112.
  • the envelope processing unit receives vibration waveform data of the bearing 60 from the vibration sensor 70
  • the envelope processing unit performs envelope processing on the received vibration waveform data to generate an envelope waveform of the vibration waveform data of the bearing 60.
  • Various known methods can be applied to the envelope processing calculated in the envelope processing unit. For example, the vibration waveform data of the bearing 60 received from the vibration sensor 70 is rectified to an absolute value and passed through the LPF. Thus, an envelope waveform of the vibration waveform data of the bearing 60 is generated.
  • the HPF when the HPF receives the envelope waveform of the vibration waveform data of the bearing 60 from the envelope processing unit, the HPF passes a signal component higher than a predetermined frequency with respect to the received envelope waveform, and the low frequency component Shut off. That is, the HPF is configured to remove a direct current component included in the envelope waveform and extract an alternating current component of the envelope waveform.
  • the effective value calculation unit 120 receives the vibration waveform data of the bearing 60 subjected to the filter processing from the BPF 112. The effective value calculation unit 120 calculates an effective value (RMS value) of the vibration waveform data of the bearing 60 and outputs the calculated effective value of the vibration waveform data to the storage unit 130.
  • RMS value effective value
  • the effective value of the vibration waveform of the bearing 60 calculated by the effective value calculation unit 120 is the effective value of the raw vibration waveform that has not been subjected to the envelope processing, for example, separation occurs in a part of the bearing ring of the bearing 60.
  • the increase in the value is small for the impulse-like vibration in which the vibration increases only when the rolling element passes through the peeled portion, it occurs when the surface of the contact portion between the race ring and the rolling element is rough or poorly lubricated. For continuous vibrations, the value increases.
  • the effective value of the alternating current component of the envelope waveform calculated by the effective value calculating unit 120 is the continuous value generated when the raceway surface is rough or poorly lubricated.
  • the increase in value is small for vibration, and the increase is large for impulse vibration.
  • the storage unit 130 includes a vibration waveform data storage unit 132 and an evaluation value trend storage unit 134.
  • the vibration waveform data storage unit 132 and the evaluation value trend storage unit 134 are configured by, for example, a readable / writable nonvolatile memory.
  • the vibration waveform data storage unit 132 stores the effective value of the vibration waveform data of the bearing 60 calculated by the effective value calculation unit 120 every moment.
  • the vibration waveform data storage unit 132 is configured to store an effective value of vibration waveform data of the bearing 60 within a predetermined time. As will be described later, the effective value of the vibration waveform data of the bearing 60 stored in the vibration waveform data storage unit 132 is read, and the abnormality of the bearing 60 is diagnosed using the read effective value. In the following description, the effective value of the vibration waveform data is simply referred to as “vibration waveform data”.
  • the evaluation value calculation unit 140 calculates an evaluation value that characterizes the read vibration waveform data of the bearing 60 within the predetermined time.
  • the evaluation value calculation unit 140 is configured to calculate the evaluation value continuously in time.
  • the evaluation value trend storage unit 134 receives the evaluation value calculated by the evaluation value calculation unit 140.
  • the evaluation value trend storage unit 134 stores the evaluation value given from the evaluation value calculation unit 140 every moment.
  • the evaluation value trend storage unit 134 is configured to store an evaluation value trend indicating a tendency of the evaluation value to change over time.
  • FIG. 15 is a diagram for explaining operations of the vibration waveform data storage unit 132 and the evaluation value calculation unit 140 shown in FIG.
  • vibration waveform data storage unit 132 receives vibration waveform data of bearing 60 from effective value calculation unit 120 at predetermined time intervals.
  • the predetermined time interval is 1 second.
  • D0 to D11 in FIG. 15 represent vibration waveform data given to the vibration waveform data storage unit 132 at intervals of one second.
  • the vibration waveform data storage unit 132 stores vibration waveform data of the bearing 60 within a predetermined time.
  • the fixed time can be set according to the rotational speed of the main shaft 20.
  • the predetermined time is 10 seconds.
  • the vibration waveform data storage unit 132 stores a total of 10 pieces of vibration waveform data D0 to D9 that are continuous in time (that is, for 10 seconds).
  • the vibration waveform data storage unit 132 When the vibration waveform data storage unit 132 receives the vibration waveform data D10 from the effective value calculation unit 120 at time t1 when 1 second has elapsed from time t0, the oldest vibration waveform among the vibration waveform data D0 to D9 for 10 seconds. While deleting the data D0 and adding the newly input vibration waveform data D10, the vibration waveform data within a predetermined time is updated.
  • the vibration waveform data storage unit 132 deletes the oldest vibration waveform data D1 from the vibration waveform data D1 to D10 for 10 seconds and is newly input. By adding the vibration waveform data D11, the vibration waveform data of the bearing 60 within a predetermined time is updated.
  • the vibration waveform data storage unit 132 updates the vibration waveform data of the bearing 60 within a predetermined time at predetermined time intervals.
  • the evaluation value calculation unit 140 reads vibration waveform data of the bearing 60 from the vibration waveform data storage unit 132 within a predetermined time that is updated at predetermined time intervals.
  • the evaluation value calculation unit 140 calculates an evaluation value by statistically processing the vibration waveform data of the bearing 60 within the read fixed time.
  • the evaluation value calculation unit 140 reads the vibration waveform data D0 to D9 for 10 seconds from the vibration waveform data storage unit 132, and performs statistical processing on the read vibration waveform data D0 to D9. As a result, the evaluation value E0 is calculated.
  • the evaluation value E0 is a value (representative value) that characterizes the vibration waveform data D0 to D9 for 10 seconds immediately before the time t0. Therefore, in the statistical process, for example, an average value of the vibration waveform data D0 to D9 can be calculated as the evaluation value E0. Alternatively, the median value, mode value, minimum value, etc. of the vibration waveform data D0 to D9 can be calculated as the evaluation value E0.
  • the evaluation value calculation unit 140 calculates the evaluation value E1 by statistically processing the vibration waveform data D1 to D10 for 10 seconds.
  • the evaluation value calculator 140 calculates the evaluation value E2 by statistically processing the vibration waveform data D2 to D11 for 10 seconds.
  • the evaluation value calculation unit 140 calculates the evaluation value of the vibration waveform data of the bearing 60 within a predetermined time at predetermined time intervals.
  • the evaluation value calculation unit 140 outputs the calculated evaluation value to the evaluation value trend storage unit 134.
  • FIG. 16 is a diagram for explaining the operation of the evaluation value trend storage unit 134 shown in FIG.
  • evaluation value trend storage unit 134 receives evaluation values from evaluation value calculation unit 140 at predetermined time intervals.
  • the predetermined time interval is set to 1 second.
  • E0 to E6 in FIG. 16 represent evaluation values given from the evaluation value calculation unit 140 to the evaluation value trend storage unit 134 at intervals of 1 second.
  • the evaluation value trend storage unit 134 stores a predetermined number of evaluation values that are continuous in time.
  • the predetermined number of evaluation values that are continuous in time corresponds to an “evaluation value trend” that represents a tendency of the evaluation value to change over time.
  • the predetermined number is 5.
  • the evaluation value trend storage unit 134 stores the evaluation value E0 at time t0, stores the evaluation value E1 at time t1 when 1 second has elapsed from time t0, and at time t2 when 1 second has elapsed from time t1.
  • the evaluation value E2 is stored
  • the evaluation value E3 is stored at time t3 when 1 second has elapsed from time t2
  • the evaluation value E4 is stored at time t4 when 1 second has elapsed from time t3.
  • the evaluation value E3 is calculated by statistically processing vibration waveform data D3 to D12 for 10 seconds immediately before time t3.
  • the evaluation value E4 is calculated by statistically processing vibration waveform data D4 to D13 for 10 seconds immediately before time t4.
  • the evaluation value trend storage unit 134 stores, for example, a total of five evaluation values E0 to E4 at time t5.
  • the evaluation value trend storage unit 134 receives the evaluation values E5 of the vibration waveform data D5 to D14 for 10 seconds immediately before the time t5 from the evaluation value calculation unit 140 at time t6 when 1 second has elapsed from time t5, a total of 5 is obtained.
  • the oldest evaluation value E0 among the evaluation values E0 to E4 is deleted, and a newly input evaluation value E5 is added to update a predetermined number of evaluation values.
  • the evaluation value trend storage unit 134 receives the evaluation value E6 of the vibration waveform data D6 to D15 for 10 seconds immediately before time t6 from the evaluation value calculation unit 140.
  • the oldest evaluation value E1 out of the total of five evaluation values E1 to E5 is deleted, and a newly input evaluation value E6 is added to update a predetermined number of evaluation values.
  • the evaluation value trend storage unit 134 updates a predetermined number of evaluation values (evaluation value trends) that are temporally continuous at predetermined time intervals.
  • the measurement trigger generation unit 180 when the measurement trigger generation unit 180 reads out a predetermined number of evaluation values (evaluation value trends) that are temporally continuous from the evaluation value trend storage unit 134, a vibration waveform is generated based on the read evaluation value trend.
  • a trigger for starting data measurement hereinafter also referred to as “measurement trigger” is generated.
  • the measurement trigger generation unit 180 outputs the generated measurement trigger to the vibration waveform data output unit 170.
  • FIG. 17 is a diagram for explaining the operations of the measurement trigger generation unit 180 and the vibration waveform data output unit 170 shown in FIG. 17 shows the evaluation value trend stored in the evaluation value trend storage unit 134, the measurement trigger generated from the measurement trigger generation unit 180 based on the evaluation value trend, and the bearing 60 output from the vibration waveform data output unit 170.
  • An example of vibration waveform data is shown.
  • Ei-4, Ei-3,... Ei, Ei + 1 represent evaluation values given to the evaluation value trend storage unit 134 at predetermined time intervals.
  • the predetermined time interval is 1 second.
  • Ei represents an evaluation value given to the evaluation value trend storage unit 134 at time ti
  • Ei-1 represents an evaluation value given to the evaluation value trend storage unit 134 at time ti-1
  • Ei + 1 represents an evaluation value trend at time ti + 1.
  • An evaluation value given to the storage unit 134 is shown.
  • the measurement trigger generation unit 180 determines whether or not the evaluation value trend indicating the tendency of the evaluation value over time has changed. When it is determined that the evaluation value trend has changed, the measurement trigger generator 180 generates a measurement trigger. Specifically, the measurement trigger generation unit 180 determines whether or not the evaluation value trend has changed based on the temporal change rate of the evaluation value, that is, the amount of change within the unit time.
  • the measurement trigger generation unit 180 calculates the evaluation value Ei at time ti and the evaluation value Ei ⁇ 1 at time ti + 1. Based on the difference, the temporal change rate of the evaluation value is calculated. If the rate of change of the evaluation value at time ti is dEi, dEi is expressed by equation (2).
  • the measurement trigger generation unit 180 compares the calculated temporal change rate dEi with a predetermined threshold value ⁇ . When the temporal change rate dEi is equal to or greater than the threshold value ⁇ , the measurement trigger generation unit 180 sets the measurement trigger to ON. On the other hand, when the temporal change rate dEi is smaller than the threshold value ⁇ , the measurement trigger generation unit 180 sets the measurement trigger to OFF.
  • FIG. 17 shows a case where the temporal change rate dEi + 1 at time ti + 1 is equal to or greater than the threshold value ⁇ . In this case, at time ti + 1, measurement trigger generator 180 switches the measurement trigger from off to on. The measurement trigger generator 180 outputs the measurement trigger to the vibration waveform data output unit 170.
  • the vibration waveform data output unit 170 When receiving the measurement trigger from the measurement trigger generation unit 180, the vibration waveform data output unit 170 reads the vibration waveform data of the bearing 60 within a predetermined time stored in the vibration waveform data storage unit 132.
  • the vibration waveform data of the bearing 60 within the certain time corresponds to the vibration waveform data of the bearing 60 within the certain time immediately before the time when the measurement trigger is generated.
  • vibration waveform data Di-9 to Di for 10 seconds immediately before time ti + 1 are read from the vibration waveform data storage unit 132.
  • the vibration waveform data output unit 170 receives the vibration waveform data of the bearing 60 after the time ti + 1 from the effective value calculation unit 120.
  • the vibration waveform data output unit 170 receives vibration waveform data Di + 1 to Di + 10 for 10 seconds after time ti + 1 from the effective value calculation unit 120.
  • the vibration waveform data output unit 170 includes vibration waveform data Di-9 to Di of the bearing 60 within a certain time immediately before time ti + 1, which is the time when the measurement trigger is generated, and time ti + 1 and later, which is the time when the measurement trigger is generated.
  • the vibration waveform data Di + 1 to Di + 10 of the bearing 60 are collectively output to the diagnosis unit 150.
  • the diagnosis unit 150 receives the combined vibration waveform data Di-9 to Di + 10 of the bearing 60, and diagnoses the abnormality of the bearing 60 based on the received vibration waveform data Di-9 to Di + 10. That is, the diagnosis unit 150 is configured to start measurement of vibration waveform data when a measurement trigger is generated due to a change in the tendency of the evaluation value to change over time.
  • the evaluation value characterizing the vibration waveform data within a predetermined time is calculated, and the evaluation value temporally indicating the tendency of the evaluation value to change over time is calculated.
  • a trigger for starting measurement of vibration waveform data is generated.
  • the trigger can be generated based on the evaluation value in which the influence of noise superimposed on the vibration waveform data is appropriately eliminated, thus preventing frequent triggers due to the influence of noise. can do.
  • vibration waveform data when a failure occurs in the bearing 60 can be reliably and efficiently measured, an accurate abnormality diagnosis can be realized.
  • the combined vibration waveform data Di-9 to Di + 10 of the bearing 60 supplied to the diagnosis unit 150 is before and after the time point when the measurement trigger occurs, that is, the time point when the tendency of the evaluation value changes. This corresponds to the vibration waveform data of the bearing 60 acquired over the entire time. Therefore, the diagnosis unit 150 can analyze the state of the bearing 60 before and after the time point when the tendency of the evaluation value changes with time by analyzing these vibration waveform data.
  • the vibration waveform data storage unit 132 stores the vibration waveform data of the bearing 60 within a certain time immediately before the time when the measurement trigger is generated, while deleting the vibration waveform data of the bearing 60 when the measurement trigger is not generated. Configured to do. According to this, since the vibration waveform data storage unit 132 only needs to have a storage capacity that can store only data useful for the subsequent investigation, the storage capacity of the memory built in the data processing device 80 is large. It is possible to avoid becoming too much.
  • the vibration waveform data storage unit 132 and the evaluation value trend storage unit 134 are independent from the storage unit for storing the vibration waveform data output from the effective value calculation unit 120 momentarily. Can be configured. In this way, the vibration waveform data storage unit 132 and the evaluation value trend storage unit 134 can be easily added or removed according to the use and situation of the wind power generator 10.
  • FIG. 18 is a flowchart illustrating a control process for storing vibration waveform data of the bearing 60 in the state monitoring system according to the fifth embodiment.
  • the control process shown in FIG. 18 is repeatedly executed by the vibration waveform data storage unit 132 at predetermined time intervals. For example, in the example of FIG. 15, the control process shown in FIG. 18 is repeatedly executed at intervals of 1 second.
  • the vibration waveform data storage unit 132 receives the vibration waveform data of the bearing 60 from the effective value calculation unit 120 in step S21.
  • the vibration waveform data storage unit 132 determines whether or not the number of stored vibration waveform data of the bearing 60 is equal to or greater than a predetermined number X.
  • This predetermined number X is equivalent to the number of vibration waveform data of the bearing 60 acquired within a certain time. In the example of FIG. 15, since the predetermined time is 10 seconds, the predetermined number X is set to “10” that is a value obtained by dividing the predetermined time by a predetermined time interval.
  • the vibration waveform data storage unit 132 proceeds to step S23 and includes the predetermined number X of vibration waveform data. Delete the oldest vibration waveform data. And vibration waveform data storage part 132 adds vibration waveform data acquired at Step S21 by Step S24.
  • the vibration waveform data storage unit 132 proceeds to step S24 and acquires the vibration acquired in step S21. Add waveform data. In this way, the vibration waveform data storage unit 132 updates the vibration waveform data within a predetermined time at predetermined time intervals.
  • FIG. 19 is a flowchart illustrating a control process for generating a measurement trigger for vibration waveform data of the bearing 60 in the state monitoring system according to the fifth embodiment.
  • the control process shown in FIG. 19 is repeatedly executed at predetermined time intervals by the evaluation value calculation unit 140, the evaluation value trend storage unit 134, the measurement trigger generation unit 180, and the vibration waveform data output unit 170.
  • evaluation value calculation unit 140 reads vibration waveform data of bearing 60 within a predetermined time from vibration waveform data storage unit 132 in step S31.
  • the evaluation value calculation unit 140 calculates the evaluation value of the vibration waveform data of the bearing 60 within a predetermined time by performing statistical processing on the vibration waveform data of the bearing 60 within the predetermined time read out at step S31 in step S32.
  • the evaluation value calculation unit 140 outputs the calculated evaluation value to the evaluation value trend storage unit 134.
  • the evaluation value trend storage unit 134 determines whether or not the number of stored evaluation value data is a predetermined number Y or more in step S33.
  • the predetermined number Y corresponds to the number of data necessary for obtaining an evaluation value trend representing a tendency of the evaluation value to change over time.
  • the predetermined number Y is set to a number of 2 or more. In the example of FIG. 15, the predetermined number Y is set to 5.
  • the evaluation value trend storage unit 134 proceeds to step S34 and evaluates the oldest evaluation value among the predetermined number Y of evaluation values. Erase the value. And the evaluation value trend memory
  • the evaluation value trend storage unit 134 proceeds to step S35 and adds the evaluation value calculated in step S32. . In this way, the evaluation value trend storage unit 134 updates the predetermined number Y of evaluation values at predetermined time intervals.
  • step S36 When the measurement trigger generation unit 180 reads out a predetermined number Y of evaluation values (evaluation value trend) continuous in time from the evaluation value trend storage unit 134 in step S36, the temporal change in the evaluation value in the read evaluation value trend. Calculate the rate.
  • step S36 the measurement trigger generation unit 180 reads the evaluation value added in step S35 and the evaluation value added immediately before this evaluation value from the evaluation value trend storage unit 134. Then, the measurement trigger generation unit 180 calculates the temporal change rate of the evaluation value based on the difference between the two read evaluation values using the above equation (2).
  • step S37 the measurement trigger generation unit 180 compares the temporal change rate of the evaluation value calculated in step S36 with the threshold value ⁇ .
  • the temporal change rate of the evaluation value is smaller than the threshold value ⁇ (when NO is determined in S37)
  • the subsequent processes S38 to S31 are skipped.
  • the measurement trigger generation unit 180 when the temporal change rate of the evaluation value is equal to or greater than the threshold value ⁇ (when YES is determined in S37), the measurement trigger generation unit 180 generates a measurement trigger in step S38, and outputs the generated measurement trigger as vibration waveform data. To the unit 170.
  • the vibration waveform data output unit 170 When the vibration waveform data output unit 170 receives the measurement trigger from the measurement trigger generation unit 180, the vibration waveform data output unit 170 is stored in the vibration waveform data storage unit 132 every moment in step S39. Read waveform data.
  • the vibration waveform data output unit 170 further reads out the vibration waveform data of the bearing 60 within a predetermined time stored in the vibration waveform data storage unit 132 in step S40. As described with reference to FIG. 17, the vibration waveform data of the bearing 60 within the certain time corresponds to the vibration waveform data of the bearing 60 within the certain time immediately before the time when the measurement trigger is generated.
  • the vibration waveform data output unit 170 reads the vibration waveform data of the bearing 60 within a certain period of time immediately before the time when the measurement trigger is generated, which is read in step S40 in step S41, and the measurement trigger acquired in step S39.
  • the vibration waveform data of the bearing 60 after the point of occurrence of the failure is collectively output to the diagnosis unit 150.
  • the diagnosis unit 150 diagnoses the abnormality of the bearing 60 using the vibration waveform data of the bearings 60 collected together.
  • the temporal change rate (for example, dEi in FIG. 17) between two temporally continuous evaluation values (for example, the evaluation values Ei ⁇ 1 and Ei in FIG. 17) is calculated.
  • the configuration for generating the measurement trigger has been described based on the result of comparing the calculated temporal change rate and the threshold value ⁇ .
  • the temporal change rate of the evaluation value may temporarily exceed the threshold value ⁇ due to the influence of the noise. In such a case, there is a possibility that the measurement trigger generation unit 180 erroneously generates a measurement trigger.
  • the measurement trigger generation unit 180 continuously receives a determination result that the temporal change rate of the evaluation value is equal to or greater than the threshold value ⁇ . If obtained, it can be configured to generate a measurement trigger. For example, in the example of FIG. 17, the measurement trigger generation unit 180 generates a measurement trigger when it is determined that the temporal change rate dEi + 1 at time ti + 1 and the temporal change rate dEi + 2 at time ti + 2 are both equal to or greater than the threshold value ⁇ . It can be set as the structure to do.
  • the measurement trigger generation unit 180 sets the measurement trigger. Does not occur. Since the increase in the temporal change rate dEi + 1 is considered to be temporary due to the influence of noise, it is possible to prevent the measurement trigger from being erroneously generated.
  • a measurement trigger is generated by determining that the tendency of the temporal change in the evaluation value of the vibration waveform data of the bearing 60 within a predetermined time has changed based on the temporal change rate of the evaluation value.
  • the configuration to be described has been described.
  • a measurement trigger is generated by determining that a tendency of a temporal change in an evaluation value has changed based on the magnitude of the evaluation value will be described.
  • FIG. 20 is a flowchart illustrating a control process for generating a measurement trigger for vibration waveform data of the bearing 60 in the state monitoring system according to the sixth embodiment.
  • the control process shown in FIG. 20 is repeatedly executed at predetermined time intervals by the evaluation value calculation unit 140, the evaluation value trend storage unit 134, the measurement trigger generation unit 180, and the vibration waveform data output unit 170.
  • FIG. 20 is compared with FIG. 19 and the state monitoring system according to the sixth embodiment executes step S37A instead of steps S36 and S37 after the processing of steps S31 to S35 similar to FIG.
  • the measurement trigger generation unit 180 compares the evaluation value added in step S35 with the threshold value ⁇ in step S37A. .
  • the evaluation value is smaller than the threshold ⁇ (when NO is determined in S37A)
  • the subsequent processes S38 to S41 are skipped.
  • the measurement trigger generation unit 180 generates a measurement trigger by the process of step S38 similar to FIG.
  • the vibration waveform data output unit 170 performs the processing of steps S39 to S41 similar to FIG. 19, so that the vibration waveform data of the bearing 60 and the measurement trigger are generated within a certain time immediately before the time when the measurement trigger is generated.
  • the vibration waveform data of the bearing 60 after the time is collectively output to the diagnosis unit 150.
  • the evaluation value that characterizes the vibration waveform data within a predetermined time is calculated, and when the magnitude of the evaluation value becomes equal to or larger than the threshold value ⁇ , the temporal change of the evaluation value is calculated. It is determined that the tendency has changed, and a trigger for starting measurement of vibration waveform data is generated. In this way, the trigger can be generated based on the evaluation value from which the influence of noise superimposed on the vibration waveform data is appropriately eliminated. Therefore, also in the sixth embodiment, the same effect as in the fifth embodiment can be obtained.
  • the measurement trigger generation unit 180 performs measurement when the determination result that the evaluation value is equal to or greater than the threshold value ⁇ is continuously obtained a plurality of times. It can be configured to generate a trigger. For example, in the example of FIG. 17, the measurement trigger generation unit 180 generates a measurement trigger when it is determined that the evaluation value Ei + 1 at time ti + 1 and the evaluation value Ei + 2 at time ti + 2 are both greater than or equal to the threshold value ⁇ . be able to.
  • the measurement trigger generation unit 180 does not generate a measurement trigger. Since the increase in the evaluation value Ei + 1 is considered to be temporary due to the influence of noise, it is possible to prevent the measurement trigger from being erroneously generated.
  • FIG. 21 is a flowchart illustrating a control process for generating a measurement trigger for vibration waveform data of the bearing 60 in the state monitoring system according to the seventh embodiment.
  • the control processing shown in FIG. 21 is repeatedly executed at predetermined time intervals by the evaluation value calculation unit 140, the evaluation value trend storage unit 134, the measurement trigger generation unit 180, and the vibration waveform data output unit 170.
  • FIG. 21 is compared with FIG. 19 and the state monitoring system according to the seventh embodiment executes step S37A in addition to step S37 after the processing of steps S31 to S36 similar to FIG.
  • the measurement trigger generation unit 180 performs the temporal change rate and threshold value ⁇ of the evaluation value calculated in step S36 in step S37.
  • (First threshold) is compared.
  • the temporal change rate of the evaluation value is smaller than the threshold value ⁇ (when NO is determined in S37)
  • the subsequent processes S37A to S41 are skipped.
  • the measurement trigger generation unit 180 proceeds to step S37A, and the evaluation value added in step S35 and the threshold value ⁇ (second The threshold).
  • the evaluation value is smaller than the threshold ⁇ (when NO is determined in S37A)
  • the subsequent processes S38 to S41 are skipped.
  • the measurement trigger generation unit 180 when the evaluation value is equal to or greater than the threshold value ⁇ (when YES is determined in S37A), the measurement trigger generation unit 180 generates a measurement trigger by the process of step S38 similar to FIG.
  • the vibration waveform data output unit 170 performs the processing of steps S39 to S41 similar to FIG. 19, so that the vibration waveform data of the bearing 60 and the measurement trigger are generated within a certain time immediately before the time when the measurement trigger is generated.
  • the vibration waveform data of the bearing 60 after the time is collectively output to the diagnosis unit 150.
  • the evaluation value characterizing the vibration waveform data within a predetermined time is calculated, the temporal change rate of the evaluation value is equal to or higher than the threshold value ⁇ , and the magnitude of the evaluation value is When it becomes more than threshold value (beta), it determines with the tendency of the time change of an evaluation value having changed, and the trigger which starts the measurement of vibration waveform data is generated. Even when the temporal change rate of the evaluation value is equal to or greater than the threshold value ⁇ , when the evaluation value is smaller than the threshold value ⁇ , the degree of vibration, which is the magnitude of vibration of the bearing 60, is small, so It can be determined that the degree of influence has increased.
  • the trigger can be generated based on the evaluation value from which the influence of noise superimposed on the vibration waveform data is appropriately eliminated. Therefore, also in the seventh embodiment, the same effect as in the fifth embodiment can be obtained.
  • the measurement trigger generation unit 180 a determination result that the temporal change rate of the evaluation value is equal to or greater than the threshold value ⁇ is continuously obtained a plurality of times, and a determination result that the evaluation value is equal to or greater than the threshold value ⁇ is obtained multiple times. It can be configured to generate a measurement trigger when obtained continuously. According to this, since the increase in the evaluation value is considered to be temporary due to the influence of noise, it is possible to prevent the measurement trigger from being erroneously generated.
  • the vibration sensor 70 is installed in the bearing 60 that is one of the mechanical elements constituting the wind power generator 10, and the abnormality of the bearing 60 is diagnosed.
  • the point that the machine element to be diagnosed is not limited to the bearing 60 will be described.
  • a vibration sensor is installed in a bearing provided in the speed increaser 40 or in the generator 50 together with or in place of the bearing 60, and the speed increaser 40 is obtained by the same method as in each of the above embodiments.
  • An abnormality of a bearing provided in the generator 50 or in the generator 50 can be diagnosed.
  • the configuration is described in which the evaluation value characterizing the vibration waveform data within a certain time is calculated by statistically processing the effective value of the vibration waveform data within the certain time.
  • the evaluation value may be calculated by statistically processing the peak value of the vibration waveform data within the predetermined time.
  • the peak value of the vibration waveform data corresponds to the absolute value of the maximum value or the minimum value of the vibration waveform.
  • the evaluation value may be calculated by statistically processing the crest factor of the vibration waveform data within the predetermined time.
  • the crest factor of the vibration waveform data corresponds to the ratio of the effective value to the maximum value of the vibration waveform.
  • FIG. 22 is a functional block diagram functionally showing the configuration of the data processing device 80 in the state monitoring system according to Embodiment 8 of the present invention.
  • the data processing device 80 includes a BPF 112, an effective value calculation unit 120, a storage unit 130, a vibration waveform data output unit 170, an evaluation value calculation unit 140, a measurement trigger generation unit 180, And a diagnosis unit 150.
  • the storage unit 130 includes a vibration waveform data storage unit 132, an evaluation value trend storage unit 134, and a normal data storage unit 136.
  • the vibration waveform data storage unit 132, the evaluation value trend storage unit 134, and the normal data storage unit 136 are configured by, for example, a readable / writable nonvolatile memory.
  • the vibration waveform data storage unit 132 is configured to store the effective value (vibration waveform data) of the vibration waveform data of the bearing 60 within a predetermined time, as described with reference to FIG.
  • the normal data storage unit 136 is an effective value (vibration waveform data) of the vibration waveform data of the bearing 60 measured when normal operation of the wind turbine generator 10 (see FIG. 1) is guaranteed (for example, in an initial state). Configured to store.
  • the vibration waveform data stored in the normal data storage unit 136 is used for setting a classification boundary in the learning unit 142 described later.
  • the vibration waveform data stored in the normal data storage unit 136 is also referred to as “learning data”.
  • evaluation value calculation unit 140 calculates an evaluation value that characterizes the read vibration waveform data of the bearing 60 within the predetermined time.
  • evaluation value calculation unit 140 includes a learning unit 142 and an abnormality degree calculation unit 144.
  • the learning unit 142 When the learning unit 142 reads the learning data from the normal data storage unit 136, the learning unit 142 sets a classification boundary for classifying normal and abnormal based on the read learning data.
  • the abnormality degree calculation unit 144 calculates the abnormality degree of the vibration waveform data by applying the classification boundary to the vibration waveform data of the bearing 60 within a certain time read from the vibration waveform data storage unit 132.
  • the degree of abnormality corresponds to the distance from the classification boundary.
  • the calculated degree of abnormality is an evaluation value that characterizes the vibration waveform data of the bearing 60 within the predetermined time.
  • the abnormality degree calculating unit 144 is configured to calculate the abnormality degree continuously in time.
  • the evaluation value calculation unit 140 divides the vibration waveform data into a plurality of segments when processing the vibration waveform data of the bearing 60 within a predetermined time, and processes the data for each segment.
  • the segment will be described.
  • FIG. 23 is a conceptual diagram showing the relationship between the vibration waveform data of the bearing 60 and the segments within a certain time.
  • the vibration waveform data within a fixed time is vibration waveform data D0 to D9 for 10 seconds, as in the example of FIG.
  • the vibration waveform data D0 to D9 for 10 seconds are divided into 10 segments.
  • the abnormality degree calculation unit 144 generates a feature vector for each segment for the vibration waveform data D0 to D9 for 10 seconds.
  • the learning unit 142 generates a feature vector for each segment for the learning data read from the normal data storage unit 136.
  • FIG. 24 is a diagram for explaining the feature quantity vector.
  • FIG. 24 shows an example in which the vibration waveform data D0 to D9 for 10 seconds are divided into 10 segments and the feature quantity is n.
  • the feature amount is, for example, the effective value (OA), maximum value (Max), peak value (Crest factor), kurtosis, skewness, and values after these signal processing (FFT processing, quefrency processing) of the vibration waveform data. It can be.
  • the feature vector handles n feature values as a set of vectors.
  • the feature vector is used for abnormality determination. In the example of FIG. 24, ten feature quantity vectors are generated for vibration waveform data D0 to D9 for 10 seconds.
  • vibration waveform data within a certain time is divided into a plurality of segments, and feature amounts are extracted and feature amount vectors are generated in units of segments.
  • sudden vibration may be temporarily detected by the vibration sensor 70.
  • a correct feature amount can be extracted at a time other than the sudden abnormality. Therefore, it is possible to exclude the segment corresponding to the sudden abnormality and compare and evaluate the feature value for each segment.
  • the degree of abnormality 0 to 9 is calculated for the feature vectors 0 to 9 based on the classification boundary.
  • the classification boundary is an index for performing abnormality determination used in a known abnormality detection method (One Class Support Vector Machine: OC-SVM).
  • FIG. 25 is a diagram for explaining the basic concept of OC-SVM.
  • the vertical axis and the horizontal axis in FIG. 25 a circle mark “ ⁇ ” is learning data, and a square mark “ ⁇ ” and a triangle mark “ ⁇ ” are vibration waveform data.
  • ⁇ is data indicating abnormality
  • ⁇ is data indicating normal.
  • an appropriate feature amount is selected based on the diagnosis target and the operating conditions.
  • the degree of abnormality which is the distance from the classification boundary.
  • the degree of abnormality is zero on the classification boundary, the degree of abnormality is negative ( ⁇ ) on the normal side of the classification boundary, and the degree of abnormality is positive (+) on the abnormal side of the classification boundary.
  • Such a method is called machine learning by OC-SVM, and it is possible to evaluate by converting many feature values into one index (abnormality).
  • the learning unit 142 sets the above-described classification boundary using the learning data.
  • the degree of abnormality calculation unit 144 calculates the degree of abnormality 0 to 9, which is the distance from the classification boundary in the feature section, for each of the feature vectors 0 to 9.
  • the abnormality degree calculation unit 144 calculates the evaluation value E0 by performing statistical processing on the calculated abnormality degrees 0 to 9.
  • the calculation of the evaluation value E0 corresponds to the process of step S32 in the control process shown in FIGS.
  • the evaluation value E0 is a value (representative value) that characterizes the abnormalities 0 to 9 of vibration waveform data for 10 seconds. Therefore, in the statistical process, the average value of the degree of abnormality 0 to 9 can be calculated as the evaluation value E0. Alternatively, the median value, mode value, minimum value, etc. of the degree of abnormality 0 to 9 can be calculated as the evaluation value E0.
  • the abnormality rate may be calculated by comparing the abnormality determination threshold set based on the learning data with each abnormality degree as the evaluation value E0. it can.
  • the abnormality rate is obtained by dividing the number of abnormality degrees 0 to 9 in which the abnormality degree exceeds a predetermined abnormality determination threshold by the total number of segments (10).
  • the evaluation value calculation unit 140 calculates the evaluation value (abnormality) of the vibration waveform data of the bearing 60 within a predetermined time at predetermined time intervals.
  • the evaluation value calculation unit 140 outputs the calculated evaluation value to the evaluation value trend storage unit 134.
  • the evaluation value trend storage unit 134 stores the evaluation value (abnormality) given from the evaluation value calculation unit 140 every moment as described with reference to FIG.
  • a predetermined number of abnormalities that are temporally continuous correspond to an “evaluation value trend” that represents a tendency of temporal change in the abnormal degree.
  • the evaluation value trend storage unit 134 updates the evaluation value trend at predetermined time intervals.
  • the measurement trigger generation unit 180 when the measurement trigger generation unit 180 reads a predetermined number of abnormalities (evaluation values) that are temporally continuous from the evaluation value trend storage unit 134, the measurement trigger generation unit 180 generates a measurement trigger based on the read evaluation value trend. To do. As described with reference to FIG. 16, the measurement trigger generation unit 180 generates a measurement trigger when it is determined that the evaluation value trend has changed. The generated measurement trigger is given to the vibration waveform data output unit 170.
  • the vibration waveform data output unit 170 when the vibration waveform data output unit 170 receives the measurement trigger from the measurement trigger generation unit 180, the vibration waveform data output unit 170 is stored in the vibration waveform data storage unit 132 and is constant immediately before the measurement trigger is generated. The vibration waveform data of the bearing 60 within the time is read. The vibration waveform data output unit 170 further receives vibration waveform data of the bearing 60 from the effective value calculation unit 120 after the time when the measurement trigger is generated. The vibration waveform data output unit 170 collectively outputs these vibration waveform data to the diagnosis unit 150.
  • the diagnosis unit 150 diagnoses an abnormality in the bearing 60 based on the vibration waveform data of the bearing 60 that has been collected.
  • one index generated from a plurality of feature values extracted from the vibration waveform data is used as an evaluation value characterizing the vibration waveform data within a predetermined time.
  • one evaluation value characterizing the vibration waveform data within a predetermined time is set as one, and the change in the temporal change tendency of this one evaluation value is changed as a trigger.
  • a configuration in which the tendency of the temporal change of the plurality of evaluation values is changed may be used as a trigger.
  • the data processing device 80 corresponds to an example of the “processing device” in the present invention
  • the storage unit 130, the evaluation value calculation unit 140, and the diagnosis unit 150 are configured according to the present invention.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Wind Motors (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)

Abstract

This condition monitoring system is provided with a vibration sensor (70) for measuring a vibration waveform of a bearing in a wind power generation device, and a data processing device (80) for diagnosing abnormalities in the bearing. Within the data processing device (80), an evaluation value calculation unit (140) temporally continuously calculates an evaluation value characterizing an effective value of vibration waveform data outputted from the vibration sensor (70) over a certain period. A diagnosis unit (150) diagnoses an abnormality in the bearing on the basis of the shift in the evaluation value changes over time. The evaluation value calculation unit (140) calculates the lowest value of the effective value of the vibration waveform data over a certain period as the evaluation value.

Description

状態監視システムおよび風力発電装置Condition monitoring system and wind power generator
　この発明は、装置を構成する機械要素の状態を監視する状態監視システムに関し、特に、風力発電装置を構成する機械要素の状態を監視する状態監視システムに関する。 The present invention relates to a state monitoring system that monitors the state of a machine element that constitutes a device, and particularly relates to a state monitoring system that monitors the state of a machine element that constitutes a wind turbine generator.
　風力発電装置においては、風力を受けるブレードに接続される主軸を回転させ、増速機により主軸の回転を増速させた上で発電機のロータを回転させることによって発電が行なわれる。主軸ならびに増速機および発電機の回転軸の各々は、転がり軸受によって回転自在に支持されており、そのような軸受の異常を診断する状態監視システム（ＣＭＳ：Condition　Monitoring　System）が知られている。このような状態監視システムにおいては、軸受に固設された振動センサにより測定される振動波形データを用いて、軸受に損傷が発生しているか否かが診断される。 In a wind turbine generator, power generation is performed by rotating a main shaft connected to a blade that receives wind power, rotating the main shaft by a speed increaser, and then rotating a rotor of the power generator. Each of the main shaft, the speed increaser and the rotating shaft of the generator is rotatably supported by a rolling bearing, and a condition monitoring system (CMS: Condition Monitoring System) for diagnosing such a bearing abnormality is known. . In such a state monitoring system, whether or not the bearing is damaged is diagnosed using vibration waveform data measured by a vibration sensor fixed to the bearing.
　一般的な診断システムとして、たとえば、特開２０００－９９４８４号公報（特許文献１）には、被診断対象の計算機の劣化診断を行なう診断システムが開示されている。特許文献１に記載される診断システムは、計算機に関する情報の収集を行なう情報収集ユニットから受信した情報を記憶回路に格納し、記憶回路に格納されている情報を読み出してトレンドグラフを作成するように構成される。特許文献１では、作成したトレンドグラフに基づいて移動平均を求め、移動平均値が予め設定された閾値以下であれば計算機が正常と診断し、移動平均値が閾値以上であれば計算機が異常と診断する。 As a general diagnostic system, for example, Japanese Patent Laid-Open No. 2000-99484 (Patent Document 1) discloses a diagnostic system for performing a deterioration diagnosis of a computer to be diagnosed. The diagnostic system described in Patent Literature 1 stores information received from an information collection unit that collects information about a computer in a storage circuit, and reads the information stored in the storage circuit to create a trend graph. Composed. In Patent Document 1, a moving average is obtained based on the created trend graph. If the moving average value is equal to or less than a preset threshold value, the computer is diagnosed as normal, and if the moving average value is equal to or greater than the threshold value, the computer is abnormal. Diagnose.
　また、演算器等を内蔵する一般的な装置の内部機器の状態を監視する状態監視システムとして、たとえば、特開平７－１５９４６９号公報（特許文献２）には、被測定機器の内部状態を計測する回路から出力される信号に基づいて被測定機器の異常を検出したときに、この検出信号を受けて各計測要素回路および記録部に対して、計測および記録を開始させるトリガを発生させる構成が示されている。 Further, as a state monitoring system for monitoring the state of an internal device of a general apparatus incorporating a computing unit, for example, Japanese Patent Laid-Open No. 7-159469 (Patent Document 2) measures the internal state of a device under measurement. A configuration for generating a trigger for starting measurement and recording for each measurement element circuit and the recording unit in response to detection of an abnormality of the device under measurement based on a signal output from a circuit that performs It is shown.
　また、特開２００９－２００９０号公報（特許文献３）には、機械設備で使用される回転部品および摺動部品の異常を診断する異常診断装置が示されている。この異常診断装置は、回転部品から発生する信号の周波数分析を行なって実測データの周波数成分を求めるとともに、上記実測データの周波数成分から、回転部品の異常に起因する振動の異常周波数に対応した周波数成分を抽出する。そして、この抽出された周波数成分と閾値との比較照合を行なうことにより、回転部品の異常の有無を診断する。特許文献３では、周辺ノイズの影響を受け難くして、異常の有無の診断の精度を向上させるために、上記閾値を、異常周波数の基本波および高調波の周波数ごとに個別に設定している。 Also, Japanese Patent Laid-Open No. 2009-20090 (Patent Document 3) discloses an abnormality diagnosis device for diagnosing abnormalities in rotating parts and sliding parts used in mechanical equipment. This abnormality diagnosis device performs frequency analysis of signals generated from rotating parts to obtain frequency components of actual measurement data, and from the frequency components of the actual measurement data, a frequency corresponding to an abnormal frequency of vibration caused by abnormality of the rotating parts. Extract ingredients. Then, the presence / absence of an abnormality of the rotating component is diagnosed by comparing and collating the extracted frequency component with a threshold value. In Patent Document 3, the threshold is individually set for each of the fundamental wave and the harmonic frequency of the abnormal frequency in order to reduce the influence of ambient noise and improve the accuracy of diagnosis of the presence or absence of abnormality. .
特開２０００－９９４８４号公報JP 2000-99484 A 特開平７－１５９４６９号公報JP-A-7-159469 特開２００９－２００９０号公報JP 2009-20090 A
　風力発電装置に適用される状態監視システムにおいては、主軸ならびに増速機および発電機の回転軸の回転速度が低い場合（たとえば、１００ｒｐｍ以下となる場合）には、回転速度が高い場合に比べて、各々の軸受の振動の大きさが小さくなる。そのため、回転速度が低くなるに従って、振動センサから出力される振動波形データに重畳するノイズの影響が大きくなる。その結果、主軸ならびに増速機および発電機の回転軸の回転速度が低い場合には、誤って軸受の異常と診断される可能性が高くなる。 In the state monitoring system applied to the wind turbine generator, when the rotation speed of the main shaft, the speed increaser, and the rotation shaft of the generator is low (for example, 100 rpm or less), the rotation speed is high. The magnitude of vibration of each bearing is reduced. For this reason, as the rotational speed decreases, the influence of noise superimposed on the vibration waveform data output from the vibration sensor increases. As a result, when the rotational speeds of the main shaft, the speed increaser, and the rotating shaft of the generator are low, there is a high possibility that a bearing abnormality is erroneously diagnosed.
　また、上記の特許文献１に開示される技術に倣って、振動センサから出力される振動波形データの移動平均を求めて軸受の異常を診断しようとすると、ノイズの影響を適切に排除するためには、移動平均に用いられる振動波形データのデータ数を多くする必要があり、却って軸受の振動の大きさの変化を鈍らせてしまうことになる。その結果、特に、軸受の振動の大きさが小さくなる低回転速度において、異常が発生したときの軸受の振動の変化を捉えることが困難となり、正確な軸受の異常診断ができなくなる可能性がある。 In addition, following the technique disclosed in Patent Document 1 described above, if an attempt is made to diagnose a bearing abnormality by obtaining a moving average of vibration waveform data output from the vibration sensor, in order to appropriately eliminate the influence of noise. Therefore, it is necessary to increase the number of vibration waveform data used for the moving average, and on the contrary, the change in the magnitude of the vibration of the bearing is dulled. As a result, it is difficult to detect changes in bearing vibration when an abnormality occurs, particularly at low rotational speeds where the magnitude of the bearing vibration is small, and accurate bearing abnormality diagnosis may not be possible. .
　また、風力発電装置においては、風の吹き方を示す風況などの環境によって運転条件が時々刻々と変化する。この運転条件の変化に従って、振動、主軸の回転速度、発電量、風速などの運転状態も時々刻々と変化する。たとえば、風が強い時期は、風が弱い時期に比べて、風力発電装置の機械要素にかかる荷重が大きくなるため、振動が大きくなる。また、風向きによっても機械要素にかかる荷重が変化するため、振動も変化する。 Also, in the wind power generator, the operating conditions change from moment to moment depending on the environment such as the wind condition indicating how the wind blows. As the operating conditions change, operating conditions such as vibration, spindle rotation speed, power generation amount, and wind speed also change from moment to moment. For example, when the wind is strong, the load applied to the mechanical elements of the wind turbine generator is larger than when the wind is weak, and therefore the vibration is increased. Moreover, since the load applied to the machine element also changes depending on the wind direction, the vibration also changes.
　この結果、風力発電装置に適用される状態監視システムにおいては、振動センサにより測定される振動波形データが風力発電装置の運転条件の変化に従って時々刻々と変化する。振動波形データに基づいて機械要素の異常を正確に診断するためには、振動の変化が運転条件の変化によるものか、機械要素の損傷によるものかを区別する必要がある。これには、異常の有無を診断するために振動波形データと比較照合される閾値を如何に設定するかが重要となる。 As a result, in the state monitoring system applied to the wind turbine generator, the vibration waveform data measured by the vibration sensor changes from moment to moment according to changes in the operating conditions of the wind turbine generator. In order to accurately diagnose an abnormality in a machine element based on vibration waveform data, it is necessary to distinguish whether the change in vibration is due to a change in operating conditions or damage to the machine element. For this purpose, it is important how to set a threshold value to be compared with the vibration waveform data in order to diagnose the presence or absence of abnormality.
　さらに、上記特許文献３に開示される状態監視システムでは、被測定機器の内部状態を計測する回路から出力される信号にノイズが重畳したときに、被測定機器の異常と検出されてトリガが発生される場合が生じる。このような場合には、ノイズの影響を受けて頻繁にトリガが発生されるため、トリガが発生されるたびに、被測定機器の内部状態の計測および記録が開始されることになる。これにより、記録部には、被測定機器が正常であるときのデータと、被測定機器が異常であるときのデータとが混在した状態で、膨大なデータが蓄積されることになる。その結果、記録部に蓄積されるデータに基づいた正確な異常診断ができなくなる可能性がある。 Further, in the state monitoring system disclosed in Patent Document 3, when noise is superimposed on a signal output from a circuit that measures the internal state of the device under measurement, an abnormality is detected in the device under measurement and a trigger is generated. The case where it is done arises. In such a case, since a trigger is frequently generated under the influence of noise, measurement and recording of the internal state of the device under test is started each time the trigger is generated. As a result, a huge amount of data is accumulated in the recording unit in a state where data when the device under measurement is normal and data when the device under measurement is abnormal are mixed. As a result, there is a possibility that accurate abnormality diagnosis based on data accumulated in the recording unit cannot be performed.
　そこで、この発明は、かかる課題を解決するためになされたものであり、第１の目的は、正確な異常診断を実現する状態監視システムおよび風力発電装置を提供することである。 Therefore, the present invention has been made to solve such a problem, and a first object thereof is to provide a state monitoring system and a wind power generator that realize an accurate abnormality diagnosis.
　この発明の第２の目的は、状態監視システムおよびそれを備えた風力発電装置において、風力発電装置を構成する機械要素の異常の有無を診断するための閾値を設定する技術を提供することである。 A second object of the present invention is to provide a technique for setting a threshold value for diagnosing the presence or absence of an abnormality in a machine element constituting a wind power generator in a state monitoring system and a wind power generator equipped with the same. .
　この発明の一態様に係る状態監視システムは、装置を構成する機械要素の状態を監視する状態監視システムであって、機械要素の振動波形を計測するための振動センサと、機械要素の異常を診断するための処理装置とを備える。処理装置は、評価値演算部と、診断部とを含む。評価値演算部は、一定時間内に振動センサから出力される振動波形データの実効値を特徴付ける評価値を、時間的に連続して演算する。診断部は、評価値の時間的変化の推移に基づいて機械要素の異常を診断する。評価値演算部は、評価値として、一定時間内における振動波形データの実効値の最低値を演算するように構成される。 A state monitoring system according to an aspect of the present invention is a state monitoring system for monitoring the state of a machine element constituting the apparatus, and includes a vibration sensor for measuring a vibration waveform of the machine element, and diagnosing abnormality of the machine element And a processing device. The processing device includes an evaluation value calculation unit and a diagnosis unit. The evaluation value calculation unit continuously calculates an evaluation value characterizing the effective value of the vibration waveform data output from the vibration sensor within a predetermined time. The diagnosis unit diagnoses an abnormality of the machine element based on the transition of the temporal change in the evaluation value. The evaluation value calculation unit is configured to calculate the lowest effective value of the vibration waveform data within a predetermined time as the evaluation value.
　この発明の一態様に係る状態監視システムは、機械要素の振動波形を計測するための振動センサと、機械要素の異常を診断するための処理装置とを備える。処理装置は、診断部と、設定部とを含む。診断部は、振動センサから出力される振動波形データの実効値と閾値とを比較することによって、機械要素の異常を診断するように構成される。設定部は、閾値を設定するように構成される。設定部は、振動センサから出力されるｎ個（ｎは２以上の整数）の振動波形データの実効値の移動平均値を演算する第１演算部と、ｎ個の振動波形データの実効値の標準偏差を演算する第２演算部と、第１演算部により演算された移動平均値および第２演算部により演算された標準偏差に基づいて、閾値を演算する第３演算部とを含む。 A state monitoring system according to an aspect of the present invention includes a vibration sensor for measuring a vibration waveform of a machine element, and a processing device for diagnosing an abnormality of the machine element. The processing device includes a diagnosis unit and a setting unit. The diagnosis unit is configured to diagnose an abnormality of the machine element by comparing the effective value of the vibration waveform data output from the vibration sensor with a threshold value. The setting unit is configured to set a threshold value. The setting unit includes a first calculation unit that calculates a moving average value of effective values of n (n is an integer of 2 or more) vibration waveform data output from the vibration sensor, and an effective value of the n vibration waveform data. A second calculation unit that calculates a standard deviation; and a third calculation unit that calculates a threshold based on the moving average value calculated by the first calculation unit and the standard deviation calculated by the second calculation unit.
　この発明の一態様に係る状態監視システムは、機械要素の振動波形を計測するための振動センサと、機械要素の異常を診断するための処理装置とを備える。処理装置は、評価値演算部と、診断部とを含む。評価値演算部は、一定時間内に振動センサから出力される振動波形データを特徴付ける評価値を、時間的に連続して演算するように構成される。診断部は、評価値演算部により演算される評価値の時間的変化の傾向が変化したことをトリガとして振動波形データの計測を開始することにより、振動波形データを用いて機械要素の異常を診断するように構成される。 A state monitoring system according to an aspect of the present invention includes a vibration sensor for measuring a vibration waveform of a machine element, and a processing device for diagnosing an abnormality of the machine element. The processing device includes an evaluation value calculation unit and a diagnosis unit. The evaluation value calculation unit is configured to continuously calculate an evaluation value characterizing the vibration waveform data output from the vibration sensor within a predetermined time. The diagnosis unit uses the vibration waveform data to diagnose abnormalities in machine elements by starting measurement of vibration waveform data triggered by a change in the tendency of the evaluation value calculated by the evaluation value calculation unit over time. Configured to do.
　この発明によれば、機械要素の振動が小さい場合であっても、ノイズの影響が適切に排除された評価値を用いて機械要素の異常を診断することができるため、正確な異常診断を実現することができる。 According to this invention, even when the vibration of the machine element is small, an abnormality of the machine element can be diagnosed using the evaluation value in which the influence of noise is appropriately eliminated, and thus an accurate abnormality diagnosis is realized. can do.
　また、この発明によれば、風力発電装置を構成する機械要素の異常の有無を診断するための閾値を適正に設定することができるため、正確な異常診断を実現することができる。 Further, according to the present invention, since the threshold for diagnosing the presence / absence of abnormality of the mechanical elements constituting the wind turbine generator can be set appropriately, accurate abnormality diagnosis can be realized.
　さらに、この発明によれば、装置を構成する機械要素に異常が生じたときの振動波形データを確実かつ適切に取得することができるため、正確な異常診断を実現することができる。 Furthermore, according to the present invention, vibration waveform data when an abnormality has occurred in a mechanical element constituting the apparatus can be acquired reliably and appropriately, so that an accurate abnormality diagnosis can be realized.
実施の形態１に係る状態監視システムが適用された風力発電装置の構成を概略的に示した図である。It is the figure which showed schematically the structure of the wind power generator to which the state monitoring system which concerns on Embodiment 1 was applied. 図１に示したデータ処理装置の構成を機能的に示す機能ブロック図である。It is a functional block diagram which shows the structure of the data processor shown in FIG. 1 functionally. 記憶部に格納される軸受の振動波形データの実効値の時間的変化を示した図である。It is the figure which showed the time change of the effective value of the vibration waveform data of the bearing stored in a memory | storage part. 一定期間内における振動波形データの実効値の移動平均値の時間的変化を示した図である。It is the figure which showed the time change of the moving average value of the effective value of the vibration waveform data in a fixed period. 評価値演算部によって演算された、一定時間内における振動波形データの実効値の最低値の時間的変化を示した図である。It is the figure which showed the time change of the minimum value of the effective value of the vibration waveform data within the fixed time calculated by the evaluation value calculating part. 実施の形態１に係る状態監視システムにおける軸受の異常を診断するための制御処理を説明するフローチャートである。4 is a flowchart illustrating a control process for diagnosing a bearing abnormality in the state monitoring system according to the first embodiment. 実施の形態２に係る状態監視システムにおける軸受の異常を診断するための制御処理を説明するフローチャートである。10 is a flowchart for explaining a control process for diagnosing a bearing abnormality in the state monitoring system according to the second embodiment. 実施の形態３に係る状態監視システムにおける軸受の異常を診断するための制御処理を説明するフローチャートである。10 is a flowchart illustrating a control process for diagnosing a bearing abnormality in the state monitoring system according to the third embodiment. 実施の形態４に係る状態監視システムにおけるデータ処理装置の構成を機能的に示す機能ブロック図である。It is a functional block diagram which shows functionally the structure of the data processor in the state monitoring system which concerns on Embodiment 4. FIG. 図９に示した閾値設定部の動作を説明する図である。It is a figure explaining operation | movement of the threshold value setting part shown in FIG. 閾値設定部によって設定される閾値の一例を示すグラフである。It is a graph which shows an example of the threshold set by a threshold setting part. 実施の形態４に係る状態監視システムにおける閾値の設定処理を説明するフローチャートである。15 is a flowchart for explaining threshold setting processing in the state monitoring system according to the fourth embodiment. 実施の形態に係る状態監視システムにおける軸受６０の異常を診断するための制御処理を説明するフローチャートである。It is a flowchart explaining the control processing for diagnosing the abnormality of the bearing 60 in the state monitoring system which concerns on embodiment. 実施の形態５に係る状態監視システムにおけるデータ処理装置の構成を機能的に示す機能ブロック図である。FIG. 10 is a functional block diagram functionally showing the configuration of a data processing device in a state monitoring system according to a fifth embodiment. 図１４に示した振動波形データ記憶部および評価値演算部の動作を説明する図である。It is a figure explaining operation | movement of the vibration waveform data storage part and evaluation value calculating part which were shown in FIG. 図１４に示した評価値トレンド記憶部の動作を説明する図である。It is a figure explaining operation | movement of the evaluation value trend memory | storage part shown in FIG. 図１４に示した計測トリガ発生部および振動波形データ出力部の動作を説明する図である。It is a figure explaining operation | movement of the measurement trigger generation part shown in FIG. 14, and a vibration waveform data output part. 実施の形態５に係る状態監視システムにおける軸受の振動波形データを格納するための制御処理を説明するフローチャートである。10 is a flowchart illustrating a control process for storing bearing vibration waveform data in a state monitoring system according to a fifth embodiment. 実施の形態５に係る状態監視システムにおける軸受の振動波形データの計測トリガを発生するための制御処理を説明するフローチャートである。10 is a flowchart for explaining a control process for generating a measurement trigger for vibration waveform data of a bearing in a state monitoring system according to a fifth embodiment. 実施の形態６に係る状態監視システムにおける軸受の振動波形データの計測トリガを発生するための制御処理を説明するフローチャートである。14 is a flowchart illustrating a control process for generating a measurement trigger for vibration waveform data of a bearing in a state monitoring system according to a sixth embodiment. 実施の形態７に係る状態監視システムにおける軸受の振動波形データの計測トリガを発生するための制御処理を説明するフローチャートである。18 is a flowchart for explaining a control process for generating a measurement trigger for vibration waveform data of a bearing in the state monitoring system according to the seventh embodiment. 実施の形態８に係る状態監視システムにおけるデータ処理装置の構成を機能的に示す機能ブロック図である。FIG. 20 is a functional block diagram functionally showing the configuration of a data processing device in a state monitoring system according to an eighth embodiment. 一定時間内における軸受の振動波形データとセグメントとの関係を示す概念図である。It is a conceptual diagram which shows the relationship between the vibration waveform data of a bearing in a fixed time, and a segment. 特徴量ベクトルについて説明するための図である。It is a figure for demonstrating a feature-value vector. ＯＣ－ＳＶＭの基本概念を説明するための図である。It is a figure for demonstrating the basic concept of OC-SVM.
　以下、本発明の実施の形態について、図面を参照しながら詳細に説明する。なお、図中の同一または相当部分には同一符号を付してその説明は繰返さない。 Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference numerals, and the description thereof will not be repeated.
　［実施の形態１］
　図１は、この発明の実施の形態１に係る状態監視システムが適用された風力発電装置の構成を概略的に示した図である。図１を参照して、風力発電装置１０は、主軸２０と、ブレード３０と、増速機４０と、発電機５０と、主軸用軸受（以下、単に「軸受」と称する。）６０と、振動センサ７０と、データ処理装置８０とを備える。増速機４０、発電機５０、軸受６０、振動センサ７０およびデータ処理装置８０は、ナセル９０に格納され、ナセル９０は、タワー１００によって支持される。 [Embodiment 1]
FIG. 1 is a diagram schematically showing a configuration of a wind turbine generator to which a state monitoring system according to Embodiment 1 of the present invention is applied. Referring to FIG. 1, a wind turbine generator 10 includes a main shaft 20, a blade 30, a speed increaser 40, a generator 50, a main shaft bearing (hereinafter simply referred to as “bearing”) 60, and vibration. A sensor 70 and a data processing device 80 are provided. The step-up gear 40, the generator 50, the bearing 60, the vibration sensor 70, and the data processing device 80 are stored in the nacelle 90, and the nacelle 90 is supported by the tower 100.
　主軸２０は、ナセル９０内に進入して増速機４０の入力軸に接続され、軸受６０によって回転自在に支持される。そして、主軸２０は、風力を受けたブレード３０により発生する回転トルクを増速機４０の入力軸へ伝達する。ブレード３０は、主軸２０の先端に設けられ、風力を回転トルクに変換して主軸２０に伝達する。 The main shaft 20 enters the nacelle 90 and is connected to the input shaft of the speed increaser 40 and is rotatably supported by the bearing 60. The main shaft 20 transmits the rotational torque generated by the blade 30 receiving the wind force to the input shaft of the speed increaser 40. The blade 30 is provided at the tip of the main shaft 20 and converts wind force into rotational torque and transmits it to the main shaft 20.
　軸受６０は、ナセル９０内において固設され、主軸２０を回転自在に支持する。軸受６０は、転がり軸受によって構成され、たとえば、自動調芯ころ軸受や円すいころ軸受、円筒ころ軸受、玉軸受等によって構成される。なお、これらの軸受は、単列のものでも複列のものでもよい。 The bearing 60 is fixed in the nacelle 90 and supports the main shaft 20 in a freely rotatable manner. The bearing 60 is composed of a rolling bearing, and is composed of, for example, a self-aligning roller bearing, a tapered roller bearing, a cylindrical roller bearing, or a ball bearing. These bearings may be single row or double row.
　振動センサ７０は、軸受６０に固設される。振動センサ７０は、軸受６０の振動波形を計測し、計測した振動波形データをデータ処理装置８０へ出力する。振動センサ７０は、たとえば、圧電素子を用いた加速度センサによって構成される。 The vibration sensor 70 is fixed to the bearing 60. The vibration sensor 70 measures the vibration waveform of the bearing 60 and outputs the measured vibration waveform data to the data processing device 80. The vibration sensor 70 is constituted by, for example, an acceleration sensor using a piezoelectric element.
　増速機４０は、主軸２０と発電機５０との間に設けられ、主軸２０の回転速度を増速して発電機５０へ出力する。一例として、増速機４０は、遊星ギヤ、中間軸および高速軸等を含む歯車増速機構によって構成される。なお、特に図示はしないが、増速機４０内にも、複数の軸を回転自在に支持する複数の軸受が設けられている。 The speed increaser 40 is provided between the main shaft 20 and the generator 50, and increases the rotational speed of the main shaft 20 to output to the generator 50. As an example, the speed increaser 40 is configured by a gear speed increasing mechanism including a planetary gear, an intermediate shaft, a high speed shaft, and the like. In addition, although not specifically illustrated, a plurality of bearings that rotatably support a plurality of shafts are also provided in the speed increaser 40.
　発電機５０は、増速機４０の出力軸に接続され、増速機４０から受ける回転トルクによって発電する。発電機５０は、たとえば、誘導発電機によって構成される。なお、発電機５０内にも、ロータを回転自在に支持する軸受が設けられている。 The generator 50 is connected to the output shaft of the speed increaser 40 and generates power by the rotational torque received from the speed increaser 40. The generator 50 is constituted by, for example, an induction generator. A bearing for rotatably supporting the rotor is also provided in the generator 50.
　データ処理装置８０は、ナセル９０内に設けられ、軸受６０の振動波形データを振動センサ７０から受ける。データ処理装置８０は、予め設定されたプログラムに従って、軸受６０の振動波形データを用いて軸受６０の異常を診断する。 The data processing device 80 is provided in the nacelle 90 and receives vibration waveform data of the bearing 60 from the vibration sensor 70. The data processing device 80 diagnoses the abnormality of the bearing 60 using the vibration waveform data of the bearing 60 according to a preset program.
　図２は、図１に示したデータ処理装置８０の構成を機能的に示す機能ブロック図である。図２を参照して、データ処理装置８０は、ローパスフィルタ（以下、「ＬＰＦ（Low　Pass　Filter）」と称する。）１１０と、実効値演算部１２０と、記憶部１３０と、評価値演算部１４０と、診断部１５０と、閾値設定部１６０とを含む。 FIG. 2 is a functional block diagram functionally showing the configuration of the data processing device 80 shown in FIG. Referring to FIG. 2, the data processing device 80 includes a low-pass filter (hereinafter referred to as “LPF (Low Pass Filter)”) 110, an effective value calculation unit 120, a storage unit 130, and an evaluation value calculation unit 140. And a diagnosis unit 150 and a threshold setting unit 160.
　ＬＰＦ１１０は、軸受６０の振動波形データを振動センサ７０から受ける。ＬＰＦ１１０は、その受けた振動波形データにつき、予め定められた周波数（たとえば、４００Ｈｚ）よりも低い信号成分を通過させ、高周波成分を遮断する。 LPF 110 receives vibration waveform data of bearing 60 from vibration sensor 70. The LPF 110 passes a signal component lower than a predetermined frequency (for example, 400 Hz) in the received vibration waveform data, and blocks the high frequency component.
　実効値演算部１２０は、軸受６０の振動波形データをＬＰＦ１１０から受ける。実効値演算部１２０は、軸受６０の振動波形データの実効値（「ＲＭＳ（Root　Mean　Square）値」とも称される。）を算出し、その算出された振動波形データの実効値を記憶部１３０へ出力する。 The effective value calculation unit 120 receives the vibration waveform data of the bearing 60 from the LPF 110. The effective value calculation unit 120 calculates an effective value (also referred to as “RMS (Root Mean Square) value”) of the vibration waveform data of the bearing 60, and stores the calculated effective value of the vibration waveform data in the storage unit 130. Output to.
　記憶部１３０は、実効値演算部１２０により演算された軸受６０の振動波形データの実効値を時々刻々と格納する。記憶部１３０は、たとえば、読み書き可能な不揮発性のメモリ等によって構成される。 The storage unit 130 stores the effective value of the vibration waveform data of the bearing 60 calculated by the effective value calculating unit 120 every moment. The storage unit 130 is configured by, for example, a readable / writable nonvolatile memory.
　記憶部１３０は、少なくとも一定時間内における軸受６０の振動波形データの実効値を格納するように構成される。記憶部１３０は、たとえば、所定の時間間隔で、軸受６０の振動波形データを実効値演算部１２０から受けると、一定時間内における振動波形データの実効値のうちの最も古い振動波形データの実効値を消去するとともに、新たに入力された振動波形データの実効値を追加するように構成される。 The storage unit 130 is configured to store an effective value of vibration waveform data of the bearing 60 at least within a predetermined time. For example, when the storage unit 130 receives the vibration waveform data of the bearing 60 from the effective value calculation unit 120 at a predetermined time interval, the effective value of the oldest vibration waveform data among the effective values of the vibration waveform data within a predetermined time. And an effective value of newly inputted vibration waveform data is added.
　すなわち、記憶部１３０は、所定の時間間隔で、一定時間内における軸受６０の振動波形データの実効値を更新する。後述するように、記憶部１３０に格納された一定時間内における軸受６０の振動波形データの実効値が読み出され、その読み出された実効値を用いて軸受６０の異常が診断される。 That is, the storage unit 130 updates the effective value of the vibration waveform data of the bearing 60 within a predetermined time at predetermined time intervals. As will be described later, the effective value of the vibration waveform data of the bearing 60 stored in the storage unit 130 within a predetermined time is read, and the abnormality of the bearing 60 is diagnosed using the read effective value.
　評価値演算部１４０は、一定時間内における軸受６０の振動波形データの実効値を記憶部１３０から読み出すと、読み出した一定時間内における振動波形データの実効値を特徴付ける評価値を演算する。評価値演算部１４０は、評価値を時間的に連続して演算するように構成される。すなわち、評価値演算部１４０は、所定の時間間隔で、評価値を更新する。評価値演算部１４０における評価値の演算の詳細については後述する。 When the effective value of the vibration waveform data of the bearing 60 within a predetermined time is read from the storage unit 130, the evaluation value calculating unit 140 calculates an evaluation value that characterizes the read effective value of the vibration waveform data within the predetermined time. The evaluation value calculation unit 140 is configured to calculate the evaluation value continuously in time. That is, the evaluation value calculation unit 140 updates the evaluation value at a predetermined time interval. Details of the evaluation value calculation in the evaluation value calculation unit 140 will be described later.
　閾値設定部１６０は、診断部１５０において軸受６０の異常の有無を診断するために用いられる閾値を設定する。閾値設定部１６０は、設定された閾値を診断部１５０へ出力する。閾値設定部１６０における閾値の設定の詳細については後述する。 The threshold value setting unit 160 sets a threshold value used for diagnosing the presence or absence of abnormality of the bearing 60 in the diagnosis unit 150. The threshold setting unit 160 outputs the set threshold to the diagnosis unit 150. Details of threshold setting in the threshold setting unit 160 will be described later.
　診断部１５０は、評価値を評価値演算部１４０から受け、閾値を閾値設定部１６０から受ける。診断部１５０は、評価値と閾値とを比較することにより、軸受６０の異常を診断する。具体的には、評価値が閾値より大きい場合、診断部１５０は軸受６０が異常であると診断する。一方、評価値が閾値以下である場合、診断部１５０は軸受６０が正常であると診断する。 The diagnosis unit 150 receives an evaluation value from the evaluation value calculation unit 140 and a threshold value from the threshold value setting unit 160. The diagnosis unit 150 diagnoses an abnormality in the bearing 60 by comparing the evaluation value with a threshold value. Specifically, when the evaluation value is larger than the threshold value, the diagnosis unit 150 diagnoses that the bearing 60 is abnormal. On the other hand, when the evaluation value is less than or equal to the threshold value, the diagnosis unit 150 diagnoses that the bearing 60 is normal.
　以下、図３から図５を参照して、評価値演算部１４０における評価値の演算について説明する。 Hereinafter, the evaluation value calculation in the evaluation value calculation unit 140 will be described with reference to FIGS.
　図３は、記憶部１３０に格納される軸受６０の振動波形データの実効値の時間的変化を示した図である。図３は、主軸２０の回転速度が低い場合（たとえば、１００ｒｐｍ以下）における軸受６０の振動波形データの実効値の時間的変化の一例を示している。 FIG. 3 is a diagram showing temporal changes in the effective value of the vibration waveform data of the bearing 60 stored in the storage unit 130. FIG. 3 shows an example of a temporal change in the effective value of the vibration waveform data of the bearing 60 when the rotation speed of the main shaft 20 is low (for example, 100 rpm or less).
　図３では、ある時刻ｔにて、軸受６０を異常品から新品に交換する場合を想定している。すなわち、時刻ｔよりも前の期間は、軸受６０に異常が発生している異常発生期間を示し、時刻ｔよりも後の期間は、軸受６０が正常な状態である正常期間を示している。 FIG. 3 assumes a case where the bearing 60 is replaced from an abnormal product to a new product at a certain time t. That is, a period before time t indicates an abnormality occurrence period in which an abnormality has occurred in the bearing 60, and a period after time t indicates a normal period in which the bearing 60 is in a normal state.
　図３に示されるように、異常発生期間における振動波形データの実効値、および正常期間における振動波形データの実効値はいずれも大きく変化している。主軸２０の回転速度が低い場合には、軸受６０の振動が小さくなる。そのため、振動センサ７０から出力される振動波形データは、ノイズの影響が顕著となり、大きく変化する。 As shown in FIG. 3, the effective value of the vibration waveform data during the abnormality occurrence period and the effective value of the vibration waveform data during the normal period both change greatly. When the rotational speed of the main shaft 20 is low, the vibration of the bearing 60 is reduced. Therefore, the vibration waveform data output from the vibration sensor 70 is greatly affected by noise and changes greatly.
　ここで、図３に示される振動波形データの実効値の時間的変化に基づいて、軸受６０の異常の有無を診断するための閾値を設定することを試みる。 Here, an attempt is made to set a threshold for diagnosing the presence or absence of an abnormality in the bearing 60 based on the temporal change in the effective value of the vibration waveform data shown in FIG.
　図３に示されるように、異常発生期間における振動波形データの実効値の全てを下回るように閾値を設定すると、正常期間における振動波形データの実効値の大部分が閾値を超えてしまう。その結果、軸受６０が正常な状態であるにも拘わらす、軸受６０が異常であると誤って診断されることになる。 As shown in FIG. 3, when the threshold value is set so as to be less than all of the effective values of the vibration waveform data in the abnormality occurrence period, most of the effective values of the vibration waveform data in the normal period exceed the threshold value. As a result, although the bearing 60 is in a normal state, the bearing 60 is erroneously diagnosed as being abnormal.
　そこで、本実施の形態では、一定時間内における振動波形データの実効値を特徴付ける評価値を演算し、その演算された評価値を用いて軸受６０の異常を診断するものとする。評価値は、一定時間内における振動波形データの実効値を統計処理することによって演算することができる。上記統計処理としては、たとえば移動平均化処理を用いることができる。 Therefore, in the present embodiment, an evaluation value characterizing the effective value of the vibration waveform data within a predetermined time is calculated, and the abnormality of the bearing 60 is diagnosed using the calculated evaluation value. The evaluation value can be calculated by statistically processing the effective value of the vibration waveform data within a certain time. As the statistical process, for example, a moving average process can be used.
　図４は、一定期間内における振動波形データの実効値の移動平均値の時間的変化を示した図である。図４は、図３に示した振動波形データの実効値の時間的変化に対して移動平均化処理を施したものである。なお、移動平均化処理では、一定時間を実効値２４個分に相当する時間とし、２４個分の実効値の単純移動平均値を演算している。 FIG. 4 is a diagram showing a temporal change in the moving average value of the effective value of the vibration waveform data within a certain period. FIG. 4 is obtained by performing a moving averaging process on the temporal change of the effective value of the vibration waveform data shown in FIG. In the moving averaging process, a fixed time is set as a time corresponding to 24 effective values, and a simple moving average value of 24 effective values is calculated.
　図４に示される移動平均値の時間的変化と、図３に示される振動波形データの実効値の時間的変化とを比較すると、移動平均値は実効値に比べて変化の大きさが小さくなっていることから、ノイズの影響が低減されていることが分かる。 When the temporal change of the moving average value shown in FIG. 4 is compared with the temporal change of the effective value of the vibration waveform data shown in FIG. 3, the moving average value has a smaller magnitude of change than the effective value. Thus, it can be seen that the influence of noise is reduced.
　ここで、図３と同様に、図４に示される移動平均値の時間的変化に基づいて、軸受６０の異常の有無を診断するための閾値を設定することを試みる。 Here, as in FIG. 3, an attempt is made to set a threshold value for diagnosing the presence or absence of abnormality of the bearing 60 based on the temporal change of the moving average value shown in FIG.
　図４に示されるように、異常発生期間における移動平均値の全てを下回るように閾値を設定すると、正常期間における移動平均値の一部に閾値を超えるものが現れる。その結果、図３と同様に、軸受６０が正常な状態であるにも拘わらす、軸受６０が異常であると誤って診断されることになる。 As shown in FIG. 4, when the threshold value is set so as to be lower than all the moving average values during the abnormality occurrence period, some of the moving average values during the normal period exceed the threshold value. As a result, as in FIG. 3, the bearing 60 is erroneously diagnosed as being abnormal even though the bearing 60 is in a normal state.
　ここで、移動平均値の変化の大きさを更に小さくするためには、移動平均化処理において、一定期間の長さを実効値２４個分の長さよりもさらに長くすることが考えられる。しかしながら、一定時間の長さを長くすると、ノイズの影響を低減することができる一方で、軸受６０の振動の大きさの変化も鈍らせてしまうことになる。その結果、異常が発生したときの軸受６０の振動の変化を捉えることが困難となり、正確な軸受６０の異常診断ができなくなる可能性がある。 Here, in order to further reduce the magnitude of the change in the moving average value, in the moving averaging process, it is conceivable to make the length of the certain period longer than the length of 24 effective values. However, if the length of the predetermined time is increased, the influence of noise can be reduced, but the change in the magnitude of vibration of the bearing 60 is also dulled. As a result, it becomes difficult to capture changes in the vibration of the bearing 60 when an abnormality occurs, and there is a possibility that an accurate diagnosis of the abnormality of the bearing 60 cannot be performed.
　そこで、評価値演算部１４０では、一定時間内における振動波形データの実効値を特徴付ける評価値として、当該一定時間内における振動波形データの最低値を演算する。 Therefore, the evaluation value calculation unit 140 calculates the minimum value of the vibration waveform data within the certain time as an evaluation value characterizing the effective value of the vibration waveform data within the certain time.
　図５は、評価値演算部１４０によって演算された、一定時間内における振動波形データの実効値の最低値の時間的変化を示した図である。図５では、図３に示した振動波形データの実効値の時間的変化に対して、一定時間内における実効値の最低値を時間的に連続して演算している。なお、図５では、一定時間を、図４の移動平均値を算出したときの一定時間と同じ長さ（すなわち、実効値２４個分の長さ）に設定している。 FIG. 5 is a diagram showing a temporal change of the minimum value of the effective value of the vibration waveform data within a predetermined time calculated by the evaluation value calculation unit 140. In FIG. 5, the minimum value of the effective value within a fixed time is continuously calculated with respect to the temporal change of the effective value of the vibration waveform data shown in FIG. In FIG. 5, the fixed time is set to the same length as the fixed time when the moving average value in FIG. 4 is calculated (that is, a length corresponding to 24 effective values).
　図５に示される最低値の時間的変化と、図４に示される移動平均値の時間的変化とを比較すると、最低値は、移動平均値に比べて変化の大きさが小さくなっている。特に、正常期間においてその傾向が顕著であることから、ノイズの影響がより一層低減されていることが分かる。 When comparing the temporal change of the minimum value shown in FIG. 5 and the temporal change of the moving average value shown in FIG. 4, the magnitude of the change of the minimum value is smaller than the moving average value. In particular, since the tendency is remarkable in the normal period, it can be seen that the influence of noise is further reduced.
　軸受６０の振動波形データの実効値は、本来の軸受６０の振動の大きさに対してノイズの大きさが上乗せされた状態となっている。これによれば、一定時間内における振動波形データの実効値の最低値は、当該一定時間内における振動波形データの実効値の中でも最もノイズの影響が小さいものであると解することができる。したがって、この最低値を評価値とすることで、軸受６０の振動が小さい場合であっても、軸受６０の振動波形データの実効値へのノイズの影響を効果的に低減することができる。その結果、より正確な異常診断を実現することが可能となる。 The effective value of the vibration waveform data of the bearing 60 is in a state where the magnitude of noise is added to the magnitude of the vibration of the original bearing 60. According to this, it can be understood that the minimum value of the effective value of the vibration waveform data within a certain time is the smallest value of the influence of noise among the effective values of the vibration waveform data within the certain time. Therefore, by setting this minimum value as the evaluation value, even when the vibration of the bearing 60 is small, the influence of noise on the effective value of the vibration waveform data of the bearing 60 can be effectively reduced. As a result, a more accurate abnormality diagnosis can be realized.
　図２に戻って、閾値設定部１６０は、評価値演算部１４０によって演算された一定時間内における振動波形データの実効値の最低値の時間的変化に基づいて、閾値を設定する。図５の例では、異常発生期間における最低値の時間的変化の推移よりも小さく、かつ、正常期間における最低値の時間的変化の推移よりも大きい値に閾値を設定することができる。これは、一定時間内における振動波形データの実効値の最低値と閾値とを比較することによって、軸受６０の異常の有無を診断できることを表わしている。 2, the threshold setting unit 160 sets the threshold based on the temporal change of the lowest effective value of the vibration waveform data within a certain time calculated by the evaluation value calculating unit 140. In the example of FIG. 5, the threshold can be set to a value that is smaller than the transition of the temporal change of the lowest value during the abnormality occurrence period and larger than the transition of the temporal change of the lowest value during the normal period. This indicates that the presence or absence of an abnormality in the bearing 60 can be diagnosed by comparing the minimum value of the effective value of the vibration waveform data within a certain time with a threshold value.
　具体的には、閾値設定部１６０は、図５に示されるような、異常発生期間および正常期間の各々における最低値の時間的変化が取得されると、異常発生期間における最低値の時間的変化から所定数の最低値を抽出し、その抽出された所定数の最低値の平均値を演算する。閾値設定部１６０は、また、正常期間における最低値の時間的変化から所定数の最低値を抽出し、その抽出された所定数の最低値の平均値を演算する。閾値設定部１６０は、正常期間における平均値と異常発生期間における平均値との比を算出し、この算出された比よりも小さい値に係数を設定する。そして、設定した係数と正常期間における平均値とを掛け算することにより、閾値を演算する。 Specifically, the threshold value setting unit 160, when the temporal change of the minimum value in each of the abnormality occurrence period and the normal period as shown in FIG. 5 is acquired, the temporal change of the lowest value in the abnormality occurrence period. A predetermined number of minimum values are extracted from the above, and an average value of the extracted predetermined number of minimum values is calculated. The threshold setting unit 160 also extracts a predetermined number of minimum values from the temporal change of the minimum value in the normal period, and calculates the average value of the extracted predetermined minimum values. The threshold setting unit 160 calculates a ratio between the average value in the normal period and the average value in the abnormality occurrence period, and sets the coefficient to a value smaller than the calculated ratio. Then, the threshold value is calculated by multiplying the set coefficient by the average value in the normal period.
　図６は、実施の形態１に係る状態監視システムにおける軸受６０の異常を診断するための制御処理を説明するフローチャートである。図６に示される制御処理は、データ処理装置８０により、所定の時間間隔で繰り返し実行される。 FIG. 6 is a flowchart illustrating a control process for diagnosing an abnormality of the bearing 60 in the state monitoring system according to the first embodiment. The control process shown in FIG. 6 is repeatedly executed by the data processing device 80 at predetermined time intervals.
　図６を参照して、データ処理装置８０は、ステップＳ０１により、軸受６０の振動波形データを振動センサ７０から受ける。データ処理装置８０は、ステップＳ０２により、風力発電装置１０において所定の運転状態が成立しているか否かを判定する。所定の運転状態とは、風力発電装置１０が定格運転しているときの運転状態であり、定格運転時における主軸２０ならびに増速機４０および発電機５０の回転軸の回転速度、発電量、発電機５０の回転軸のトルク、風向および風速などを含んでいる。 Referring to FIG. 6, the data processing device 80 receives vibration waveform data of the bearing 60 from the vibration sensor 70 in step S01. In step S02, the data processing device 80 determines whether or not a predetermined operation state is established in the wind turbine generator 10. The predetermined operation state is an operation state when the wind power generator 10 is performing a rated operation, and the rotational speed, power generation amount, power generation of the main shaft 20, the speed increaser 40, and the generator 50 during the rated operation. This includes the torque, wind direction, and wind speed of the rotating shaft of the machine 50.
　風力発電装置１０において所定の運転状態が成立していない場合（Ｓ０２のＮＯ判定時）、以降の処理Ｓ０３～Ｓ０９がスキップされる。一方、風力発電装置１０において所定の運転状態が成立している場合（Ｓ０２のＹＥＳ判定時）、ＬＰＦ１１０は、軸受６０の振動波形データに対してフィルタ処理を実行する。 If the predetermined operating state is not established in the wind turbine generator 10 (NO determination in S02), the subsequent processes S03 to S09 are skipped. On the other hand, when the predetermined operation state is established in the wind turbine generator 10 (when YES is determined in S02), the LPF 110 performs a filtering process on the vibration waveform data of the bearing 60.
　次に、ステップＳ０４により、フィルタ処理が施された軸受６０の振動波形データをＬＰＦ１１０から受けると、実効値演算部１２０は、軸受６０の振動波形データの実効値を算出する。記憶部１３０は、ステップＳ０５により、実効値演算部１２０によって算出された振動波形データの実効値を格納する。 Next, when the vibration waveform data of the bearing 60 subjected to the filtering process is received from the LPF 110 in step S04, the effective value calculation unit 120 calculates the effective value of the vibration waveform data of the bearing 60. The storage unit 130 stores the effective value of the vibration waveform data calculated by the effective value calculation unit 120 in step S05.
　評価値演算部１４０は、ステップＳ０６により、記憶部１３０に格納されている振動波形データの実効値のデータ数が規定個数を満たしているか否かを判定する。ステップＳ０６において、規定個数は、一定時間内において時間的に連続する振動波形データの実効値の個数に値する。記憶部１３０に格納されている振動波形データの実効値のデータ数が規定個数に満たない場合（Ｓ０６のＮＯ判定時）、以降の処理Ｓ０６～Ｓ０９はスキップされる。 The evaluation value calculation unit 140 determines whether or not the number of effective values of the vibration waveform data stored in the storage unit 130 satisfies the specified number in step S06. In step S06, the specified number is equal to the number of effective values of vibration waveform data that are temporally continuous within a fixed time. When the number of effective values of the vibration waveform data stored in the storage unit 130 is less than the specified number (when NO is determined in S06), the subsequent processes S06 to S09 are skipped.
　一方、格納されている振動波形データの実効値のデータ数が規定個数を満たしている場合（Ｓ０６のＹＥＳ判定時）、評価値演算部１４０は、ステップＳ０７に進み、記憶部１３０に格納される規定個数の振動波形データの実効値を読み出し、読み出された規定個数の振動波形データの実効値の最低値を演算する。評価値演算部１４０は、演算された最低値を診断部１５０へ出力する。 On the other hand, if the number of effective values of the stored vibration waveform data satisfies the specified number (when YES in S06), the evaluation value calculation unit 140 proceeds to step S07 and is stored in the storage unit 130. The effective value of the specified number of vibration waveform data is read, and the lowest effective value of the read specified number of vibration waveform data is calculated. The evaluation value calculation unit 140 outputs the calculated minimum value to the diagnosis unit 150.
　診断部１５０は、ステップＳ０８により、ステップＳ０７で演算された最低値と閾値とを比較する。最低値が閾値以下である場合（Ｓ０８のＮＯ判定時）、診断部１５０は、軸受６０が正常であると診断して、以降の処理Ｓ０９をスキップする。一方、ステップＳ０７で演算した最低値が閾値よりも大きい場合（Ｓ０８のＹＥＳ判定時）、診断部１５０は、ステップＳ０９により、軸受６０が異常であると診断する。 The diagnosis unit 150 compares the minimum value calculated in step S07 with the threshold value in step S08. When the minimum value is less than or equal to the threshold (NO in S08), the diagnosis unit 150 diagnoses that the bearing 60 is normal and skips the subsequent process S09. On the other hand, when the lowest value calculated in step S07 is larger than the threshold value (when YES is determined in S08), diagnosis unit 150 diagnoses that bearing 60 is abnormal in step S09.
　以上のように、実施の形態１によれば、一定時間内における軸受６０の振動波形データの実効値を特徴付ける評価値として、当該一定時間内における振動波形データの実効値の最低値を用いることにより、主軸２０の回転速度が低く、振動波形データの実効値が小さい場合であっても、ノイズの影響が低減された評価値を得ることができる。これにより、評価値を用いて正常な軸受６０の異常診断を実現することができる。 As described above, according to the first embodiment, as the evaluation value characterizing the effective value of the vibration waveform data of the bearing 60 within a certain time, the lowest value of the effective value of the vibration waveform data within the certain time is used. Even when the rotation speed of the spindle 20 is low and the effective value of the vibration waveform data is small, an evaluation value with reduced influence of noise can be obtained. Thereby, normal abnormality diagnosis of the bearing 60 can be realized using the evaluation value.
　なお、上述の実施の形態１では、評価値と閾値とを比較することにより軸受６０の異常を診断する構成について説明したが、評価値を用いた軸受６０の異常診断は上記構成に限定されない。実施の形態２および３では、評価値を用いた異常診断の他の構成例について説明する。 In the above-described first embodiment, the configuration for diagnosing the abnormality of the bearing 60 by comparing the evaluation value and the threshold value has been described. However, the abnormality diagnosis of the bearing 60 using the evaluation value is not limited to the above configuration. In Embodiments 2 and 3, other configuration examples of abnormality diagnosis using evaluation values will be described.
　［実施の形態２］
　図７は、実施の形態２に係る状態監視システムにおける軸受６０の異常を診断するための制御処理を説明するフローチャートである。図７に示される制御処理は、データ処理装置８０により、所定の時間間隔で繰り返し実行される。 [Embodiment 2]
FIG. 7 is a flowchart for explaining a control process for diagnosing abnormality of the bearing 60 in the state monitoring system according to the second embodiment. The control processing shown in FIG. 7 is repeatedly executed by the data processing device 80 at predetermined time intervals.
　図７を図６と比較して、実施の形態２に係る状態監視システムでは、図６と同様のステップＳ０１～Ｓ０７の処理後に、ステップＳ０８に代えて、ステップＳ０８Ａを実行する。 FIG. 7 is compared with FIG. 6, the state monitoring system according to the second embodiment executes step S08A instead of step S08 after the processing of steps S01 to S07 similar to FIG.
　すなわち、ステップＳ０７により、評価値演算部１４０が、記憶部１３０から読み出された規定個数の振動波形データの実効値の最低値を演算すると、診断部１５０は、ステップＳ０８Ａにより、最低値の時間的変化率、すなわち単位時間内の変化量に基づいて、軸受６０の異常の有無を診断する。 That is, when the evaluation value calculation unit 140 calculates the minimum value of the effective values of the prescribed number of vibration waveform data read from the storage unit 130 in step S07, the diagnosis unit 150 determines the minimum value time in step S08A. The presence / absence of abnormality of the bearing 60 is diagnosed based on the rate of change, that is, the amount of change in unit time.
　具体的には、評価値演算部１４０は、ステップＳ０７で算出された最低値と、この最低値の１つ前に算出された最低値との差に基づいて、最低値の時間的変化率を演算する。そして、評価値演算部１４０は、演算された最低値の時間的変化率と閾値とを比較する。最低値の時間的変化率が閾値以下である場合（Ｓ０８ＡのＮＯ判定時）、診断部１５０は、軸受６０が正常であると診断して、以降の処理Ｓ０９をスキップする。一方、最低値の時間的変化率が閾値よりも大きい場合（Ｓ０８ＡのＹＥＳ判定時）、診断部１５０は、ステップＳ０９により、軸受６０が異常であると診断する。 Specifically, the evaluation value calculation unit 140 calculates the temporal change rate of the lowest value based on the difference between the lowest value calculated in step S07 and the lowest value calculated immediately before this lowest value. Calculate. Then, the evaluation value calculation unit 140 compares the calculated minimum value temporal change rate with a threshold value. When the temporal change rate of the minimum value is equal to or less than the threshold (when NO in S08A), the diagnosis unit 150 diagnoses that the bearing 60 is normal and skips the subsequent process S09. On the other hand, when the temporal change rate of the minimum value is larger than the threshold value (when YES is determined in S08A), diagnosis unit 150 diagnoses that bearing 60 is abnormal in step S09.
　以上のように、実施の形態２によれば、一定時間内における軸受６０の振動波形データの実効値を特徴付ける評価値として、当該一定時間内における振動波形データの実効値の最低値を用いて軸受６０の異常を診断する。したがって、実施の形態２においても、実施の形態１と同様の効果を得ることができる。 As described above, according to the second embodiment, the evaluation value characterizing the effective value of the vibration waveform data of the bearing 60 within a predetermined time is used as the evaluation value to characterize the bearing using the minimum value of the effective value of the vibration waveform data within the predetermined time. Diagnose 60 abnormalities. Therefore, also in the second embodiment, the same effect as in the first embodiment can be obtained.
　なお、図７のステップＳ０８Ａにおいて用いられる閾値は、閾値設定部１６０において、正常期間における最低値の時間的変化率よりも大きく、かつ、異常発生期間における最低値の時間的変化率よりも小さい値に設定することができる。 Note that the threshold value used in step S08A of FIG. 7 is a value larger than the temporal change rate of the lowest value in the normal period and smaller than the temporal change rate of the lowest value in the abnormality occurrence period in the threshold setting unit 160. Can be set to
　具体的には、閾値設定部１６０は、異常発生期間における最低値の時間的変化率の大きさの平均値を演算するとともに、正常期間における最低値の時間的変化率の大きさの平均値を演算する。そして、閾値設定部１６０は、正常期間における最低値の時間的変化率の大きさの平均値と異常発生期間における最低値の時間的変化率の大きさの平均値との比を算出し、この算出された比よりも小さい値に係数を設定する。閾値設定部１６０は、設定した係数と正常期間における最低値の時間的変化率の大きさの平均値とを掛け算することにより、閾値を演算する。 Specifically, the threshold setting unit 160 calculates the average value of the temporal change rate of the lowest value in the abnormality occurrence period, and calculates the average value of the temporal change rate of the lowest value in the normal period. Calculate. Then, the threshold setting unit 160 calculates the ratio of the average value of the temporal change rate of the lowest value in the normal period and the average value of the temporal change rate of the lowest value in the abnormality occurrence period, A coefficient is set to a value smaller than the calculated ratio. The threshold value setting unit 160 calculates the threshold value by multiplying the set coefficient by the average value of the temporal change rate of the lowest value in the normal period.
　［実施の形態３］
　図８は、実施の形態３に係る状態監視システムにおける軸受６０の異常を診断するための制御処理を説明するフローチャートである。図８に示される制御処理は、データ処理装置８０により、所定の時間間隔で繰り返し実行される。 [Embodiment 3]
FIG. 8 is a flowchart for explaining a control process for diagnosing an abnormality of the bearing 60 in the state monitoring system according to the third embodiment. The control processing shown in FIG. 8 is repeatedly executed by the data processing device 80 at predetermined time intervals.
　図８を図６と比較して、実施の形態３に係る状態監視システムでは、図６と同様のステップＳ０１～Ｓ０７の処理後に、ステップＳ０８に代えて、ステップＳ０８Ｂを実行する。 FIG. 8 is compared with FIG. 6, the state monitoring system according to the third embodiment executes step S08B instead of step S08 after the processing of steps S01 to S07 similar to FIG.
　すなわち、ステップＳ０７により、評価値演算部１４０が、記憶部１３０から読み出された規定個数の振動波形データの実効値の最低値を演算すると、診断部１５０は、ステップＳ０８Ｂにより、最低値の大きさおよび時間的変化率に基づいて、軸受６０の異常の有無を診断する。 That is, when the evaluation value calculation unit 140 calculates the minimum value of the effective values of the prescribed number of vibration waveform data read from the storage unit 130 in step S07, the diagnosis unit 150 determines that the minimum value is large in step S08B. The presence or absence of an abnormality in the bearing 60 is diagnosed based on the height and the temporal change rate.
　具体的には、診断部１５０は、ステップＳ０７で演算された最低値と第１閾値とを比較する。最低値が第１閾値以下である場合（Ｓ０８ＢのＮＯ判定時）、診断部１５０は、軸受６０が正常であると診断して、以降の処理Ｓ０９をスキップする。一方、ステップＳ０７で演算された最低値が第１閾値よりも大きい場合、診断部１５０は、さらに、最低値の時間的変化率と第２閾値とを比較する。最低値の時間的変化率が第２閾値以下である場合（Ｓ０８ＢのＮＯ判定時）、診断部１５０は、軸受６０が正常であると診断して、以降の処理Ｓ０９をスキップする。一方、最低値の時間的変化率が第２閾値よりも大きい場合（Ｓ０８ＢのＹＥＳ判定時）、診断部１５０は、ステップＳ０９により、軸受６０が異常であると診断する。 Specifically, the diagnosis unit 150 compares the lowest value calculated in step S07 with the first threshold value. When the minimum value is equal to or smaller than the first threshold value (when NO in S08B), the diagnosis unit 150 diagnoses that the bearing 60 is normal and skips the subsequent process S09. On the other hand, when the lowest value calculated in step S07 is larger than the first threshold, the diagnosis unit 150 further compares the temporal change rate of the lowest value with the second threshold. When the temporal change rate of the minimum value is equal to or less than the second threshold value (when NO in S08B), the diagnosis unit 150 diagnoses that the bearing 60 is normal and skips the subsequent process S09. On the other hand, when the temporal change rate of the minimum value is larger than the second threshold value (when YES is determined in S08B), diagnosis unit 150 diagnoses that bearing 60 is abnormal in step S09.
　すなわち、実施の形態３に係る異常診断においては、一定時間内における振動波形データの実効値の最低値が第１閾値よりも大きく、かつ、当該最低値の時間的変化率が第２閾値よりも大きい場合に、軸受６０が異常であると診断される。このようにすると、最低値の時間的変化率が第２閾値よりも大きくなった場合であっても、最低値の大きさが第１閾値以下であるときには、軸受６０の振動の大きさが小さいためにノイズの影響度が大きくなっているものと判断することができる。このような場合には、軸受６０が正常であると診断することにより、振動波形データに重畳するノイズの影響が適切に排除された評価値に基づいて軸受６０の異常を診断することができる。したがって、実施の形態３においても、実施の形態１と同様の効果を得ることができる。 That is, in the abnormality diagnosis according to the third embodiment, the minimum value of the effective value of the vibration waveform data within a certain time is larger than the first threshold value, and the temporal change rate of the minimum value is higher than the second threshold value. If so, the bearing 60 is diagnosed as abnormal. Thus, even when the temporal change rate of the minimum value is larger than the second threshold value, the magnitude of the vibration of the bearing 60 is small when the minimum value is equal to or smaller than the first threshold value. Therefore, it can be determined that the degree of influence of noise is large. In such a case, by diagnosing that the bearing 60 is normal, it is possible to diagnose the abnormality of the bearing 60 based on the evaluation value from which the influence of noise superimposed on the vibration waveform data is appropriately eliminated. Therefore, also in the third embodiment, the same effect as in the first embodiment can be obtained.
　なお、図８のステップＳ０８Ｂにて用いられる第１閾値は、実施の形態１で説明したように、異常発生期間における最低値の時間的変化の推移よりも小さく、かつ、正常期間における最低値の時間的変化の推移よりも大きい値に設定することができる。また、第２閾値は、実施の形態２で説明したように、正常期間における最低値の時間的変化率よりも大きく、かつ、異常発生期間における最低値の時間的変化率よりも小さい値に設定することができる。 Note that the first threshold value used in step S08B in FIG. 8 is smaller than the transition of the temporal change of the minimum value in the abnormality occurrence period and has the minimum value in the normal period as described in the first embodiment. It can be set to a value larger than the temporal change. Further, as described in the second embodiment, the second threshold value is set to a value that is larger than the temporal change rate of the lowest value in the normal period and smaller than the temporal change rate of the lowest value in the abnormality occurrence period. can do.
　なお、上記の実施の形態１～３においては、風力発電装置１０を構成する機械要素の１つである軸受６０に振動センサ７０を設置して、軸受６０の異常を診断するものとしたが、診断対象となる機械要素は軸受６０に限定されない点について確認的に記載する。たとえば、軸受６０とともに、または軸受６０に代えて、増速機４０内または発電機５０内に設けられる軸受に振動センサを設置し、上記の各実施の形態と同様の手法によって、増速機４０内または発電機５０内に設けられる軸受の異常を診断することができる。 In the first to third embodiments described above, the vibration sensor 70 is installed in the bearing 60 that is one of the mechanical elements constituting the wind power generator 10, and the abnormality of the bearing 60 is diagnosed. The point that the machine element to be diagnosed is not limited to the bearing 60 will be described. For example, a vibration sensor is installed in a bearing provided in the speed increaser 40 or in the generator 50 together with or in place of the bearing 60, and the speed increaser 40 is obtained by the same method as in each of the above embodiments. An abnormality of a bearing provided in the generator 50 or in the generator 50 can be diagnosed.
　また、上記の実施の形態１～３において、データ処理装置８０は、この発明における「処理装置」の一実施例に対応し、記憶部１３０、評価値演算部１４０、診断部１５０および閾値設定部１６０は、この発明における「記憶部」、「評価値演算部」、「診断部」および「設定部」の一実施例に対応する。 In the first to third embodiments, data processing device 80 corresponds to an example of “processing device” in the present invention, and includes storage unit 130, evaluation value calculation unit 140, diagnosis unit 150, and threshold setting unit. Reference numeral 160 corresponds to one embodiment of the “storage unit”, “evaluation value calculation unit”, “diagnosis unit”, and “setting unit” in the present invention.
　［実施の形態４］
　図９は、この発明の実施の形態４に係る状態監視システムにおけるデータ処理装置８０の構成を機能的に示す機能ブロック図である。図９を参照して、データ処理装置８０は、バンドパスフィルタ（以下、「ＢＰＦ（Band　Pass　Filter）」と称する。）１１２と、実効値演算部１２０と、記憶部１３０と、閾値設定部１６０と、診断部１５０とを含む。 [Embodiment 4]
FIG. 9 is a functional block diagram functionally showing the configuration of the data processing device 80 in the state monitoring system according to Embodiment 4 of the present invention. Referring to FIG. 9, data processing device 80 includes a bandpass filter (hereinafter referred to as “BPF (Band Pass Filter)”) 112, an effective value calculation unit 120, a storage unit 130, and a threshold setting unit 160. And a diagnostic unit 150.
　ＢＰＦ１１２は、軸受６０の振動波形データを振動センサ７０から受ける。ＢＰＦ１１２は、軸受６０の振動波形データに対してフィルタ処理を実行する。ＢＰＦ１１２は、たとえば、ハイパスフィルタ（ＨＰＦ（High　Pass　Filter））である。ＨＰＦは、その受けた振動波形データにつき、予め定められた周波数よりも高い信号成分を通過させ、低周波成分を遮断する。ＨＰＦは、軸受６０の振動波形データに含まれる直流成分を除去するために設けられたものである。なお、振動センサ７０の出力が直流成分を含まないものであれば、ＨＰＦを省略してもよい。 The BPF 112 receives vibration waveform data of the bearing 60 from the vibration sensor 70. The BPF 112 performs a filtering process on the vibration waveform data of the bearing 60. The BPF 112 is, for example, a high pass filter (HPF (High Pass Filter)). The HPF passes a signal component higher than a predetermined frequency with respect to the received vibration waveform data, and blocks a low frequency component. The HPF is provided to remove a direct current component included in the vibration waveform data of the bearing 60. Note that the HPF may be omitted if the output of the vibration sensor 70 does not include a DC component.
　ＢＰＦ１１２は、振動センサ７０とＨＰＦとの間に、エンベロープ処理部をさらに含んでいてもよい。エンベロープ処理部は、軸受６０の振動波形データを振動センサ７０から受けると、その受けた振動波形データにエンベロープ処理を行なうことで、軸受６０の振動波形データのエンベロープ波形を生成する。なお、エンベロープ処理部において演算されるエンベロープ処理には、種々の公知の手法を適用可能であり、一例として、振動センサ７０から受ける軸受６０の振動波形データを絶対値に整流し、ローパスフィルタ（ＬＰＦ（Low　Pass　Filter））を通すことによって、軸受６０の振動波形データのエンベロープ波形が生成される。この場合、ＨＰＦは、軸受６０の振動波形データのエンベロープ波形をエンベロープ処理部から受けると、その受けたエンベロープ波形につき、予め定められた周波数よりも高い信号成分を通過させ、低周波成分を遮断する。すなわち、ＨＰＦは、エンベロープ波形に含まれる直流成分を除去し、エンベロープ波形の交流成分を抽出するように構成される。 The BPF 112 may further include an envelope processing unit between the vibration sensor 70 and the HPF. When the envelope processing unit receives vibration waveform data of the bearing 60 from the vibration sensor 70, the envelope processing unit performs envelope processing on the received vibration waveform data to generate an envelope waveform of the vibration waveform data of the bearing 60. Various known methods can be applied to the envelope processing calculated in the envelope processing unit. As an example, the vibration waveform data of the bearing 60 received from the vibration sensor 70 is rectified into an absolute value, and a low-pass filter (LPF) is obtained. (Low Pass Filter)), the envelope waveform of the vibration waveform data of the bearing 60 is generated. In this case, when the HPF receives the envelope waveform of the vibration waveform data of the bearing 60 from the envelope processing unit, the HPF passes a signal component higher than a predetermined frequency for the received envelope waveform, and blocks the low frequency component. . That is, the HPF is configured to remove a direct current component included in the envelope waveform and extract an alternating current component of the envelope waveform.
　ＢＰＦ１１２は、ＬＰＦをさらに含んでいてもよい。ＬＰＦは、その受けた振動波形データにつき、予め定められた周波数よりも低い信号成分を通過させ、高周波成分を遮断する。 The BPF 112 may further include an LPF. The LPF passes a signal component lower than a predetermined frequency with respect to the received vibration waveform data, and blocks the high frequency component.
　実効値演算部１２０は、フィルタ処理が施された軸受６０の振動波形データをＢＰＦ１１２から受ける。実効値演算部１２０は、軸受６０の振動波形データの実効値（ＲＭＳ値）を算出し、その算出された振動波形データの実効値を記憶部１３０へ出力する。 The effective value calculation unit 120 receives the vibration waveform data of the bearing 60 subjected to the filter processing from the BPF 112. The effective value calculation unit 120 calculates an effective value (RMS value) of the vibration waveform data of the bearing 60 and outputs the calculated effective value of the vibration waveform data to the storage unit 130.
　実効値演算部１２０により演算される軸受６０の振動波形の実効値は、エンベロープ処理を行なっていない生の振動波形の実効値であるので、たとえば、軸受６０の軌道輪の一部に剥離が発生し、その剥離箇所を転動体が通過するときのみ振動が増加するインパルス的な振動に対しては値の増加が小さいけれども、軌道輪と転動体との接触部の面荒れまたは潤滑不良時に発生する持続的な振動に対しては値の増加が大きくなる。 Since the effective value of the vibration waveform of the bearing 60 calculated by the effective value calculation unit 120 is the effective value of the raw vibration waveform that has not been subjected to the envelope processing, for example, separation occurs in a part of the bearing ring of the bearing 60. However, although the increase in the value is small for the impulse-like vibration in which the vibration increases only when the rolling element passes through the peeled portion, it occurs when the surface of the contact portion between the race ring and the rolling element is rough or poorly lubricated. For continuous vibrations, the value increases.
　一方、上述のように、エンベロープ処理部を設けた場合には、実効値演算部１２０により演算されるエンベロープ波形の交流成分の実効値は、軌道輪の面荒れまたは潤滑不良時に発生する持続的な振動に対しては値の増加が小さく、インパルス的な振動に対しては値の増加が大きくなる。 On the other hand, as described above, when the envelope processing unit is provided, the effective value of the alternating current component of the envelope waveform calculated by the effective value calculating unit 120 is the continuous value generated when the raceway surface is rough or poorly lubricated. The increase in value is small for vibration, and the increase is large for impulse vibration.
　記憶部１３０は、実効値演算部１２０により演算された軸受６０の振動波形データの実効値を時々刻々と格納する。記憶部１３０は、たとえば、読み書き可能な不揮発性のメモリ等によって構成される。記憶部１３０は、少なくとも最新のｎ個（ｎは２以上の整数）の軸受６０の振動波形データの実効値を格納するように構成される。以下の説明では、振動波形データの実効値を、単に「振動波形データ」と称する。 The storage unit 130 stores the effective value of the vibration waveform data of the bearing 60 calculated by the effective value calculating unit 120 every moment. The storage unit 130 is configured by, for example, a readable / writable nonvolatile memory. The storage unit 130 is configured to store effective values of vibration waveform data of at least the latest n bearings (n is an integer of 2 or more). In the following description, the effective value of the vibration waveform data is simply referred to as “vibration waveform data”.
　閾値設定部１６０は、軸受６０の異常の有無を診断するために用いられる閾値を設定する。閾値設定部１６０は、設定された閾値を診断部１５０へ出力する。閾値設定部１６０における閾値の設定の詳細については後述する。 The threshold setting unit 160 sets a threshold used for diagnosing the presence or absence of an abnormality in the bearing 60. The threshold setting unit 160 outputs the set threshold to the diagnosis unit 150. Details of threshold setting in the threshold setting unit 160 will be described later.
　診断部１５０は、閾値設定部１６０で設定された閾値に基づいて、軸受６０の異常を診断する。具体的には、診断部１５０は、読み出された振動波形データと、閾値設定部１６０によって設定された閾値とを比較する。診断部１５０は、振動波形データが閾値を超えたことが判定されると、軸受６０の異常を報知するためのアラームを発報する。また、診断部１５０は、計測された振動波形データの時間的変化の推移に基づいて、軸受６０の異常を診断する。 The diagnosis unit 150 diagnoses the abnormality of the bearing 60 based on the threshold set by the threshold setting unit 160. Specifically, the diagnosis unit 150 compares the read vibration waveform data with the threshold set by the threshold setting unit 160. When it is determined that the vibration waveform data exceeds the threshold value, the diagnosis unit 150 issues an alarm for notifying the abnormality of the bearing 60. Further, the diagnosis unit 150 diagnoses the abnormality of the bearing 60 based on the transition of the temporal change of the measured vibration waveform data.
　次に、図１０よび図１１を参照して、閾値設定部１６０にて実行される閾値の設定処理について説明する。 Next, a threshold value setting process executed by the threshold value setting unit 160 will be described with reference to FIGS. 10 and 11.
　図９に示されるように、閾値設定部１６０は、移動平均演算部１６２（第１演算部）と、標準偏差演算部１６４（第２演算部）と、閾値演算部１６６（第３演算部）と、閾値記憶部１６８とを含む。 As illustrated in FIG. 9, the threshold setting unit 160 includes a moving average calculation unit 162 (first calculation unit), a standard deviation calculation unit 164 (second calculation unit), and a threshold calculation unit 166 (third calculation unit). And a threshold storage unit 168.
　図１０は、閾値設定部１６０の動作を説明する図である。図１０を参照して、記憶部１３０は、所定の時間間隔で、軸受６０の振動波形データを実効値演算部１２０から受ける。図１０中のＤ１～Ｄｎ＋２は、所定の時間間隔で記憶部１３０に与えられる振動波形データを表している。 FIG. 10 is a diagram for explaining the operation of the threshold setting unit 160. Referring to FIG. 10, storage unit 130 receives vibration waveform data of bearing 60 from effective value calculation unit 120 at predetermined time intervals. D1 to Dn + 2 in FIG. 10 represent vibration waveform data given to the storage unit 130 at predetermined time intervals.
　閾値設定部１６０は、記憶部１３０に格納されている振動波形データから、指定された期間の振動波形データを順次読み出して、移動平均演算処理、標準偏差演算処理、および閾値演算処理を行ない、閾値を算出する。この閾値を算出する処理は、記憶部１３０に振動波形データが充分に蓄積されたときに実施されることが望ましい。 The threshold setting unit 160 sequentially reads vibration waveform data for a specified period from the vibration waveform data stored in the storage unit 130, performs moving average calculation processing, standard deviation calculation processing, and threshold calculation processing. Is calculated. The processing for calculating the threshold value is desirably performed when vibration waveform data is sufficiently accumulated in the storage unit 130.
　具体的には、移動平均演算部１６２は、読み出された最新のｎ個の軸受６０の振動波形データの移動平均値を演算する。図１０の例では、時刻ｔｎまでの最新のｎ個の軸受６０の振動波形データＤ１～Ｄｎが記憶部１３０から読み出されると、ｎ個の振動波形データＤ１～Ｄｎの平均値ＭＡｎが算出される。次に、時刻ｔｎ＋１までの最新のｎ個の軸受６０の振動波形データＤ２～Ｄｎ＋２が記憶部１３０から読み出されると、ｎ個の振動波形データＤ２～Ｄｎ＋１の平均値ＭＡｎ＋１が算出される。さらに、時刻ｔｎ＋２までの最新のｎ個の軸受６０の振動波形データＤ３～Ｄｎ＋２が記憶部１３０から読み出されると、ｎ個の振動波形データＤ３～Ｄｎ＋２の平均値ＭＡｎ＋２が算出される。なお、移動平均値は、単純移動平均値を用いても、加重移動平均値を用いてもよい。このようにして、移動平均演算部１６２は、最新のｎ個の軸受６０の振動波形データを使用して移動平均値ＭＡを算出する。 Specifically, the moving average calculation unit 162 calculates the moving average value of the latest read vibration waveform data of the n bearings 60. In the example of FIG. 10, when the latest vibration waveform data D1 to Dn of the n bearings 60 up to time tn are read from the storage unit 130, the average value MAn of the n vibration waveform data D1 to Dn is calculated. . Next, when the latest vibration waveform data D2 to Dn + 2 of the n bearings 60 up to time tn + 1 are read from the storage unit 130, an average value MAn + 1 of the n pieces of vibration waveform data D2 to Dn + 1 is calculated. Further, when the latest vibration waveform data D3 to Dn + 2 of the n bearings 60 up to time tn + 2 are read from the storage unit 130, an average value MAn + 2 of the n vibration waveform data D3 to Dn + 2 is calculated. The moving average value may be a simple moving average value or a weighted moving average value. In this way, the moving average calculation unit 162 calculates the moving average value MA using the latest vibration waveform data of the n bearings 60.
　標準偏差演算部１６４は、ｎ個の軸受６０の振動波形データの標準偏差σを演算する。
　閾値演算部１６６は、移動平均演算部１６２によって算出された移動平均値ＭＡおよび標準偏差演算部１６４によって算出された標準偏差σを用いて、閾値を演算する。閾値をＴｈとすると、閾値Ｔｈは次式（１）で表される。
Ｔｈ＝ＭＡ＋ｋ・σ　　…（１）
　上記式（１）における係数ｋは正の値であり（ｋ＞０）、たとえば、ｋ＝２に設定される。すなわち、閾値Ｔｈは、たとえば「ＭＡ＋２σ」に設定される。 The standard deviation calculator 164 calculates the standard deviation σ of the vibration waveform data of the n bearings 60.
The threshold calculation unit 166 calculates a threshold using the moving average value MA calculated by the moving average calculation unit 162 and the standard deviation σ calculated by the standard deviation calculation unit 164. When the threshold is Th, the threshold Th is expressed by the following equation (1).
Th = MA + k · σ (1)
The coefficient k in the above formula (1) is a positive value (k> 0), and is set to k = 2, for example. That is, the threshold Th is set to “MA + 2σ”, for example.
　図１０の例では、時刻ｔｎにおける移動平均値ＭＡｎおよび標準偏差σを用いて閾値Ｔｈｎが算出され、時刻ｔｎ＋１における移動平均値ＭＡｎ＋１および標準偏差σを用いて閾値Ｔｈｎ＋１が算出され、時刻ｔｎ＋２における移動平均値ＭＡｎ＋２および標準偏差σを用いて閾値Ｔｈｎ＋２が算出される。このようにして、閾値演算部１６６は、閾値Ｔｈを算出し、算出した閾値Ｔｈを閾値記憶部１６８に保存する。 In the example of FIG. 10, the threshold value Thn is calculated using the moving average value MAn and the standard deviation σ at time tn, the threshold value Thn + 1 is calculated using the moving average value MAn + 1 and the standard deviation σ at time tn + 1, and the movement at the time tn + 2 is performed. The threshold value Thn + 2 is calculated using the average value MAn + 2 and the standard deviation σ. In this way, the threshold value calculation unit 166 calculates the threshold value Th, and stores the calculated threshold value Th in the threshold value storage unit 168.
　閾値Ｔｈには季節変動成分が含まれている。そのため、診断部１５０は、閾値記憶部１６８に保存されている閾値Ｔｈのうち、現在の季節と過去の同時期の閾値Ｔｈを使用するように構成されている。すなわち、診断部１５０は、振動波形データと同じ運転条件での過去の振動波形データに基づいて設定された閾値Ｔｈを使用するように構成されている。 Threshold value Th includes a seasonal variation component. Therefore, the diagnosis unit 150 is configured to use the threshold value Th of the current season and the past simultaneous period among the threshold values Th stored in the threshold value storage unit 168. That is, the diagnosis unit 150 is configured to use a threshold value Th set based on past vibration waveform data under the same operating conditions as the vibration waveform data.
　風力発電装置の運転条件は、一般的に風況などの環境に依存するため、主に季節によって変化する。上記のような構成とすることにより、診断部１５０では、季節要因等の運転条件の変化に対応した閾値Ｔｈを用いて軸受６０の異常の診断が実行されることになる。図３に示したように、閾値Ｔｈは、ｎ個の振動波形データについて統計処理がなされることによって設定されたものであるため、風力発電装置１０の運転条件の変化に従って変化する。すなわち、閾値Ｔｈは、風力発電装置１０の運転条件の変化を反映することができる。 Since the operating conditions of wind power generators generally depend on the environment such as wind conditions, they vary mainly depending on the season. With the above-described configuration, the diagnosis unit 150 performs the diagnosis of the abnormality of the bearing 60 using the threshold Th corresponding to a change in operating conditions such as seasonal factors. As shown in FIG. 3, the threshold value Th is set by performing statistical processing on n pieces of vibration waveform data, and thus changes according to a change in operating conditions of the wind turbine generator 10. That is, the threshold value Th can reflect a change in operating conditions of the wind turbine generator 10.
　そして、風力発電装置１０の運転条件によって変化する軸受６０の振動波形データと、当該運転条件を反映した閾値Ｔｈとを比較することで、その比較結果において、風力発電装置１０の運転条件の変化の影響を低減することができる。この結果、軸受６０の損傷に起因する振動の変化を捉えることが可能となるため、正確な異常診断を実現することができる。 Then, by comparing the vibration waveform data of the bearing 60 that changes according to the operating conditions of the wind power generator 10 and the threshold value Th that reflects the operating conditions, the comparison result shows that the operating conditions of the wind power generator 10 change. The influence can be reduced. As a result, it is possible to capture a change in vibration caused by damage to the bearing 60, so that an accurate abnormality diagnosis can be realized.
　図１１は、閾値設定部１６０によって設定される閾値の一例を示すグラフである。図１１は、ある年の２月１日からその翌年の２月２６日までの約１年間の計測期間において振動センサ７０によって計測された振動波形データの実効値と、当該振動波形データの移動平均値および閾値との時間的変化を示している。 FIG. 11 is a graph showing an example of the threshold set by the threshold setting unit 160. FIG. 11 shows an effective value of vibration waveform data measured by the vibration sensor 70 in a measurement period of about one year from February 1 of a certain year to February 26 of the following year, and a moving average of the vibration waveform data. The time change with a value and a threshold is shown.
　図１１中の黒丸は、軸受６０の振動波形データの実効値を示す。図１１中の破線は、ｎ個の振動波形データの実効値の移動平均値ＭＡの時間的変化を示す。なお、図１１の例では、ｎ＝１２０としている。図１１中の実線は、ｎ個の振動波形データの実効値の移動平均値ＭＡおよび標準偏差σを用いて設定された閾値の時間的変化を示す。なお、閾値は、式Ｔｈ＝ＭＡ＋２σを用いて算出されたものである。 11 represents the effective value of the vibration waveform data of the bearing 60. A broken line in FIG. 11 indicates a temporal change in the moving average value MA of the effective values of the n pieces of vibration waveform data. In the example of FIG. 11, n = 120. The solid line in FIG. 11 shows the temporal change of the threshold value set using the moving average value MA and the standard deviation σ of the effective values of the n pieces of vibration waveform data. The threshold value is calculated using the formula Th = MA + 2σ.
　図１１に示されるように、計測期間中、振動波形データの実効値は大きく変化している。図１１の例では、１２月から１月までの間に実効値が相対的に大きくなる一方で、７月から８月までの間に実効値が相対的に小さくなっている。このように、季節ごとに変化する運転条件に起因して実効値も大きく変化する。 As shown in FIG. 11, the effective value of the vibration waveform data changes greatly during the measurement period. In the example of FIG. 11, the effective value is relatively large from December to January, while the effective value is relatively small from July to August. In this way, the effective value changes greatly due to the operating conditions that change from season to season.
　実効値が相対的に小さくなる期間においても正確な診断を行なうためには、当該期間における実効値に基づいて、閾値を一定値に設定することが考えられる。しかしながら、このようにすると、実効値が相対的に大きくなる期間において、閾値を超える実効値が頻繁に発生してしまい、正確な診断が困難となる。 In order to make an accurate diagnosis even in a period in which the effective value is relatively small, it is conceivable to set the threshold value to a constant value based on the effective value in the period. However, if this is done, an effective value that exceeds the threshold frequently occurs during a period in which the effective value is relatively large, and accurate diagnosis becomes difficult.
　本実施の形態では、過去の一定期間に記録された軸受６０の振動波形データの実効値から算出された移動平均値に基づいて閾値が設定されている。特に、過去の軸受６０が正常だったと判断される時期の振動波形データの実効値を用いて閾値が設定される。したがって、過去の同じ運転条件（たとえば、過去の同時期）に対して設定された閾値を基準として異常を診断するように構成すれば、実効値が相対的に小さくなる期間では閾値が相対的に小さくなる一方で、実効値が相対的に大きくなる期間では閾値が相対的に大きくなる。このように、閾値が風力発電装置１０の運転条件の変化を反映するため、正確な異常診断を実現することができる。 In the present embodiment, the threshold value is set based on the moving average value calculated from the effective value of the vibration waveform data of the bearing 60 recorded in the past certain period. In particular, the threshold is set using the effective value of the vibration waveform data at the time when it is determined that the past bearing 60 is normal. Therefore, if the abnormality is diagnosed based on the threshold value set for the same past operating conditions (for example, the same period in the past), the threshold value is relatively low during the period in which the effective value is relatively small. On the other hand, the threshold value becomes relatively large during the period when the effective value becomes relatively large. Thus, since the threshold value reflects the change in the operating condition of the wind turbine generator 10, an accurate abnormality diagnosis can be realized.
　図１２は、実施の形態４に係る状態監視システムにおける閾値の設定処理を説明するフローチャートである。図１２に示される設定処理は、閾値算出に使用するデータ範囲（期間）を指定して、データ処理装置８０（図９）により実行される。 FIG. 12 is a flowchart for explaining threshold setting processing in the state monitoring system according to the fourth embodiment. The setting process shown in FIG. 12 is executed by the data processing device 80 (FIG. 9) by designating a data range (period) used for threshold calculation.
　図１２を参照して、データ処理装置８０は、ステップＳ１１により、閾値算出に使用するデータの範囲を指定する。データの範囲は、たとえば１年前の同じ月などのように自動的に設定されてもよいし、外部からパラメータとして通信等によって与えられるように構成してもよい。 Referring to FIG. 12, the data processing device 80 designates a range of data used for threshold calculation in step S11. The data range may be automatically set, for example, the same month one year ago, or may be configured to be given by communication or the like as a parameter from the outside.
　次に、閾値設定部１６０は、ステップＳ１２により、指定されたデータ範囲の先頭から、記憶部１３０に格納されている振動波形データを順次読み出す。 Next, the threshold value setting unit 160 sequentially reads the vibration waveform data stored in the storage unit 130 from the head of the designated data range in step S12.
　閾値設定部１６０は、ステップＳ１３により、読み出された振動波形データの実効値のデータ数がｎ個以上であるか否かを判定する。読み出された振動波形データの実効値のデータ数がｎ個未満である場合（Ｓ１３のＮＯ判定時）、以降の処理Ｓ１４～Ｓ１７はスキップされる。 The threshold setting unit 160 determines whether or not the number of effective values of the read vibration waveform data is n or more in step S13. When the number of effective values of the read vibration waveform data is less than n (NO in S13), the subsequent processes S14 to S17 are skipped.
　一方、読み出された振動波形データの実効値のデータ数がｎ個以上である場合（Ｓ１３のＹＥＳ判定時）、閾値設定部１６０は、ステップＳ１４に進み、読み出された最新のｎ個の振動波形データの実効値の移動平均値を演算する。 On the other hand, when the number of effective values of the read vibration waveform data is n or more (at the time of YES determination in S13), the threshold setting unit 160 proceeds to step S14, and reads the latest n read data. Calculates the moving average value of the effective value of vibration waveform data.
　続いて、閾値設定部１６０は、ステップＳ１５により、読み出された最新のｎ個の振動波形データの実効値の標準偏差を演算する。そして、閾値設定部１６０は、ステップＳ１６により、ステップＳ１４にて演算された移動平均値とステップＳ１５にて演算された標準偏差とを用いて、閾値を設定する。閾値設定部１６０は、ステップＳ１７により、設定した閾値を閾値記憶部１６８（図９）に順次保存する。閾値は、算出に用いたデータの時刻情報とともに記憶され、診断に用いる閾値を選択するために使用される。 Subsequently, in step S15, the threshold setting unit 160 calculates a standard deviation of effective values of the latest n pieces of vibration waveform data read out. Then, in step S16, the threshold setting unit 160 sets a threshold using the moving average value calculated in step S14 and the standard deviation calculated in step S15. The threshold setting unit 160 sequentially stores the set thresholds in the threshold storage unit 168 (FIG. 9) in step S17. The threshold value is stored together with the time information of the data used for the calculation, and is used for selecting the threshold value used for the diagnosis.
　閾値設定部１６０は、ステップＳ１８により、対象期間の振動波形データの全てについて処理を終了したか否かを判定する。処理が終了していない場合（Ｓ１８のＮＯ判定時）、処理はＳ１２に戻される。 The threshold setting unit 160 determines whether or not the processing has been completed for all vibration waveform data in the target period in step S18. If the process has not been completed (NO in S18), the process returns to S12.
　図１３は、実施の形態４に係る状態監視システムにおける軸受６０の異常を診断するための制御処理を説明するフローチャートである。図１３に示される制御処理は、データ処理装置８０により所定の時間間隔で繰り返し実行される。 FIG. 13 is a flowchart for explaining a control process for diagnosing an abnormality of the bearing 60 in the state monitoring system according to the fourth embodiment. The control processing shown in FIG. 13 is repeatedly executed by the data processing device 80 at predetermined time intervals.
　図１３を参照して、データ処理装置８０は、ステップＳ５１により軸受６０の振動波形データを振動センサ７０から受ける。データ処理装置８０において、ステップＳ５２により、ＢＰＦ１１２は、軸受６０の振動波形データに対してフィルタ処理を実行する。 Referring to FIG. 13, the data processing device 80 receives the vibration waveform data of the bearing 60 from the vibration sensor 70 in step S51. In the data processing device 80, the BPF 112 performs a filtering process on the vibration waveform data of the bearing 60 in step S <b> 52.
　次に、ステップＳ５３により、フィルタ処理が施された軸受６０の振動波形データをＢＰＦ１１２から受けると、実効値演算部１２０は、軸受６０の振動波形データの実効値を算出する。記憶部１３０は、ステップＳ５４により、実効値演算部１２０によって算出された振動波形データの実効値を格納する。 Next, when the vibration waveform data of the bearing 60 subjected to the filtering process is received from the BPF 112 in step S53, the effective value calculator 120 calculates the effective value of the vibration waveform data of the bearing 60. The storage unit 130 stores the effective value of the vibration waveform data calculated by the effective value calculation unit 120 in step S54.
　診断部１５０は、ステップＳ５５により、閾値設定部１６０内の閾値記憶部１６８から、振動波形データの実効値と同じ運転条件での過去の振動波形データの実効値に基づいて設定された閾値を読み出す。たとえば、診断部１５０は、現在の季節と過去の同時期に設定された閾値を読み出す。 In step S55, the diagnosis unit 150 reads the threshold value set based on the effective value of the past vibration waveform data under the same operation condition as the effective value of the vibration waveform data from the threshold value storage unit 168 in the threshold value setting unit 160. . For example, the diagnosis unit 150 reads out the threshold values set for the current season and the past simultaneous period.
　データ処理装置８０は、ステップＳ５６により、ステップＳ５３で算出された振動波形データの実効値と、ステップＳ５５で読み出された閾値とを比較する。実効値が閾値以下である場合（Ｓ５６のＮＯ判定時）、診断部１５０は、軸受６０が正常であると診断して、以降の処理Ｓ５７をスキップする。一方、実効値が閾値よりも大きい場合（Ｓ５６のＹＥＳ判定時）、診断部１５０は、ステップＳ５７により、軸受６０が異常であると診断し、アラームを発報する。 In step S56, the data processing device 80 compares the effective value of the vibration waveform data calculated in step S53 with the threshold value read in step S55. When the effective value is less than or equal to the threshold value (NO determination in S56), the diagnosis unit 150 diagnoses that the bearing 60 is normal and skips the subsequent processing S57. On the other hand, when the effective value is larger than the threshold value (when YES is determined in S56), the diagnosis unit 150 diagnoses that the bearing 60 is abnormal in step S57 and issues an alarm.
　なお、上記の実施の形態４においては、風力発電装置１０を構成する機械要素の１つである軸受６０に振動センサ７０を設置して、軸受６０の異常を診断するものとしたが、診断対象となる機械要素は軸受６０に限定されない点について確認的に記載する。たとえば、軸受６０とともに、または軸受６０に代えて、増速機４０内または発電機５０内に設けられる軸受に振動センサを設置し、上記の実施の形態４と同様の手法によって、増速機４０内または発電機５０内に設けられる軸受の異常を診断することができる。 In the above-described fourth embodiment, the vibration sensor 70 is installed in the bearing 60 that is one of the mechanical elements constituting the wind power generator 10, and the abnormality of the bearing 60 is diagnosed. It will be described in a definite manner that the mechanical element is not limited to the bearing 60. For example, a vibration sensor is installed in a bearing provided in the speed increaser 40 or in the generator 50 together with or in place of the bearing 60, and the speed increaser 40 is obtained by the same method as in the fourth embodiment. An abnormality of a bearing provided in the generator 50 or in the generator 50 can be diagnosed.
　また、上記の実施の形態４において、データ処理装置８０は、この発明における「処理装置」の一実施例に対応し、閾値設定部１６０および診断部１５０は、それぞれ、この発明における「設定部」および「診断部」の一実施例に対応する。また、上記の実施の形態４において、移動平均演算部１６２、標準偏差演算部１６４、閾値演算部１６６および閾値記憶部１６８は、それぞれ、この発明における「第１演算部」、「第２演算部」、「第３演算部」および「記憶部」の一実施例に対応する。 In the fourth embodiment, the data processing device 80 corresponds to an example of the “processing device” in the present invention, and the threshold setting unit 160 and the diagnosis unit 150 are each the “setting unit” in the present invention. And one example of the “diagnostic unit”. In the fourth embodiment, the moving average calculation unit 162, the standard deviation calculation unit 164, the threshold value calculation unit 166, and the threshold value storage unit 168 are respectively the “first calculation unit” and the “second calculation unit” in the present invention. ”,“ Third arithmetic unit ”, and“ storage unit ”.
　［実施の形態５］
　図１４は、この発明の実施の形態５に係る状態監視システムにおけるデータ処理装置８０の構成を機能的に示す機能ブロック図である。図１４を参照して、データ処理装置８０は、ＢＰＦ１１２と、実効値演算部１２０と、記憶部１３０と、振動波形データ出力部１７０と、診断部１５０と、評価値演算部１４０と、計測トリガ発生部１８０とを含む。 [Embodiment 5]
FIG. 14 is a functional block diagram functionally showing the configuration of the data processing device 80 in the state monitoring system according to Embodiment 5 of the present invention. Referring to FIG. 14, the data processing device 80 includes a BPF 112, an effective value calculation unit 120, a storage unit 130, a vibration waveform data output unit 170, a diagnosis unit 150, an evaluation value calculation unit 140, a measurement trigger. Generator 180.
　ＢＰＦ１１２は、軸受６０の振動波形データを振動センサ７０から受ける。ＢＰＦ１１２は、たとえば、ＨＰＦを含む。ＨＰＦは、その受けた振動波形データにつき、予め定められた周波数よりも高い信号成分を通過させ、低周波成分を遮断する。ＨＰＦは、軸受６０の振動波形データに含まれる直流成分を除去するために設けられたものである。なお、振動センサ７０の出力が直流成分を含まないものであれば、ＨＰＦを省略してもよい。 The BPF 112 receives vibration waveform data of the bearing 60 from the vibration sensor 70. The BPF 112 includes, for example, an HPF. The HPF passes a signal component higher than a predetermined frequency with respect to the received vibration waveform data, and blocks a low frequency component. The HPF is provided to remove a direct current component included in the vibration waveform data of the bearing 60. Note that the HPF may be omitted if the output of the vibration sensor 70 does not include a DC component.
　ＢＰＦ１１２は、ＨＰＦに加えて、またはＨＰＦに代えてＬＰＦを含んでいてもよい。ＬＰＦは、その受けた振動波形データにつき、予め定められた周波数よりも低い信号成分を通過させる。 The BPF 112 may include an LPF in addition to the HPF or instead of the HPF. The LPF passes a signal component lower than a predetermined frequency for the received vibration waveform data.
　また、振動センサ７０とＢＰＦ１１２との間に、エンベロープ処理部を設けてもよい。エンベロープ処理部は、軸受６０の振動波形データを振動センサ７０から受けると、その受けた振動波形データにエンベロープ処理を行なうことで、軸受６０の振動波形データのエンベロープ波形を生成する。なお、エンベロープ処理部において演算されるエンベロープ処理には、種々の公知の手法を適用可能であり、一例として、振動センサ７０から受ける軸受６０の振動波形データを絶対値に整流し、ＬＰＦを通すことによって、軸受６０の振動波形データのエンベロープ波形が生成される。 Further, an envelope processing unit may be provided between the vibration sensor 70 and the BPF 112. When the envelope processing unit receives vibration waveform data of the bearing 60 from the vibration sensor 70, the envelope processing unit performs envelope processing on the received vibration waveform data to generate an envelope waveform of the vibration waveform data of the bearing 60. Various known methods can be applied to the envelope processing calculated in the envelope processing unit. For example, the vibration waveform data of the bearing 60 received from the vibration sensor 70 is rectified to an absolute value and passed through the LPF. Thus, an envelope waveform of the vibration waveform data of the bearing 60 is generated.
　この場合、ＢＰＦ１１２において、ＨＰＦは、軸受６０の振動波形データのエンベロープ波形をエンベロープ処理部から受けると、その受けたエンベロープ波形につき、予め定められた周波数よりも高い信号成分を通過させ、低周波成分を遮断する。すなわち、ＨＰＦは、エンベロープ波形に含まれる直流成分を除去し、エンベロープ波形の交流成分を抽出するように構成される。 In this case, in the BPF 112, when the HPF receives the envelope waveform of the vibration waveform data of the bearing 60 from the envelope processing unit, the HPF passes a signal component higher than a predetermined frequency with respect to the received envelope waveform, and the low frequency component Shut off. That is, the HPF is configured to remove a direct current component included in the envelope waveform and extract an alternating current component of the envelope waveform.
　実効値演算部１２０は、フィルタ処理が施された軸受６０の振動波形データをＢＰＦ１１２から受ける。実効値演算部１２０は、軸受６０の振動波形データの実効値（ＲＭＳ値）を算出し、その算出された振動波形データの実効値を記憶部１３０へ出力する。 The effective value calculation unit 120 receives the vibration waveform data of the bearing 60 subjected to the filter processing from the BPF 112. The effective value calculation unit 120 calculates an effective value (RMS value) of the vibration waveform data of the bearing 60 and outputs the calculated effective value of the vibration waveform data to the storage unit 130.
　実効値演算部１２０により演算される軸受６０の振動波形の実効値は、エンベロープ処理を行なっていない生の振動波形の実効値であるので、たとえば、軸受６０の軌道輪の一部に剥離が発生し、その剥離箇所を転動体が通過するときのみ振動が増加するインパルス的な振動に対しては値の増加が小さいけれども、軌道輪と転動体との接触部の面荒れまたは潤滑不良時に発生する持続的な振動に対しては値の増加が大きくなる。 Since the effective value of the vibration waveform of the bearing 60 calculated by the effective value calculation unit 120 is the effective value of the raw vibration waveform that has not been subjected to the envelope processing, for example, separation occurs in a part of the bearing ring of the bearing 60. However, although the increase in the value is small for the impulse-like vibration in which the vibration increases only when the rolling element passes through the peeled portion, it occurs when the surface of the contact portion between the race ring and the rolling element is rough or poorly lubricated. For continuous vibrations, the value increases.
　一方、上述のように、エンベロープ処理部を設けた場合には、実効値演算部１２０により演算されるエンベロープ波形の交流成分の実効値は、軌道輪の面荒れまたは潤滑不良時に発生する持続的な振動に対しては値の増加が小さく、インパルス的な振動に対しては値の増加が大きくなる。 On the other hand, as described above, when the envelope processing unit is provided, the effective value of the alternating current component of the envelope waveform calculated by the effective value calculating unit 120 is the continuous value generated when the raceway surface is rough or poorly lubricated. The increase in value is small for vibration, and the increase is large for impulse vibration.
　記憶部１３０は、振動波形データ記憶部１３２と、評価値トレンド記憶部１３４とを含む。振動波形データ記憶部１３２および評価値トレンド記憶部１３４は、たとえば、読み書き可能な不揮発性のメモリ等によって構成される。 The storage unit 130 includes a vibration waveform data storage unit 132 and an evaluation value trend storage unit 134. The vibration waveform data storage unit 132 and the evaluation value trend storage unit 134 are configured by, for example, a readable / writable nonvolatile memory.
　振動波形データ記憶部１３２は、実効値演算部１２０により演算された軸受６０の振動波形データの実効値を時々刻々と格納する。振動波形データ記憶部１３２は、一定時間内における軸受６０の振動波形データの実効値を格納するように構成される。後述するように、振動波形データ記憶部１３２に格納された軸受６０の振動波形データの実効値が読み出され、その読み出された実効値を用いて軸受６０の異常が診断される。以下の説明では、振動波形データの実効値を、単に「振動波形データ」と称する。 The vibration waveform data storage unit 132 stores the effective value of the vibration waveform data of the bearing 60 calculated by the effective value calculation unit 120 every moment. The vibration waveform data storage unit 132 is configured to store an effective value of vibration waveform data of the bearing 60 within a predetermined time. As will be described later, the effective value of the vibration waveform data of the bearing 60 stored in the vibration waveform data storage unit 132 is read, and the abnormality of the bearing 60 is diagnosed using the read effective value. In the following description, the effective value of the vibration waveform data is simply referred to as “vibration waveform data”.
　評価値演算部１４０は、一定時間内における軸受６０の振動波形データを振動波形データ記憶部１３２から読み出すと、読み出した一定時間内における軸受６０の振動波形データを特徴付ける評価値を演算する。評価値演算部１４０は、評価値を時間的に連続して演算するように構成される。 When the vibration value data of the bearing 60 within a predetermined time is read from the vibration waveform data storage unit 132, the evaluation value calculation unit 140 calculates an evaluation value that characterizes the read vibration waveform data of the bearing 60 within the predetermined time. The evaluation value calculation unit 140 is configured to calculate the evaluation value continuously in time.
　評価値トレンド記憶部１３４は、評価値演算部１４０により演算された評価値を受ける。評価値トレンド記憶部１３４は、評価値演算部１４０から時々刻々と与えられる評価値を格納する。言い換えれば、評価値トレンド記憶部１３４は、評価値の時間的変化の傾向を示す評価値トレンドを格納するように構成される。 The evaluation value trend storage unit 134 receives the evaluation value calculated by the evaluation value calculation unit 140. The evaluation value trend storage unit 134 stores the evaluation value given from the evaluation value calculation unit 140 every moment. In other words, the evaluation value trend storage unit 134 is configured to store an evaluation value trend indicating a tendency of the evaluation value to change over time.
　図１５は、図１４に示した振動波形データ記憶部１３２および評価値演算部１４０の動作を説明する図である。図１５を参照して、振動波形データ記憶部１３２は、所定の時間間隔で、軸受６０の振動波形データを実効値演算部１２０から受ける。図１５の例では、所定の時間間隔を１秒間隔としている。図１５中のＤ０～Ｄ１１は、１秒間隔で振動波形データ記憶部１３２に与えられる振動波形データを表わしている。 FIG. 15 is a diagram for explaining operations of the vibration waveform data storage unit 132 and the evaluation value calculation unit 140 shown in FIG. Referring to FIG. 15, vibration waveform data storage unit 132 receives vibration waveform data of bearing 60 from effective value calculation unit 120 at predetermined time intervals. In the example of FIG. 15, the predetermined time interval is 1 second. D0 to D11 in FIG. 15 represent vibration waveform data given to the vibration waveform data storage unit 132 at intervals of one second.
　振動波形データ記憶部１３２は、一定時間内における軸受６０の振動波形データを格納する。一定時間は、主軸２０の回転速度に応じて設定することができる。図１５の例では、一定時間を１０秒間としている。たとえば、時刻ｔ０において、振動波形データ記憶部１３２は、時間的に連続する合計１０個（すなわち、１０秒間分）の振動波形データＤ０～Ｄ９を格納している。 The vibration waveform data storage unit 132 stores vibration waveform data of the bearing 60 within a predetermined time. The fixed time can be set according to the rotational speed of the main shaft 20. In the example of FIG. 15, the predetermined time is 10 seconds. For example, at time t0, the vibration waveform data storage unit 132 stores a total of 10 pieces of vibration waveform data D0 to D9 that are continuous in time (that is, for 10 seconds).
　時刻ｔ０から１秒経過した時刻ｔ１において、振動波形データ記憶部１３２は、振動波形データＤ１０を実効値演算部１２０から受けると、１０秒間分の振動波形データＤ０～Ｄ９のうちの最も古い振動波形データＤ０を消去するとともに、新たに入力された振動波形データＤ１０を追加することで、一定時間内における振動波形データを更新する。 When the vibration waveform data storage unit 132 receives the vibration waveform data D10 from the effective value calculation unit 120 at time t1 when 1 second has elapsed from time t0, the oldest vibration waveform among the vibration waveform data D0 to D9 for 10 seconds. While deleting the data D0 and adding the newly input vibration waveform data D10, the vibration waveform data within a predetermined time is updated.
　さらに、時刻ｔ１から１秒経過した時刻ｔ２では、振動波形データ記憶部１３２は、１０秒間分の振動波形データＤ１～Ｄ１０のうちの最も古い振動波形データＤ１を消去するとともに、新たに入力された振動波形データＤ１１を追加することで、一定時間内における軸受６０の振動波形データを更新する。 Furthermore, at time t2 when 1 second has elapsed from time t1, the vibration waveform data storage unit 132 deletes the oldest vibration waveform data D1 from the vibration waveform data D1 to D10 for 10 seconds and is newly input. By adding the vibration waveform data D11, the vibration waveform data of the bearing 60 within a predetermined time is updated.
　このようにして、振動波形データ記憶部１３２は、所定の時間間隔で、一定時間内における軸受６０の振動波形データを更新する。評価値演算部１４０は、所定の時間間隔で更新される一定時間内における軸受６０の振動波形データを振動波形データ記憶部１３２から読み出す。評価値演算部１４０は、読み出した一定時間内における軸受６０の振動波形データを統計処理することにより評価値を演算する。 In this way, the vibration waveform data storage unit 132 updates the vibration waveform data of the bearing 60 within a predetermined time at predetermined time intervals. The evaluation value calculation unit 140 reads vibration waveform data of the bearing 60 from the vibration waveform data storage unit 132 within a predetermined time that is updated at predetermined time intervals. The evaluation value calculation unit 140 calculates an evaluation value by statistically processing the vibration waveform data of the bearing 60 within the read fixed time.
　図１５の例では、時刻ｔ０において、評価値演算部１４０は、振動波形データ記憶部１３２から、１０秒間分の振動波形データＤ０～Ｄ９を読み出すと、読み出した振動波形データＤ０～Ｄ９を統計処理することによって評価値Ｅ０を演算する。評価値Ｅ０は、時刻ｔ０の直前の１０秒間分の振動波形データＤ０～Ｄ９を特徴付ける値（代表値）となる。したがって、統計処理では、評価値Ｅ０として、たとえば、振動波形データＤ０～Ｄ９の平均値を演算することができる。あるいは、評価値Ｅ０として、振動波形データＤ０～Ｄ９の中央値、最頻値、最小値などを演算することもできる。 In the example of FIG. 15, at time t0, the evaluation value calculation unit 140 reads the vibration waveform data D0 to D9 for 10 seconds from the vibration waveform data storage unit 132, and performs statistical processing on the read vibration waveform data D0 to D9. As a result, the evaluation value E0 is calculated. The evaluation value E0 is a value (representative value) that characterizes the vibration waveform data D0 to D9 for 10 seconds immediately before the time t0. Therefore, in the statistical process, for example, an average value of the vibration waveform data D0 to D9 can be calculated as the evaluation value E0. Alternatively, the median value, mode value, minimum value, etc. of the vibration waveform data D0 to D9 can be calculated as the evaluation value E0.
　時刻ｔ１において、評価値演算部１４０は、１０秒間分の振動波形データＤ１～Ｄ１０を統計処理することにより、評価値Ｅ１を演算する。時刻ｔ２において、評価値演算部１４０は、１０秒間分の振動波形データＤ２～Ｄ１１を統計処理することにより、評価値Ｅ２を演算する。 At time t1, the evaluation value calculation unit 140 calculates the evaluation value E1 by statistically processing the vibration waveform data D1 to D10 for 10 seconds. At time t2, the evaluation value calculator 140 calculates the evaluation value E2 by statistically processing the vibration waveform data D2 to D11 for 10 seconds.
　このようにして、評価値演算部１４０は、所定の時間間隔で、一定時間内における軸受６０の振動波形データの評価値を演算する。評価値演算部１４０は、演算した評価値を評価値トレンド記憶部１３４へ出力する。 In this way, the evaluation value calculation unit 140 calculates the evaluation value of the vibration waveform data of the bearing 60 within a predetermined time at predetermined time intervals. The evaluation value calculation unit 140 outputs the calculated evaluation value to the evaluation value trend storage unit 134.
　図１６は、図１４に示した評価値トレンド記憶部１３４の動作を説明する図である。図１６を参照して、評価値トレンド記憶部１３４は、所定の時間間隔で、評価値を評価値演算部１４０から受ける。図１６の例では、所定の時間間隔を１秒間隔としている。図１６中のＥ０～Ｅ６は、１秒間隔で評価値演算部１４０から評価値トレンド記憶部１３４に与えられる評価値を表わしている。 FIG. 16 is a diagram for explaining the operation of the evaluation value trend storage unit 134 shown in FIG. Referring to FIG. 16, evaluation value trend storage unit 134 receives evaluation values from evaluation value calculation unit 140 at predetermined time intervals. In the example of FIG. 16, the predetermined time interval is set to 1 second. E0 to E6 in FIG. 16 represent evaluation values given from the evaluation value calculation unit 140 to the evaluation value trend storage unit 134 at intervals of 1 second.
　評価値トレンド記憶部１３４は、時間的に連続する所定数の評価値を格納する。この時間的に連続する所定数の評価値は、評価値の時間的変化の傾向を表わす「評価値トレンド」に相当する。 The evaluation value trend storage unit 134 stores a predetermined number of evaluation values that are continuous in time. The predetermined number of evaluation values that are continuous in time corresponds to an “evaluation value trend” that represents a tendency of the evaluation value to change over time.
　図１６の例では、所定数を５としている。たとえば、評価値トレンド記憶部１３４は、時刻ｔ０にて評価値Ｅ０を格納し、時刻ｔ０から１秒経過した時刻ｔ１にて評価値Ｅ１を格納し、時刻ｔ１から１秒経過した時刻ｔ２にて評価値Ｅ２を格納し、時刻ｔ２から１秒経過した時刻ｔ３にて評価値Ｅ３を格納し、時刻ｔ３から１秒経過した時刻ｔ４にて評価値Ｅ４を格納する。なお、評価値Ｅ３は、時刻ｔ３の直前の１０秒間分の振動波形データＤ３～Ｄ１２を統計処理することにより演算されたものである。評価値Ｅ４は、時刻ｔ４の直前の１０秒間分の振動波形データＤ４～Ｄ１３を統計処理することにより演算されたものである。 In the example of FIG. 16, the predetermined number is 5. For example, the evaluation value trend storage unit 134 stores the evaluation value E0 at time t0, stores the evaluation value E1 at time t1 when 1 second has elapsed from time t0, and at time t2 when 1 second has elapsed from time t1. The evaluation value E2 is stored, the evaluation value E3 is stored at time t3 when 1 second has elapsed from time t2, and the evaluation value E4 is stored at time t4 when 1 second has elapsed from time t3. The evaluation value E3 is calculated by statistically processing vibration waveform data D3 to D12 for 10 seconds immediately before time t3. The evaluation value E4 is calculated by statistically processing vibration waveform data D4 to D13 for 10 seconds immediately before time t4.
　図１６の例では、評価値トレンド記憶部１３４は、たとえば、時刻ｔ５において、合計５個の評価値Ｅ０～Ｅ４を格納している。時刻ｔ５から１秒経過した時刻ｔ６において、評価値トレンド記憶部１３４は、時刻ｔ５の直前の１０秒間分の振動波形データＤ５～Ｄ１４の評価値Ｅ５を評価値演算部１４０から受けると、合計５個の評価値Ｅ０～Ｅ４のうちの最も古い評価値Ｅ０を消去するとともに、新たに入力された評価値Ｅ５を追加することにより、所定数の評価値を更新する。 In the example of FIG. 16, the evaluation value trend storage unit 134 stores, for example, a total of five evaluation values E0 to E4 at time t5. When the evaluation value trend storage unit 134 receives the evaluation values E5 of the vibration waveform data D5 to D14 for 10 seconds immediately before the time t5 from the evaluation value calculation unit 140 at time t6 when 1 second has elapsed from time t5, a total of 5 is obtained. The oldest evaluation value E0 among the evaluation values E0 to E4 is deleted, and a newly input evaluation value E5 is added to update a predetermined number of evaluation values.
　さらに、時刻ｔ５から１秒経過した時刻ｔ６では、評価値トレンド記憶部１３４は、時刻ｔ６の直前の１０秒間分の振動波形データＤ６～Ｄ１５の評価値Ｅ６を評価値演算部１４０から受けると、合計５個の評価値Ｅ１～Ｅ５のうちの最も古い評価値Ｅ１を消去するとともに、新たに入力された評価値Ｅ６を追加することにより、所定数の評価値を更新する。 Furthermore, at time t6 when 1 second has elapsed from time t5, the evaluation value trend storage unit 134 receives the evaluation value E6 of the vibration waveform data D6 to D15 for 10 seconds immediately before time t6 from the evaluation value calculation unit 140. The oldest evaluation value E1 out of the total of five evaluation values E1 to E5 is deleted, and a newly input evaluation value E6 is added to update a predetermined number of evaluation values.
　このようにして、評価値トレンド記憶部１３４は、所定の時間間隔で、時間的に連続する所定数の評価値（評価値トレンド）を更新する。 In this way, the evaluation value trend storage unit 134 updates a predetermined number of evaluation values (evaluation value trends) that are temporally continuous at predetermined time intervals.
　図１４に戻って、計測トリガ発生部１８０は、評価値トレンド記憶部１３４から時間的に連続する所定数の評価値（評価値トレンド）を読み出すと、読み出した評価値トレンドに基づいて、振動波形データの計測を開始するためのトリガ（以下、「計測トリガ」とも称する。）を発生する。計測トリガ発生部１８０は、発生した計測トリガを振動波形データ出力部１７０へ出力する。 Returning to FIG. 14, when the measurement trigger generation unit 180 reads out a predetermined number of evaluation values (evaluation value trends) that are temporally continuous from the evaluation value trend storage unit 134, a vibration waveform is generated based on the read evaluation value trend. A trigger for starting data measurement (hereinafter also referred to as “measurement trigger”) is generated. The measurement trigger generation unit 180 outputs the generated measurement trigger to the vibration waveform data output unit 170.
　図１７は、図１４に示した計測トリガ発生部１８０および振動波形データ出力部１７０の動作を説明する図である。図１７には、評価値トレンド記憶部１３４に格納される評価値トレンドと、これに基づいて計測トリガ発生部１８０から発生される計測トリガ、および振動波形データ出力部１７０から出力される軸受６０の振動波形データの一例を示している。 FIG. 17 is a diagram for explaining the operations of the measurement trigger generation unit 180 and the vibration waveform data output unit 170 shown in FIG. 17 shows the evaluation value trend stored in the evaluation value trend storage unit 134, the measurement trigger generated from the measurement trigger generation unit 180 based on the evaluation value trend, and the bearing 60 output from the vibration waveform data output unit 170. An example of vibration waveform data is shown.
　図１７中のＥｉ－４，Ｅｉ－３，・・・Ｅｉ，Ｅｉ＋１は、所定の時間間隔で、評価値トレンド記憶部１３４に与えられる評価値を表わしている。図１７の例では、所定の時間間隔を１秒間隔としている。Ｅｉは時刻ｔｉにおいて評価値トレンド記憶部１３４に与えられる評価値を示し、Ｅｉ－１は時刻ｔｉ－１において評価値トレンド記憶部１３４に与えられる評価値を示し、Ｅｉ＋１は時刻ｔｉ＋１において評価値トレンド記憶部１３４に与えられる評価値を示す。 In FIG. 17, Ei-4, Ei-3,... Ei, Ei + 1 represent evaluation values given to the evaluation value trend storage unit 134 at predetermined time intervals. In the example of FIG. 17, the predetermined time interval is 1 second. Ei represents an evaluation value given to the evaluation value trend storage unit 134 at time ti, Ei-1 represents an evaluation value given to the evaluation value trend storage unit 134 at time ti-1, and Ei + 1 represents an evaluation value trend at time ti + 1. An evaluation value given to the storage unit 134 is shown.
　計測トリガ発生部１８０は、評価値の時間的変化の傾向を表わす評価値トレンドが変化したか否かを判定する。評価値トレンドが変化したと判定されると、計測トリガ発生部１８０は計測トリガを発生する。具体的には、計測トリガ発生部１８０は、評価値の時間的変化率、すなわち単位時間内の変化量に基づいて、評価値トレンドが変化したか否かを判定する。 The measurement trigger generation unit 180 determines whether or not the evaluation value trend indicating the tendency of the evaluation value over time has changed. When it is determined that the evaluation value trend has changed, the measurement trigger generator 180 generates a measurement trigger. Specifically, the measurement trigger generation unit 180 determines whether or not the evaluation value trend has changed based on the temporal change rate of the evaluation value, that is, the amount of change within the unit time.
　図１７の例では、計測トリガ発生部１８０は、時刻ｔｉにて評価値Ｅｉが評価値トレンド記憶部１３４に格納されると、時刻ｔｉにおける評価値Ｅｉと時刻ｔｉ＋１における評価値Ｅｉ－１との差に基づいて、評価値の時間的変化率を演算する。時刻ｔｉにおける評価値の時間的変化率をｄＥｉとすると、ｄＥｉは式（２）で表される。 In the example of FIG. 17, when the evaluation value Ei is stored in the evaluation value trend storage unit 134 at time ti, the measurement trigger generation unit 180 calculates the evaluation value Ei at time ti and the evaluation value Ei−1 at time ti + 1. Based on the difference, the temporal change rate of the evaluation value is calculated. If the rate of change of the evaluation value at time ti is dEi, dEi is expressed by equation (2).
　ｄＥｉ＝（Ｅｉ－Ｅｉ＋１）／（ｔｉ－ｔｉ＋１）　　…（２）
　計測トリガ発生部１８０は、演算した時間的変化率ｄＥｉと予め定められた閾値αとを比較する。時間的変化率ｄＥｉが閾値α以上である場合、計測トリガ発生部１８０は、計測トリガをオンに設定する。一方、時間的変化率ｄＥｉが閾値αより小さい場合、計測トリガ発生部１８０は、計測トリガをオフに設定する。図１７には、時刻ｔｉ＋１における時間的変化率ｄＥｉ＋１が閾値α以上である場合が示されている。この場合、時刻ｔｉ＋１において、計測トリガ発生部１８０は、計測トリガをオフからオンに切り替える。計測トリガ発生部１８０は、計測トリガを振動波形データ出力部１７０へ出力する。 dEi = (Ei−Ei + 1) / (ti−ti + 1) (2)
The measurement trigger generation unit 180 compares the calculated temporal change rate dEi with a predetermined threshold value α. When the temporal change rate dEi is equal to or greater than the threshold value α, the measurement trigger generation unit 180 sets the measurement trigger to ON. On the other hand, when the temporal change rate dEi is smaller than the threshold value α, the measurement trigger generation unit 180 sets the measurement trigger to OFF. FIG. 17 shows a case where the temporal change rate dEi + 1 at time ti + 1 is equal to or greater than the threshold value α. In this case, at time ti + 1, measurement trigger generator 180 switches the measurement trigger from off to on. The measurement trigger generator 180 outputs the measurement trigger to the vibration waveform data output unit 170.
　振動波形データ出力部１７０は、計測トリガ発生部１８０から計測トリガを受けると、振動波形データ記憶部１３２に格納されている、一定時間内における軸受６０の振動波形データを読み出す。この一定時間内における軸受６０の振動波形データは、計測トリガが発生した時点の直前の一定時間内における軸受６０の振動波形データに相当する。図１７の例では、時刻ｔｉ＋１の直前の１０秒間分の振動波形データＤｉ－９～Ｄｉが振動波形データ記憶部１３２から読み出される。 When receiving the measurement trigger from the measurement trigger generation unit 180, the vibration waveform data output unit 170 reads the vibration waveform data of the bearing 60 within a predetermined time stored in the vibration waveform data storage unit 132. The vibration waveform data of the bearing 60 within the certain time corresponds to the vibration waveform data of the bearing 60 within the certain time immediately before the time when the measurement trigger is generated. In the example of FIG. 17, vibration waveform data Di-9 to Di for 10 seconds immediately before time ti + 1 are read from the vibration waveform data storage unit 132.
　振動波形データ出力部１７０は、さらに、時刻ｔｉ＋１以降における軸受６０の振動波形データを実効値演算部１２０から受ける。図１７の例では、振動波形データ出力部１７０は、時刻ｔｉ＋１以降の１０秒間分の振動波形データＤｉ＋１～Ｄｉ＋１０を実効値演算部１２０から受ける。 Further, the vibration waveform data output unit 170 receives the vibration waveform data of the bearing 60 after the time ti + 1 from the effective value calculation unit 120. In the example of FIG. 17, the vibration waveform data output unit 170 receives vibration waveform data Di + 1 to Di + 10 for 10 seconds after time ti + 1 from the effective value calculation unit 120.
　振動波形データ出力部１７０は、計測トリガが発生した時点である時刻ｔｉ＋１の直前の一定時間内における軸受６０の振動波形データＤｉ－９～Ｄｉと、計測トリガが発生した時点である時刻ｔｉ＋１以降における軸受６０の振動波形データＤｉ＋１～Ｄｉ＋１０とをひとまとめにして、診断部１５０へ出力する。 The vibration waveform data output unit 170 includes vibration waveform data Di-9 to Di of the bearing 60 within a certain time immediately before time ti + 1, which is the time when the measurement trigger is generated, and time ti + 1 and later, which is the time when the measurement trigger is generated. The vibration waveform data Di + 1 to Di + 10 of the bearing 60 are collectively output to the diagnosis unit 150.
　診断部１５０は、ひとまとめにされた軸受６０の振動波形データＤｉ－９～Ｄｉ＋１０を受けると、これに基づいて軸受６０の異常を診断する。すなわち、診断部１５０は、評価値の時間的変化の傾向が変化したことによって計測トリガが発生されると、振動波形データの計測を開始するように構成される。 The diagnosis unit 150 receives the combined vibration waveform data Di-9 to Di + 10 of the bearing 60, and diagnoses the abnormality of the bearing 60 based on the received vibration waveform data Di-9 to Di + 10. That is, the diagnosis unit 150 is configured to start measurement of vibration waveform data when a measurement trigger is generated due to a change in the tendency of the evaluation value to change over time.
　以上のように、実施の形態５に係る状態監視システムによれば、一定時間内における振動波形データを特徴付ける評価値を演算し、この評価値の時間的変化の傾向を示す、評価値の時間的変化率が変化したときに、振動波形データの計測を開始させるトリガを発生する。このようにすると、振動波形データに重畳するノイズの影響が適切に排除された評価値に基づいて、トリガを発生させることができるため、ノイズの影響を受けて頻繁にトリガが発生することを防止することができる。この結果、軸受６０に故障が発生したときの振動波形データを確実かつ効率的に計測することができるため、正確な異常診断を実現することができる。 As described above, according to the state monitoring system according to the fifth embodiment, the evaluation value characterizing the vibration waveform data within a predetermined time is calculated, and the evaluation value temporally indicating the tendency of the evaluation value to change over time is calculated. When the change rate changes, a trigger for starting measurement of vibration waveform data is generated. In this way, the trigger can be generated based on the evaluation value in which the influence of noise superimposed on the vibration waveform data is appropriately eliminated, thus preventing frequent triggers due to the influence of noise. can do. As a result, since vibration waveform data when a failure occurs in the bearing 60 can be reliably and efficiently measured, an accurate abnormality diagnosis can be realized.
　ここで、診断部１５０に与えられる、ひとまとめにされた軸受６０の振動波形データＤｉ－９～Ｄｉ＋１０は、計測トリガが発生した時点、すなわち、評価値の時間的変化の傾向が変化した時点の前後にわたって取得された軸受６０の振動波形データに相当するものである。したがって、診断部１５０は、これらの振動波形データを分析することで、評価値の時間的変化の傾向が変化した時点前後での軸受６０の状態を、事後に調査することができる。 Here, the combined vibration waveform data Di-9 to Di + 10 of the bearing 60 supplied to the diagnosis unit 150 is before and after the time point when the measurement trigger occurs, that is, the time point when the tendency of the evaluation value changes. This corresponds to the vibration waveform data of the bearing 60 acquired over the entire time. Therefore, the diagnosis unit 150 can analyze the state of the bearing 60 before and after the time point when the tendency of the evaluation value changes with time by analyzing these vibration waveform data.
　なお、振動波形データ記憶部１３２は、計測トリガが発生した時点の直前の一定時間内における軸受６０の振動波形データを格納する一方で、計測トリガが発生しないときの軸受６０の振動波形データを消去するように構成される。これによれば、振動波形データ記憶部１３２を、事後の調査に有用となるデータのみを格納することができる記憶容量とすればよいため、データ処理装置８０に内蔵されるメモリの記憶容量が大きくなりすぎることを回避することができる。 The vibration waveform data storage unit 132 stores the vibration waveform data of the bearing 60 within a certain time immediately before the time when the measurement trigger is generated, while deleting the vibration waveform data of the bearing 60 when the measurement trigger is not generated. Configured to do. According to this, since the vibration waveform data storage unit 132 only needs to have a storage capacity that can store only data useful for the subsequent investigation, the storage capacity of the memory built in the data processing device 80 is large. It is possible to avoid becoming too much.
　また、データ処理装置８０において、振動波形データ記憶部１３２および評価値トレンド記憶部１３４を、実効値演算部１２０から出力される振動波形データを時々刻々と格納するための記憶部とは独立したメモリによって構成することができる。このようにすると、風力発電装置１０の用途および状況などに応じて、振動波形データ記憶部１３２および評価値トレンド記憶部１３４を増設または撤去を容易に行なうことができる。 In the data processing device 80, the vibration waveform data storage unit 132 and the evaluation value trend storage unit 134 are independent from the storage unit for storing the vibration waveform data output from the effective value calculation unit 120 momentarily. Can be configured. In this way, the vibration waveform data storage unit 132 and the evaluation value trend storage unit 134 can be easily added or removed according to the use and situation of the wind power generator 10.
　次に、図１８および図１９を参照して、実施の形態５に係る状態監視システムにおける軸受６０の異常診断のための制御処理を説明する。 Next, with reference to FIG. 18 and FIG. 19, a control process for abnormality diagnosis of the bearing 60 in the state monitoring system according to the fifth embodiment will be described.
　図１８は、実施の形態５に係る状態監視システムにおける軸受６０の振動波形データを格納するための制御処理を説明するフローチャートである。図１８に示される制御処理は、振動波形データ記憶部１３２により、所定の時間間隔で繰り返し実行される。たとえば、図１５の例では、図１８に示される制御処理が、１秒間隔で繰り返し実行される。 FIG. 18 is a flowchart illustrating a control process for storing vibration waveform data of the bearing 60 in the state monitoring system according to the fifth embodiment. The control process shown in FIG. 18 is repeatedly executed by the vibration waveform data storage unit 132 at predetermined time intervals. For example, in the example of FIG. 15, the control process shown in FIG. 18 is repeatedly executed at intervals of 1 second.
　図１８を参照して、振動波形データ記憶部１３２は、ステップＳ２１により、軸受６０の振動波形データを実効値演算部１２０から受ける。振動波形データ記憶部１３２は、ステップＳ２２により、格納されている軸受６０の振動波形データの数が所定数Ｘ以上であるか否かを判定する。この所定数Ｘは、一定時間内に取得される軸受６０の振動波形データの数に値する。図１５の例では、一定時間を１０秒間としているため、所定数Ｘは、一定時間を所定の時間間隔で除算した値である「１０」に設定される。 Referring to FIG. 18, the vibration waveform data storage unit 132 receives the vibration waveform data of the bearing 60 from the effective value calculation unit 120 in step S21. In step S22, the vibration waveform data storage unit 132 determines whether or not the number of stored vibration waveform data of the bearing 60 is equal to or greater than a predetermined number X. This predetermined number X is equivalent to the number of vibration waveform data of the bearing 60 acquired within a certain time. In the example of FIG. 15, since the predetermined time is 10 seconds, the predetermined number X is set to “10” that is a value obtained by dividing the predetermined time by a predetermined time interval.
　格納されている軸受６０の振動波形データの数が所定数Ｘ以上である場合（Ｓ２２のＹＥＳ判定時）、振動波形データ記憶部１３２は、ステップＳ２３に進み、所定数Ｘの振動波形データのうちの最も古い振動波形データを消去する。そして、振動波形データ記憶部１３２は、ステップＳ２４により、ステップＳ２１で取得された振動波形データを追加する。 When the number of stored vibration waveform data of the bearing 60 is equal to or greater than the predetermined number X (when YES in S22), the vibration waveform data storage unit 132 proceeds to step S23 and includes the predetermined number X of vibration waveform data. Delete the oldest vibration waveform data. And vibration waveform data storage part 132 adds vibration waveform data acquired at Step S21 by Step S24.
　一方、格納されている軸受６０の振動波形データの数が所定数Ｘよりも少ない場合（Ｓ２２のＮＯ判定時）、振動波形データ記憶部１３２は、ステップＳ２４に進み、ステップＳ２１で取得された振動波形データを追加する。このようにして、振動波形データ記憶部１３２は、所定の時間間隔で、一定時間内における振動波形データを更新する。 On the other hand, when the number of stored vibration waveform data of the bearing 60 is smaller than the predetermined number X (when NO is determined in S22), the vibration waveform data storage unit 132 proceeds to step S24 and acquires the vibration acquired in step S21. Add waveform data. In this way, the vibration waveform data storage unit 132 updates the vibration waveform data within a predetermined time at predetermined time intervals.
　図１９は、実施の形態５に係る状態監視システムにおける軸受６０の振動波形データの計測トリガを発生するための制御処理を説明するフローチャートである。図１９に示される制御処理は、評価値演算部１４０、評価値トレンド記憶部１３４、計測トリガ発生部１８０および振動波形データ出力部１７０により、所定の時間間隔で繰り返し実行される。 FIG. 19 is a flowchart illustrating a control process for generating a measurement trigger for vibration waveform data of the bearing 60 in the state monitoring system according to the fifth embodiment. The control process shown in FIG. 19 is repeatedly executed at predetermined time intervals by the evaluation value calculation unit 140, the evaluation value trend storage unit 134, the measurement trigger generation unit 180, and the vibration waveform data output unit 170.
　図１９を参照して、評価値演算部１４０は、ステップＳ３１により、振動波形データ記憶部１３２から、一定時間内における軸受６０の振動波形データを読み出す。 Referring to FIG. 19, evaluation value calculation unit 140 reads vibration waveform data of bearing 60 within a predetermined time from vibration waveform data storage unit 132 in step S31.
　評価値演算部１４０は、ステップＳ３２により、ステップＳ３１で読み出した一定時間内における軸受６０の振動波形データを統計処理することにより、一定時間内における軸受６０の振動波形データの評価値を演算する。評価値演算部１４０は、演算した評価値を評価値トレンド記憶部１３４へ出力する。 The evaluation value calculation unit 140 calculates the evaluation value of the vibration waveform data of the bearing 60 within a predetermined time by performing statistical processing on the vibration waveform data of the bearing 60 within the predetermined time read out at step S31 in step S32. The evaluation value calculation unit 140 outputs the calculated evaluation value to the evaluation value trend storage unit 134.
　評価値トレンド記憶部１３４は、ステップＳ３３により、格納されている評価値のデータ数が所定数Ｙ以上であるか否かを判定する。この所定数Ｙは、評価値の時間的変化の傾向を表す評価値トレンドを取得するために必要なデータ数に相当する。所定数Ｙは２以上の数に設定される。図１５の例では、所定数Ｙは５に設定されている。 The evaluation value trend storage unit 134 determines whether or not the number of stored evaluation value data is a predetermined number Y or more in step S33. The predetermined number Y corresponds to the number of data necessary for obtaining an evaluation value trend representing a tendency of the evaluation value to change over time. The predetermined number Y is set to a number of 2 or more. In the example of FIG. 15, the predetermined number Y is set to 5.
　格納されている評価値のデータ数が所定数Ｙ以上である場合（Ｓ３３のＹＥＳ判定時）、評価値トレンド記憶部１３４は、ステップＳ３４に進み、所定数Ｙの評価値のうちの最も古い評価値を消去する。そして、評価値トレンド記憶部１３４は、ステップＳ３５により、ステップＳ３２で演算した評価値を追加する。 If the number of stored evaluation value data is greater than or equal to the predetermined number Y (when YES is determined in S33), the evaluation value trend storage unit 134 proceeds to step S34 and evaluates the oldest evaluation value among the predetermined number Y of evaluation values. Erase the value. And the evaluation value trend memory | storage part 134 adds the evaluation value calculated by step S32 by step S35.
　一方、格納されている評価値のデータ数が所定数Ｙよりも少ない場合（Ｓ３３のＮＯ判定時）、評価値トレンド記憶部１３４は、ステップＳ３５に進み、ステップＳ３２で演算した評価値を追加する。このようにして、評価値トレンド記憶部１３４は、所定の時間間隔で、所定数Ｙの評価値を更新する。 On the other hand, when the number of stored evaluation value data is smaller than the predetermined number Y (NO determination in S33), the evaluation value trend storage unit 134 proceeds to step S35 and adds the evaluation value calculated in step S32. . In this way, the evaluation value trend storage unit 134 updates the predetermined number Y of evaluation values at predetermined time intervals.
　計測トリガ発生部１８０は、ステップＳ３６により、評価値トレンド記憶部１３４から時間的に連続する所定数Ｙの評価値（評価値トレンド）を読み出すと、読み出した評価値トレンドにおける評価値の時間的変化率を演算する。ステップＳ３６において、計測トリガ発生部１８０は、ステップＳ３５で追加された評価値と、この評価値の１つ前に追加された評価値とを評価値トレンド記憶部１３４から読み出す。そして、計測トリガ発生部１８０は、上記式（２）を用いて、読み出した２つの評価値の差に基づいて、評価値の時間的変化率を演算する。 When the measurement trigger generation unit 180 reads out a predetermined number Y of evaluation values (evaluation value trend) continuous in time from the evaluation value trend storage unit 134 in step S36, the temporal change in the evaluation value in the read evaluation value trend. Calculate the rate. In step S36, the measurement trigger generation unit 180 reads the evaluation value added in step S35 and the evaluation value added immediately before this evaluation value from the evaluation value trend storage unit 134. Then, the measurement trigger generation unit 180 calculates the temporal change rate of the evaluation value based on the difference between the two read evaluation values using the above equation (2).
　計測トリガ発生部１８０は、ステップＳ３７により、ステップＳ３６で演算した評価値の時間的変化率と閾値αとを比較する。評価値の時間的変化率が閾値αよりも小さい場合（Ｓ３７のＮＯ判定時）、以降の処理Ｓ３８～Ｓ３１はスキップされる。一方、評価値の時間的変化率が閾値α以上である場合（Ｓ３７のＹＥＳ判定時）、計測トリガ発生部１８０は、ステップＳ３８により、計測トリガを発生し、発生した計測トリガを振動波形データ出力部１７０へ出力する。 In step S37, the measurement trigger generation unit 180 compares the temporal change rate of the evaluation value calculated in step S36 with the threshold value α. When the temporal change rate of the evaluation value is smaller than the threshold value α (when NO is determined in S37), the subsequent processes S38 to S31 are skipped. On the other hand, when the temporal change rate of the evaluation value is equal to or greater than the threshold value α (when YES is determined in S37), the measurement trigger generation unit 180 generates a measurement trigger in step S38, and outputs the generated measurement trigger as vibration waveform data. To the unit 170.
　振動波形データ出力部１７０は、計測トリガ発生部１８０から計測トリガを受けると、ステップＳ３９により、振動波形データ記憶部１３２に時々刻々と格納される、計測トリガが発生した時点以降における軸受６０の振動波形データを読み出す。 When the vibration waveform data output unit 170 receives the measurement trigger from the measurement trigger generation unit 180, the vibration waveform data output unit 170 is stored in the vibration waveform data storage unit 132 every moment in step S39. Read waveform data.
　振動波形データ出力部１７０は、さらに、ステップＳ４０により、振動波形データ記憶部１３２に格納されている、一定時間内における軸受６０の振動波形データを読み出す。図１７で説明したように、この一定時間内における軸受６０の振動波形データは、計測トリガが発生した時点の直前の一定時間内における軸受６０の振動波形データに相当する。 The vibration waveform data output unit 170 further reads out the vibration waveform data of the bearing 60 within a predetermined time stored in the vibration waveform data storage unit 132 in step S40. As described with reference to FIG. 17, the vibration waveform data of the bearing 60 within the certain time corresponds to the vibration waveform data of the bearing 60 within the certain time immediately before the time when the measurement trigger is generated.
　振動波形データ出力部１７０は、ステップＳ４１により、ステップＳ４０で読み出された、計測トリガが発生した時点の直前の一定時間内における軸受６０の振動波形データと、ステップＳ３９で取得された、計測トリガが発生した時点以降における軸受６０の振動波形データをひとまとめにして、診断部１５０へ出力する。これにより、診断部１５０では、ひとまとめにされた軸受６０の振動波形データを用いて軸受６０の異常が診断される。 The vibration waveform data output unit 170 reads the vibration waveform data of the bearing 60 within a certain period of time immediately before the time when the measurement trigger is generated, which is read in step S40 in step S41, and the measurement trigger acquired in step S39. The vibration waveform data of the bearing 60 after the point of occurrence of the failure is collectively output to the diagnosis unit 150. As a result, the diagnosis unit 150 diagnoses the abnormality of the bearing 60 using the vibration waveform data of the bearings 60 collected together.
　（実施の形態５の変形例）
　上記の実施の形態５では、時間的に連続する２つの評価値（たとえば、図１７の評価値Ｅｉ－１，Ｅｉ）の間の時間的変化率（たとえば、図１７のｄＥｉ）を演算し、その演算した時間的変化率と閾値αとを比較した結果に基づいて、計測トリガを発生する構成について説明した。しかしながら、この構成においては、２つの評価値のいずれか一方にノイズが重畳すると、このノイズの影響を受けて評価値の時間的変化率が一時的に閾値αを超える場合が起こり得る。このような場合には、計測トリガ発生部１８０が計測トリガを誤って発生してしまう可能性がある。 (Modification of Embodiment 5)
In the above-described fifth embodiment, the temporal change rate (for example, dEi in FIG. 17) between two temporally continuous evaluation values (for example, the evaluation values Ei−1 and Ei in FIG. 17) is calculated, The configuration for generating the measurement trigger has been described based on the result of comparing the calculated temporal change rate and the threshold value α. However, in this configuration, when noise is superimposed on one of the two evaluation values, the temporal change rate of the evaluation value may temporarily exceed the threshold value α due to the influence of the noise. In such a case, there is a possibility that the measurement trigger generation unit 180 erroneously generates a measurement trigger.
　そこで、このようなノイズの影響により計測トリガを誤って発生することを防ぐため、計測トリガ発生部１８０では、評価値の時間的変化率が閾値α以上であるという判定結果が複数回連続して得られた場合に、計測トリガを発生するように構成することができる。たとえば、図１７の例では、時刻ｔｉ＋１における時間的変化率ｄＥｉ＋１、および時刻ｔｉ＋２における時間的変化率ｄＥｉ＋２がともに閾値α以上であると判定された場合に、計測トリガ発生部１８０が計測トリガを発生する構成とすることができる。 Therefore, in order to prevent the measurement trigger from being erroneously generated due to the influence of such noise, the measurement trigger generation unit 180 continuously receives a determination result that the temporal change rate of the evaluation value is equal to or greater than the threshold value α. If obtained, it can be configured to generate a measurement trigger. For example, in the example of FIG. 17, the measurement trigger generation unit 180 generates a measurement trigger when it is determined that the temporal change rate dEi + 1 at time ti + 1 and the temporal change rate dEi + 2 at time ti + 2 are both equal to or greater than the threshold value α. It can be set as the structure to do.
　このようにすると、時刻ｔｉ＋１における時間的変化率ｄＥｉ＋１が閾値α以上となる一方で、時刻ｔｉ＋２における時間的変化率ｄＥｉ＋２が閾値αよりも小さくなる場合には、計測トリガ発生部１８０は、計測トリガを発生させない。時間的変化率ｄＥｉ＋１の増加がノイズの影響による一時的なものであるとみなされるため、計測トリガが誤って発生することを防ぐことができる。 In this way, when the temporal change rate dEi + 1 at time ti + 1 is equal to or greater than the threshold value α, and when the temporal change rate dEi + 2 at time ti + 2 is smaller than the threshold value α, the measurement trigger generation unit 180 sets the measurement trigger. Does not occur. Since the increase in the temporal change rate dEi + 1 is considered to be temporary due to the influence of noise, it is possible to prevent the measurement trigger from being erroneously generated.
　［実施の形態６］
　上述した実施の形態５では、一定時間内における軸受６０の振動波形データの評価値の時間的変化の傾向が変化したことを評価値の時間的変化率に基づいて判定して、計測トリガを発生する構成について説明した。実施の形態６では、評価値の時間的変化の傾向が変化したことを評価値の大きさに基づいて判定して、計測トリガを発生する構成について説明する。 [Embodiment 6]
In the above-described fifth embodiment, a measurement trigger is generated by determining that the tendency of the temporal change in the evaluation value of the vibration waveform data of the bearing 60 within a predetermined time has changed based on the temporal change rate of the evaluation value. The configuration to be described has been described. In the sixth embodiment, a configuration in which a measurement trigger is generated by determining that a tendency of a temporal change in an evaluation value has changed based on the magnitude of the evaluation value will be described.
　図２０は、実施の形態６に係る状態監視システムにおける軸受６０の振動波形データの計測トリガを発生するための制御処理を説明するフローチャートである。図２０に示される制御処理は、評価値演算部１４０、評価値トレンド記憶部１３４、計測トリガ発生部１８０および振動波形データ出力部１７０により、所定の時間間隔で繰り返し実行される。 FIG. 20 is a flowchart illustrating a control process for generating a measurement trigger for vibration waveform data of the bearing 60 in the state monitoring system according to the sixth embodiment. The control process shown in FIG. 20 is repeatedly executed at predetermined time intervals by the evaluation value calculation unit 140, the evaluation value trend storage unit 134, the measurement trigger generation unit 180, and the vibration waveform data output unit 170.
　図２０を図１９と比較して、実施の形態６に係る状態監視システムでは、図１９と同様のステップＳ３１～Ｓ３５の処理後に、ステップＳ３６，Ｓ３７に代えて、ステップＳ３７Ａを実行する。 FIG. 20 is compared with FIG. 19 and the state monitoring system according to the sixth embodiment executes step S37A instead of steps S36 and S37 after the processing of steps S31 to S35 similar to FIG.
　すなわち、ステップＳ３５により、評価値トレンド記憶部１３４がステップＳ３２で演算した評価値を追加すると、計測トリガ発生部１８０は、ステップＳ３７Ａにより、ステップＳ３５で追加された評価値と閾値βとを比較する。評価値が閾値βよりも小さい場合（Ｓ３７ＡのＮＯ判定時）、以降の処理Ｓ３８～Ｓ４１はスキップされる。一方、評価値が閾値β以上である場合（Ｓ３７ＡのＹＥＳ判定時）、計測トリガ発生部１８０は、図１９と同様のステップＳ３８の処理によって計測トリガを発生する。 That is, when the evaluation value trend storage unit 134 adds the evaluation value calculated in step S32 in step S35, the measurement trigger generation unit 180 compares the evaluation value added in step S35 with the threshold value β in step S37A. . When the evaluation value is smaller than the threshold β (when NO is determined in S37A), the subsequent processes S38 to S41 are skipped. On the other hand, when the evaluation value is equal to or greater than the threshold value β (when YES is determined in S37A), the measurement trigger generation unit 180 generates a measurement trigger by the process of step S38 similar to FIG.
　振動波形データ出力部１７０は、図１９と同様のステップＳ３９～Ｓ４１の処理を行なうことにより、計測トリガが発生した時点の直前の一定時間内における軸受６０の振動波形データと、計測トリガが発生した時点以降における軸受６０の振動波形データをひとまとめにして、診断部１５０へ出力する。 The vibration waveform data output unit 170 performs the processing of steps S39 to S41 similar to FIG. 19, so that the vibration waveform data of the bearing 60 and the measurement trigger are generated within a certain time immediately before the time when the measurement trigger is generated. The vibration waveform data of the bearing 60 after the time is collectively output to the diagnosis unit 150.
　以上のように、実施の形態６によれば、一定時間内における振動波形データを特徴付ける評価値を演算し、この評価値の大きさが閾値β以上となったときに評価値の時間的変化の傾向が変化したと判定して、振動波形データの計測を開始させるトリガを発生する。このようにすると、振動波形データに重畳するノイズの影響が適切に排除された評価値に基づいてトリガを発生させることができる。したがって、実施の形態６においても、実施の形態５と同様の効果を得ることができる。 As described above, according to the sixth embodiment, the evaluation value that characterizes the vibration waveform data within a predetermined time is calculated, and when the magnitude of the evaluation value becomes equal to or larger than the threshold value β, the temporal change of the evaluation value is calculated. It is determined that the tendency has changed, and a trigger for starting measurement of vibration waveform data is generated. In this way, the trigger can be generated based on the evaluation value from which the influence of noise superimposed on the vibration waveform data is appropriately eliminated. Therefore, also in the sixth embodiment, the same effect as in the fifth embodiment can be obtained.
　（実施の形態６の変形例）
　上記の実施の形態６では、評価値と閾値βとを比較した結果に基づいて、計測トリガを発生する構成について説明した。しかしながら、この構成においては、評価値にノイズが重畳することによって評価値が一時的に閾値β以上となる場合に、計測トリガ発生部１８０が計測トリガを誤って発生してしまう可能性がある。 (Modification of Embodiment 6)
In the sixth embodiment, the configuration for generating the measurement trigger based on the result of comparing the evaluation value and the threshold value β has been described. However, in this configuration, when the evaluation value temporarily exceeds the threshold value β due to noise superimposed on the evaluation value, the measurement trigger generation unit 180 may erroneously generate the measurement trigger.
　このようなノイズの影響により計測トリガを誤って発生することを防ぐため、計測トリガ発生部１８０では、評価値が閾値β以上であるという判定結果が複数回連続して得られた場合に、計測トリガを発生するように構成することができる。たとえば、図１７の例では、時刻ｔｉ＋１における評価値Ｅｉ＋１、および時刻ｔｉ＋２における評価値Ｅｉ＋２がともに閾値β以上であると判定された場合に、計測トリガ発生部１８０が計測トリガを発生する構成とすることができる。 In order to prevent the measurement trigger from being erroneously generated due to the influence of such noise, the measurement trigger generation unit 180 performs measurement when the determination result that the evaluation value is equal to or greater than the threshold value β is continuously obtained a plurality of times. It can be configured to generate a trigger. For example, in the example of FIG. 17, the measurement trigger generation unit 180 generates a measurement trigger when it is determined that the evaluation value Ei + 1 at time ti + 1 and the evaluation value Ei + 2 at time ti + 2 are both greater than or equal to the threshold value β. be able to.
　このようにすると、時刻ｔｉ＋１における評価値Ｅｉ＋１が閾値β以上となる一方で、時刻ｔｉ＋２における評価値Ｅｉ＋２が閾値βよりも小さくなる場合には、計測トリガ発生部１８０は、計測トリガを発生させない。評価値Ｅｉ＋１の増加がノイズの影響による一時的なものであるとみなされるため、計測トリガが誤って発生することを防ぐことができる。 In this way, when the evaluation value Ei + 1 at the time ti + 1 is equal to or greater than the threshold value β, but the evaluation value Ei + 2 at the time ti + 2 is smaller than the threshold value β, the measurement trigger generation unit 180 does not generate a measurement trigger. Since the increase in the evaluation value Ei + 1 is considered to be temporary due to the influence of noise, it is possible to prevent the measurement trigger from being erroneously generated.
　［実施の形態７］
　実施の形態７では、評価値の時間的変化の傾向が変化したことを評価値の時間的変化率および大きさに基づいて判定して、計測トリガを発生する構成について説明する。 [Embodiment 7]
In the seventh embodiment, a configuration will be described in which it is determined that the tendency of the evaluation value to change over time is changed based on the time change rate and magnitude of the evaluation value, and a measurement trigger is generated.
　図２１は、実施の形態７に係る状態監視システムにおける軸受６０の振動波形データの計測トリガを発生するための制御処理を説明するフローチャートである。図２１に示される制御処理は、評価値演算部１４０、評価値トレンド記憶部１３４、計測トリガ発生部１８０および振動波形データ出力部１７０により、所定の時間間隔で繰り返し実行される。 FIG. 21 is a flowchart illustrating a control process for generating a measurement trigger for vibration waveform data of the bearing 60 in the state monitoring system according to the seventh embodiment. The control processing shown in FIG. 21 is repeatedly executed at predetermined time intervals by the evaluation value calculation unit 140, the evaluation value trend storage unit 134, the measurement trigger generation unit 180, and the vibration waveform data output unit 170.
　図２１を図１９と比較して、実施の形態７に係る状態監視システムでは、図１９と同様のステップＳ３１～Ｓ３６の処理後に、ステップＳ３７に加えて、ステップＳ３７Ａを実行する。 FIG. 21 is compared with FIG. 19 and the state monitoring system according to the seventh embodiment executes step S37A in addition to step S37 after the processing of steps S31 to S36 similar to FIG.
　すなわち、ステップＳ３５により、評価値トレンド記憶部１３４がステップＳ３２で演算した評価値を追加すると、計測トリガ発生部１８０は、ステップＳ３７により、ステップＳ３６で演算した評価値の時間的変化率と閾値α（第１の閾値）とを比較する。評価値の時間的変化率が閾値αよりも小さい場合（Ｓ３７のＮＯ判定時）、以降の処理Ｓ３７Ａ～Ｓ４１はスキップされる。一方、評価値の時間的変化率が閾値α以上である場合（Ｓ３７のＹＥＳ判定時）、計測トリガ発生部１８０は、ステップＳ３７Ａに進み、ステップＳ３５で追加された評価値と閾値β（第２の閾値）とを比較する。評価値が閾値βよりも小さい場合（Ｓ３７ＡのＮＯ判定時）、以降の処理Ｓ３８～Ｓ４１はスキップされる。 That is, when the evaluation value trend storage unit 134 adds the evaluation value calculated in step S32 in step S35, the measurement trigger generation unit 180 performs the temporal change rate and threshold value α of the evaluation value calculated in step S36 in step S37. (First threshold) is compared. When the temporal change rate of the evaluation value is smaller than the threshold value α (when NO is determined in S37), the subsequent processes S37A to S41 are skipped. On the other hand, when the temporal change rate of the evaluation value is equal to or greater than the threshold value α (when YES is determined in S37), the measurement trigger generation unit 180 proceeds to step S37A, and the evaluation value added in step S35 and the threshold value β (second The threshold). When the evaluation value is smaller than the threshold β (when NO is determined in S37A), the subsequent processes S38 to S41 are skipped.
　一方、評価値が閾値β以上である場合（Ｓ３７ＡのＹＥＳ判定時）、計測トリガ発生部１８０は、図１９と同様のステップＳ３８の処理によって計測トリガを発生する。 On the other hand, when the evaluation value is equal to or greater than the threshold value β (when YES is determined in S37A), the measurement trigger generation unit 180 generates a measurement trigger by the process of step S38 similar to FIG.
　振動波形データ出力部１７０は、図１９と同様のステップＳ３９～Ｓ４１の処理を行なうことにより、計測トリガが発生した時点の直前の一定時間内における軸受６０の振動波形データと、計測トリガが発生した時点以降における軸受６０の振動波形データをひとまとめにして、診断部１５０へ出力する。 The vibration waveform data output unit 170 performs the processing of steps S39 to S41 similar to FIG. 19, so that the vibration waveform data of the bearing 60 and the measurement trigger are generated within a certain time immediately before the time when the measurement trigger is generated. The vibration waveform data of the bearing 60 after the time is collectively output to the diagnosis unit 150.
　以上のように、実施の形態７によれば、一定時間内における振動波形データを特徴付ける評価値を演算し、この評価値の時間的変化率が閾値α以上となり、かつ、評価値の大きさが閾値β以上となったときに評価値の時間的変化の傾向が変化したと判定して、振動波形データの計測を開始させるトリガを発生する。評価値の時間的変化率が閾値α以上となった場合であっても、評価値の大きさが閾値βよりも小さいときには、軸受６０の振動の大きさである振動度が小さいためにノイズの影響度が大きくなっているものと判定することができる。このような場合には、トリガを発生させない構成とすることで、振動波形データに重畳するノイズの影響が適切に排除された評価値に基づいてトリガを発生させることができる。したがって、実施の形態７においても、実施の形態５と同様の効果を得ることができる。 As described above, according to the seventh embodiment, the evaluation value characterizing the vibration waveform data within a predetermined time is calculated, the temporal change rate of the evaluation value is equal to or higher than the threshold value α, and the magnitude of the evaluation value is When it becomes more than threshold value (beta), it determines with the tendency of the time change of an evaluation value having changed, and the trigger which starts the measurement of vibration waveform data is generated. Even when the temporal change rate of the evaluation value is equal to or greater than the threshold value α, when the evaluation value is smaller than the threshold value β, the degree of vibration, which is the magnitude of vibration of the bearing 60, is small, so It can be determined that the degree of influence has increased. In such a case, by adopting a configuration in which the trigger is not generated, the trigger can be generated based on the evaluation value from which the influence of noise superimposed on the vibration waveform data is appropriately eliminated. Therefore, also in the seventh embodiment, the same effect as in the fifth embodiment can be obtained.
　（実施の形態７の変形例）
　上述のように、評価値にノイズが重畳すると、評価値の時間的変化率が一時的に閾値α以上となる、または、評価値が一時的に閾値β以上となることで、計測トリガ発生部１８０が計測トリガを誤って発生してしまう可能性がある。 (Modification of Embodiment 7)
As described above, when noise is superimposed on the evaluation value, the temporal change rate of the evaluation value temporarily becomes greater than or equal to the threshold value α, or the evaluation value temporarily becomes greater than or equal to the threshold value β. 180 may generate a measurement trigger in error.
　そこで、計測トリガ発生部１８０では、評価値の時間的変化率が閾値α以上であるという判定結果が複数回連続して得られ、かつ、評価値が閾値β以上であるという判定結果が複数回連続して得られた場合に、計測トリガを発生するように構成することができる。これによれば、評価値の増加がノイズの影響による一時的なものであるとみなされるため、計測トリガが誤って発生することを防ぐことができる。 Therefore, in the measurement trigger generation unit 180, a determination result that the temporal change rate of the evaluation value is equal to or greater than the threshold value α is continuously obtained a plurality of times, and a determination result that the evaluation value is equal to or greater than the threshold value β is obtained multiple times. It can be configured to generate a measurement trigger when obtained continuously. According to this, since the increase in the evaluation value is considered to be temporary due to the influence of noise, it is possible to prevent the measurement trigger from being erroneously generated.
　なお、上記の実施の形態５～７においては、風力発電装置１０を構成する機械要素の１つである軸受６０に振動センサ７０を設置して、軸受６０の異常を診断するものとしたが、診断対象となる機械要素は軸受６０に限定されない点について確認的に記載する。たとえば、軸受６０とともに、または軸受６０に代えて、増速機４０内または発電機５０内に設けられる軸受に振動センサを設置し、上記の各実施の形態と同様の手法によって、増速機４０内または発電機５０内に設けられる軸受の異常を診断することができる。 In the above fifth to seventh embodiments, the vibration sensor 70 is installed in the bearing 60 that is one of the mechanical elements constituting the wind power generator 10, and the abnormality of the bearing 60 is diagnosed. The point that the machine element to be diagnosed is not limited to the bearing 60 will be described. For example, a vibration sensor is installed in a bearing provided in the speed increaser 40 or in the generator 50 together with or in place of the bearing 60, and the speed increaser 40 is obtained by the same method as in each of the above embodiments. An abnormality of a bearing provided in the generator 50 or in the generator 50 can be diagnosed.
　また、上記の実施の形態５～７においては、一定時間内における振動波形データを特徴付ける評価値を、当該一定時間内における振動波形データの実効値を統計処理することによって演算する構成について説明したが、当該一定時間内における振動波形データのピーク値を統計処理することによって、評価値を演算する構成としてもよい。この構成において、振動波形データのピーク値とは、振動波形の最大値または最小値の絶対値に相当する。あるいは、当該一定時間内における振動波形データの波高率を統計処理することによって、評価値を演算する構成としてもよい。この構成において、振動波形データの波高率とは、振動波形の最大値に対する実効値の比率に相当する。 In the fifth to seventh embodiments described above, the configuration is described in which the evaluation value characterizing the vibration waveform data within a certain time is calculated by statistically processing the effective value of the vibration waveform data within the certain time. The evaluation value may be calculated by statistically processing the peak value of the vibration waveform data within the predetermined time. In this configuration, the peak value of the vibration waveform data corresponds to the absolute value of the maximum value or the minimum value of the vibration waveform. Alternatively, the evaluation value may be calculated by statistically processing the crest factor of the vibration waveform data within the predetermined time. In this configuration, the crest factor of the vibration waveform data corresponds to the ratio of the effective value to the maximum value of the vibration waveform.
　［実施の形態８］
　実施の形態８では、一定時間内における振動波形データを特徴付ける評価値（図１５）として、当該一定時間内における振動波形データの異常度を演算する構成について説明する。 [Embodiment 8]
In the eighth embodiment, a configuration for calculating the degree of abnormality of vibration waveform data within a certain time will be described as an evaluation value (FIG. 15) that characterizes vibration waveform data within a certain time.
　図２２は、この発明の実施の形態８に係る状態監視システムにおけるデータ処理装置８０の構成を機能的に示す機能ブロック図である。図２２を参照して、データ処理装置８０は、ＢＰＦ１１２と、実効値演算部１２０と、記憶部１３０と、振動波形データ出力部１７０と、評価値演算部１４０と、計測トリガ発生部１８０と、診断部１５０とを含む。 FIG. 22 is a functional block diagram functionally showing the configuration of the data processing device 80 in the state monitoring system according to Embodiment 8 of the present invention. Referring to FIG. 22, the data processing device 80 includes a BPF 112, an effective value calculation unit 120, a storage unit 130, a vibration waveform data output unit 170, an evaluation value calculation unit 140, a measurement trigger generation unit 180, And a diagnosis unit 150.
　記憶部１３０は、振動波形データ記憶部１３２と、評価値トレンド記憶部１３４と、正常データ記憶部１３６とを含む。振動波形データ記憶部１３２、評価値トレンド記憶部１３４および正常データ記憶部１３６は、たとえば、読み書き可能な不揮発性メモリ等によって構成される。 The storage unit 130 includes a vibration waveform data storage unit 132, an evaluation value trend storage unit 134, and a normal data storage unit 136. The vibration waveform data storage unit 132, the evaluation value trend storage unit 134, and the normal data storage unit 136 are configured by, for example, a readable / writable nonvolatile memory.
　振動波形データ記憶部１３２は、図１５で説明したように、一定時間内における軸受６０の振動波形データの実効値（振動波形データ）を格納するように構成される。 The vibration waveform data storage unit 132 is configured to store the effective value (vibration waveform data) of the vibration waveform data of the bearing 60 within a predetermined time, as described with reference to FIG.
　正常データ記憶部１３６は、風力発電装置１０（図１参照）の正常運転が保証されているとき（たとえば初期状態など）に測定された、軸受６０の振動波形データの実効値（振動波形データ）を格納するように構成される。正常データ記憶部１３６に格納された振動波形データは、後述する学習部１４２における分類境界の設定に用いられる。以下の説明では、正常データ記憶部１３６に格納されている振動波形データを「学習データ」とも称する。 The normal data storage unit 136 is an effective value (vibration waveform data) of the vibration waveform data of the bearing 60 measured when normal operation of the wind turbine generator 10 (see FIG. 1) is guaranteed (for example, in an initial state). Configured to store. The vibration waveform data stored in the normal data storage unit 136 is used for setting a classification boundary in the learning unit 142 described later. In the following description, the vibration waveform data stored in the normal data storage unit 136 is also referred to as “learning data”.
　評価値演算部１４０は、一定時間内における軸受６０の振動波形データを振動波形データ記憶部１３２から読み出すと、読み出した一定時間内における軸受６０の振動波形データを特徴付ける評価値を演算する。本実施の形態では、評価値演算部１４０は、学習部１４２と、異常度演算部１４４とを含む。 When the vibration value data of the bearing 60 within a predetermined time is read from the vibration waveform data storage unit 132, the evaluation value calculation unit 140 calculates an evaluation value that characterizes the read vibration waveform data of the bearing 60 within the predetermined time. In the present embodiment, evaluation value calculation unit 140 includes a learning unit 142 and an abnormality degree calculation unit 144.
　学習部１４２は、正常データ記憶部１３６から学習データを読み出すと、読み出した学習データに基づいて、正常と異常とを分類する分類境界を設定する。 When the learning unit 142 reads the learning data from the normal data storage unit 136, the learning unit 142 sets a classification boundary for classifying normal and abnormal based on the read learning data.
　異常度演算部１４４は、振動波形データ記憶部１３２から読み出した一定時間内における軸受６０の振動波形データに分類境界を適用することによって、該振動波形データの異常度を演算する。異常度とは分類境界からの距離に相当する。演算された異常度は、該一定時間内における軸受６０の振動波形データを特徴付ける評価値となる。異常度演算部１４４は、異常度を時間的に連続して演算するように構成される。 The abnormality degree calculation unit 144 calculates the abnormality degree of the vibration waveform data by applying the classification boundary to the vibration waveform data of the bearing 60 within a certain time read from the vibration waveform data storage unit 132. The degree of abnormality corresponds to the distance from the classification boundary. The calculated degree of abnormality is an evaluation value that characterizes the vibration waveform data of the bearing 60 within the predetermined time. The abnormality degree calculating unit 144 is configured to calculate the abnormality degree continuously in time.
　本実施の形態では、評価値演算部１４０は、一定時間内における軸受６０の振動波形データを処理する際に、該振動波形データを複数のセグメントに分割し、セグメントごとに処理する。以下、セグメントについて説明する。 In the present embodiment, the evaluation value calculation unit 140 divides the vibration waveform data into a plurality of segments when processing the vibration waveform data of the bearing 60 within a predetermined time, and processes the data for each segment. Hereinafter, the segment will be described.
　図２３は、一定時間内における軸受６０の振動波形データとセグメントとの関係を示す概念図である。図２３の例では、一定時間内における振動波形データは、図１５の例と同様に、１０秒間分の振動波形データＤ０～Ｄ９である。１０秒間分の振動波形データＤ０～Ｄ９は１０個のセグメントに分割される。 FIG. 23 is a conceptual diagram showing the relationship between the vibration waveform data of the bearing 60 and the segments within a certain time. In the example of FIG. 23, the vibration waveform data within a fixed time is vibration waveform data D0 to D9 for 10 seconds, as in the example of FIG. The vibration waveform data D0 to D9 for 10 seconds are divided into 10 segments.
　異常度演算部１４４は、１０秒間分の振動波形データＤ０～Ｄ９について、セグメントごとに特徴量ベクトルを生成する。学習部１４２も同様に、正常データ記憶部１３６から読み出した学習データについて、セグメントごとに特徴量ベクトルを生成する。 The abnormality degree calculation unit 144 generates a feature vector for each segment for the vibration waveform data D0 to D9 for 10 seconds. Similarly, the learning unit 142 generates a feature vector for each segment for the learning data read from the normal data storage unit 136.
　図２４は、特徴量ベクトルについて説明するための図である。図２４では、１０秒間分の振動波形データＤ０～Ｄ９が１０個のセグメントに分割され、特徴量がｎ個である例を示している。 FIG. 24 is a diagram for explaining the feature quantity vector. FIG. 24 shows an example in which the vibration waveform data D0 to D9 for 10 seconds are divided into 10 segments and the feature quantity is n.
　特徴量は、たとえば、振動波形データの実効値（ＯＡ）、最大値（Ｍａｘ）、波高値（Ｃｒｅｓｔ　ｆａｃｔｏｒ）、尖度、歪度、およびこれらの信号処理（ＦＦＴ処理、ケフレンシ処理）後の値とすることができる。特徴量ベクトルは、ｎ個の特徴量を一組のベクトルとして扱うものである。特徴量ベクトルが異常判定に使用される。図２４の例では、１０秒間分の振動波形データＤ０～Ｄ９に対して、１０個の特徴量ベクトルが生成される。 The feature amount is, for example, the effective value (OA), maximum value (Max), peak value (Crest factor), kurtosis, skewness, and values after these signal processing (FFT processing, quefrency processing) of the vibration waveform data. It can be. The feature vector handles n feature values as a set of vectors. The feature vector is used for abnormality determination. In the example of FIG. 24, ten feature quantity vectors are generated for vibration waveform data D0 to D9 for 10 seconds.
　特徴量の抽出および特徴量ベクトルの生成を、一定時間内における振動波形データ全体をひとまとめにして行なうと、突発的な異常が生じたときにデータ全体が診断に使用できなくなってしまうおそれがある。そのため、本実施の形態では、一定時間内における振動波形データを複数のセグメントに分割し、セグメントを単位として特徴量の抽出および特徴量ベクトルの生成を行なう。たとえば、風力発電装置１０を振動センサ７０で監視しているときに、突発的な振動が振動センサ７０によって一時的に検出される場合がある。このような場合でも突発異常以外の時間では正しい特徴量を抽出することができる。したがって、突発異常に相当するセグメントを除外して、特徴量をセグメントごとに比較して評価することも可能となる。 If extraction of feature amounts and generation of feature amount vectors are performed collectively for the entire vibration waveform data within a certain period of time, the entire data may not be usable for diagnosis when a sudden abnormality occurs. Therefore, in the present embodiment, vibration waveform data within a certain time is divided into a plurality of segments, and feature amounts are extracted and feature amount vectors are generated in units of segments. For example, when the wind power generation apparatus 10 is monitored by the vibration sensor 70, sudden vibration may be temporarily detected by the vibration sensor 70. Even in such a case, a correct feature amount can be extracted at a time other than the sudden abnormality. Therefore, it is possible to exclude the segment corresponding to the sudden abnormality and compare and evaluate the feature value for each segment.
　図２４に示すように、特徴量ベクトル０～９に対して、分類境界に基づいて異常度０～９が演算される。分類境界は、既知の異常検出方法（One　Class　Support　Vector　Machine：ＯＣ－ＳＶＭ）で使用される異常判別を行なうための指標である。 As shown in FIG. 24, the degree of abnormality 0 to 9 is calculated for the feature vectors 0 to 9 based on the classification boundary. The classification boundary is an index for performing abnormality determination used in a known abnormality detection method (One Class Support Vector Machine: OC-SVM).
　図２５は、ＯＣ－ＳＶＭの基本概念を説明するための図である。図２５の縦軸および横軸は互いに異なる特徴量である。図２５において、丸印「○」は学習データであり、四角印「□」および三角印「△」は振動波形データである。なお、振動波形データのうち、「□」が異常を示すデータであり、「△」は正常を示すデータであるとする。 FIG. 25 is a diagram for explaining the basic concept of OC-SVM. The vertical axis and the horizontal axis in FIG. In FIG. 25, a circle mark “◯” is learning data, and a square mark “□” and a triangle mark “Δ” are vibration waveform data. In the vibration waveform data, “□” is data indicating abnormality, and “Δ” is data indicating normal.
　たとえば図２５（Ａ）に示すように、特徴量が２個の場合の二次元の散布図上では、学習データおよび振動波形データには正常／異常を分類できる境界線を引くことができない場合を考える。 For example, as shown in FIG. 25A, on the two-dimensional scatter diagram in the case where there are two feature quantities, a case where a boundary line that can classify normal / abnormal cannot be drawn in the learning data and the vibration waveform data. Think.
　その一方で、診断対象および運転条件によって有用な特徴量が異なる。したがって、診断対象および運転条件に基づいて適切な特徴量を選択する。適切な特徴量を含む多次元の特徴空間に各学習データおよび振動波形データを写像することによって、図２５（Ｂ）に示すように、正常／異常を分類できる分類境界面が生成できるようになる。 On the other hand, useful features differ depending on the diagnosis target and operating conditions. Therefore, an appropriate feature amount is selected based on the diagnosis target and the operating conditions. By mapping each learning data and vibration waveform data to a multidimensional feature space including appropriate feature amounts, a classification boundary surface that can classify normal / abnormal can be generated as shown in FIG. .
　各学習データおよび振動波形データに対しては、分類境界からの距離である異常度を算出することができる。分類境界上では異常度はゼロとなり、分類境界よりも正常側では異常度は負（－）の値となり、分類境界よりも異常側では異常度は正（＋）の値となる。 For each learning data and vibration waveform data, the degree of abnormality, which is the distance from the classification boundary, can be calculated. The degree of abnormality is zero on the classification boundary, the degree of abnormality is negative (−) on the normal side of the classification boundary, and the degree of abnormality is positive (+) on the abnormal side of the classification boundary.
　このような手法はＯＣ－ＳＶＭによる機械学習といわれ、多くの特徴量を１つの指標（異常度）に変換して評価することが可能となる。 Such a method is called machine learning by OC-SVM, and it is possible to evaluate by converting many feature values into one index (abnormality).
　図２２に戻って、学習部１４２は、学習データを用いて上述した分類境界を設定する。異常度演算部１４４は、特徴ベクトル０～９のそれぞれについて、特徴区間における分類境界からの距離である異常度０～９を演算する。 22, the learning unit 142 sets the above-described classification boundary using the learning data. The degree of abnormality calculation unit 144 calculates the degree of abnormality 0 to 9, which is the distance from the classification boundary in the feature section, for each of the feature vectors 0 to 9.
　異常度演算部１４４は、算出した異常度０～９を統計処理にすることによって評価値Ｅ０を演算する。この評価値Ｅ０の演算は、図１９、図２０および図２１に示される制御処理におけるステップＳ３２の処理に該当する。評価値Ｅ０は、１０秒間分の振動波形データの異常度０～９を特徴付ける値（代表値）となる。したがって、統計処理では、評価値Ｅ０として、異常度０～９の平均値を演算することができる。あるいは、評価値Ｅ０として、異常度０～９の中央値、最頻値、最小値などを演算することもできる。 The abnormality degree calculation unit 144 calculates the evaluation value E0 by performing statistical processing on the calculated abnormality degrees 0 to 9. The calculation of the evaluation value E0 corresponds to the process of step S32 in the control process shown in FIGS. The evaluation value E0 is a value (representative value) that characterizes the abnormalities 0 to 9 of vibration waveform data for 10 seconds. Therefore, in the statistical process, the average value of the degree of abnormality 0 to 9 can be calculated as the evaluation value E0. Alternatively, the median value, mode value, minimum value, etc. of the degree of abnormality 0 to 9 can be calculated as the evaluation value E0.
　または、図１９、図２０および図２１のステップＳ３２において、評価値Ｅ０として、学習データに基づいて設定された異常判別しきい値と各異常度とを比較して、異常率を演算することができる。異常率は、異常度０～９のうち異常度が予め定められた異常判別しきい値を超えた数を総セグメント数（１０個）で除算することによって求められる。 Alternatively, in step S32 of FIG. 19, FIG. 20, and FIG. 21, the abnormality rate may be calculated by comparing the abnormality determination threshold set based on the learning data with each abnormality degree as the evaluation value E0. it can. The abnormality rate is obtained by dividing the number of abnormality degrees 0 to 9 in which the abnormality degree exceeds a predetermined abnormality determination threshold by the total number of segments (10).
　このようにして、評価値演算部１４０は、所定の時間間隔で、一定時間内における軸受６０の振動波形データの評価値（異常度）を演算する。評価値演算部１４０は、演算した評価値を評価値トレンド記憶部１３４へ出力する。 In this way, the evaluation value calculation unit 140 calculates the evaluation value (abnormality) of the vibration waveform data of the bearing 60 within a predetermined time at predetermined time intervals. The evaluation value calculation unit 140 outputs the calculated evaluation value to the evaluation value trend storage unit 134.
　評価値トレンド記憶部１３４は、図１６で説明したように、評価値演算部１４０から時々刻々と与えられる評価値（異常度）を格納する。本実施の形態では、時間的に連続する所定数の異常度が、異常度の時間的変化の傾向を表す「評価値トレンド」に相当する。評価値トレンド記憶部１３４は、所定の時間間隔で、評価値トレンドを更新する。 The evaluation value trend storage unit 134 stores the evaluation value (abnormality) given from the evaluation value calculation unit 140 every moment as described with reference to FIG. In the present embodiment, a predetermined number of abnormalities that are temporally continuous correspond to an “evaluation value trend” that represents a tendency of temporal change in the abnormal degree. The evaluation value trend storage unit 134 updates the evaluation value trend at predetermined time intervals.
　図２２に戻って、計測トリガ発生部１８０は、評価値トレンド記憶部１３４から時間的に連続する所定数の異常度（評価値）を読み出すと、読み出した評価値トレンドに基づいて計測トリガを発生する。図１６で説明したように、計測トリガ発生部１８０は、評価値トレンドが変化したと判定されると、計測トリガを発生する。発生した計測トリガは振動波形データ出力部１７０に与えられる。 Returning to FIG. 22, when the measurement trigger generation unit 180 reads a predetermined number of abnormalities (evaluation values) that are temporally continuous from the evaluation value trend storage unit 134, the measurement trigger generation unit 180 generates a measurement trigger based on the read evaluation value trend. To do. As described with reference to FIG. 16, the measurement trigger generation unit 180 generates a measurement trigger when it is determined that the evaluation value trend has changed. The generated measurement trigger is given to the vibration waveform data output unit 170.
　振動波形データ出力部１７０は、図１７で説明したように、計測トリガ発生部１８０から計測トリガを受けると、振動波形データ記憶部１３２に格納されている、計測トリガが発生した時点の直前の一定時間内における軸受６０の振動波形データを読み出す。振動波形データ出力部１７０は、さらに、計測トリガが発生した時点以降における軸受６０の振動波形データを実効値演算部１２０から受ける。振動波形データ出力部１７０は、これらの振動波形データをひとまとめにして診断部１５０へ出力する。 As described with reference to FIG. 17, when the vibration waveform data output unit 170 receives the measurement trigger from the measurement trigger generation unit 180, the vibration waveform data output unit 170 is stored in the vibration waveform data storage unit 132 and is constant immediately before the measurement trigger is generated. The vibration waveform data of the bearing 60 within the time is read. The vibration waveform data output unit 170 further receives vibration waveform data of the bearing 60 from the effective value calculation unit 120 after the time when the measurement trigger is generated. The vibration waveform data output unit 170 collectively outputs these vibration waveform data to the diagnosis unit 150.
　診断部１５０は、ひとまとめにされた軸受６０の振動波形データに基づいて、軸受６０の異常を診断する。 The diagnosis unit 150 diagnoses an abnormality in the bearing 60 based on the vibration waveform data of the bearing 60 that has been collected.
　以上のように、実施の形態８に係る状態監視システムによれば、一定時間内における振動波形データを特徴付ける評価値として、該振動波形データから抽出される複数の特徴量から生成された１つの指標（異常度）を用いることにより、複数の特徴量が個々に変化している状態であっても、普段と違う組合せで変化が発生したときには、その変化を捉えることができる。これによれば、どのような変化を計測トリガとするかを明確に定義できない状態においても、振動波形データを記録しておくことができる。 As described above, according to the state monitoring system according to the eighth embodiment, one index generated from a plurality of feature values extracted from the vibration waveform data is used as an evaluation value characterizing the vibration waveform data within a predetermined time. By using (abnormality), even when a plurality of feature quantities are individually changing, when changes occur in a different combination, the changes can be captured. According to this, it is possible to record vibration waveform data even in a state where it is not possible to clearly define what kind of change is used as a measurement trigger.
　また、正常時の振動波形データがばらつきを有している場合であっても、ＯＣ－ＳＶＭによる機械学習では全て正常状態として認識されるため、計測トリガが誤って発生することを防ぐことができる。そして、異常度の時間的変化の傾向が正常時とは異なるときに計測トリガが発生されるため、膨大なデータが蓄積されることなるとともに、異常が発生したときの振動波形データを確実かつ効率的に計測することができるため、正確な異常診断を実現することができる。 Further, even when the vibration waveform data at the normal time has variations, all of the machine learning by the OC-SVM is recognized as a normal state, so that a measurement trigger can be prevented from being erroneously generated. . And, since the measurement trigger is generated when the trend of temporal change in the degree of abnormality is different from the normal time, a huge amount of data is accumulated and the vibration waveform data when the abnormality occurs is reliably and efficiently Therefore, accurate abnormality diagnosis can be realized.
　なお、上記の実施の形態５～８においては、一定時間内における振動波形データを特徴付ける評価値を１つとし、この１つの評価値の時間的変化の傾向が変化したことをトリガとして振動波形データの計測を開始する構成について説明したが、複数の評価値の時間的変化の傾向が変化したことをトリガとする構成としてもよい。 In the above fifth to eighth embodiments, one evaluation value characterizing the vibration waveform data within a predetermined time is set as one, and the change in the temporal change tendency of this one evaluation value is changed as a trigger. Although the configuration for starting the measurement has been described, a configuration in which the tendency of the temporal change of the plurality of evaluation values is changed may be used as a trigger.
　また、上記の実施の形態５～８において、データ処理装置８０は、この発明における「処理装置」の一実施例に対応し、記憶部１３０、評価値演算部１４０および診断部１５０は、この発明における「記憶部」、「評価値演算部」および「診断部」の一実施例に対応する。 In the fifth to eighth embodiments, the data processing device 80 corresponds to an example of the “processing device” in the present invention, and the storage unit 130, the evaluation value calculation unit 140, and the diagnosis unit 150 are configured according to the present invention. Corresponds to an example of “storage unit”, “evaluation value calculation unit”, and “diagnosis unit”.
　今回開示された実施の形態は、すべての点で例示であって制限的なものではないと考えられるべきである。本発明の範囲は、上記した実施の形態の説明ではなくて請求の範囲によって示され、請求の範囲と均等の意味および範囲内でのすべての変更が含まれることが意図される。 The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is shown not by the above description of the embodiments but by the scope of claims, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.
　１０　風力発電装置、２０　主軸、３０　ブレード、４０　増速機、５０　発電機、６０　軸受、７０　振動センサ、８０　データ処理装置、９０　ナセル、１００　タワー、１１０　ＬＰＦ、１１２　ＢＰＦ、１２０　実効値演算部、１３０　記憶部、１３２　振動波形データ記憶部、１３４　評価値トレンド記憶部、１３６　正常データ記憶部、１４０　評価値演算部、１４２　学習部、１４４　異常度演算部、１５０　診断部、１６０　閾値設定部、１６２　移動平均演算部、１６４　標準偏差演算部、１６６　閾値演算部、１６８　閾値記憶部、１７０　振動波形データ出力部、１８０　計測トリガ発生部。 10 wind power generators, 20 spindles, 30 blades, 40 speed increasers, 50 generators, 60 bearings, 70 vibration sensors, 80 data processing devices, 90 nacelles, 100 towers, 110 LPFs, 112 BPFs, 120 RMS values, 130 storage unit, 132 vibration waveform data storage unit, 134 evaluation value trend storage unit, 136 normal data storage unit, 140 evaluation value calculation unit, 142 learning unit, 144 abnormality degree calculation unit, 150 diagnosis unit, 160 threshold setting unit, 162 Moving average calculation unit, 164 standard deviation calculation unit, 166 threshold calculation unit, 168 threshold storage unit, 170 vibration waveform data output unit, 180 measurement trigger generation unit.

Claims (15)

  1. 　装置を構成する機械要素の状態を監視する状態監視システムであって、
    　前記機械要素の振動波形を計測するための振動センサと、
    　前記機械要素の異常を診断するための処理装置とを備え、
    　前記処理装置は、
    　一定時間内に前記振動センサから出力される振動波形データの実効値を特徴付ける評価値を、時間的に連続して演算する評価値演算部と、
    　前記評価値の時間的変化の推移に基づいて前記機械要素の異常を診断する診断部とを含み、
    　前記評価値演算部は、前記評価値として、前記一定時間内における前記振動波形データの実効値の最低値を演算する、状態監視システム。     A state monitoring system for monitoring the state of machine elements constituting the apparatus,
    A vibration sensor for measuring a vibration waveform of the machine element;
    A processing device for diagnosing an abnormality of the machine element,
    The processor is
    An evaluation value calculating unit that continuously calculates an evaluation value that characterizes an effective value of vibration waveform data output from the vibration sensor within a certain period of time; and
    A diagnostic unit for diagnosing an abnormality of the machine element based on a transition of a temporal change of the evaluation value,
    The said evaluation value calculating part is a state monitoring system which calculates the minimum value of the effective value of the said vibration waveform data in the said fixed time as the said evaluation value.
  2. [規則91に基づく訂正 22.01.2018]　
    　前記診断部は、前記評価値が閾値を超えたときに、前記機械要素の異常と診断するように構成され、
    　前記処理装置は、前記閾値を設定する設定部をさらに含み、
    　前記設定部は、前記閾値を、前記機械要素が正常であるときの前記最低値の時間的変化の推移よりも大きく、かつ、前記機械要素が異常であるときの前記最低値の時間的変化の推移よりも小さい値に設定する、請求項１に記載の状態監視システム。     [Correction based on Rule 91 22.01.2018]
    The diagnosis unit is configured to diagnose an abnormality of the machine element when the evaluation value exceeds a threshold value,
    The processing apparatus further includes a setting unit for setting the threshold value,
    The setting unit sets the threshold value to be larger than a transition of a temporal change of the minimum value when the mechanical element is normal and the temporal change of the minimum value when the mechanical element is abnormal. The state monitoring system according to claim 1, wherein the state monitoring system is set to a value smaller than the transition.
  3. 　前記診断部は、前記評価値の時間的変化率が閾値を超えたときに、前記機械要素の異常と診断するように構成され、
    　前記設定部は、前記閾値を、前記機械要素が正常であるときの前記最低値の時間的変化率よりも大きく、かつ、前記機械要素が異常であるときの前記最低値の時間的変化率よりも小さい値に設定する、請求項２に記載の状態監視システム。     The diagnostic unit is configured to diagnose an abnormality of the machine element when a temporal change rate of the evaluation value exceeds a threshold value,
    The setting unit is configured such that the threshold value is larger than a temporal change rate of the minimum value when the mechanical element is normal, and more than a temporal change rate of the minimum value when the mechanical element is abnormal. The state monitoring system according to claim 2, wherein is set to a small value.
  4. 　前記診断部は、前記評価値が第１閾値を超え、かつ、前記評価値の時間的変化率が第２閾値を超えたときに、前記機械要素の異常と診断するように構成され、
    　前記設定部は、前記第１閾値を、前記機械要素が正常であるときの前記最低値の時間的推移よりも小さく、かつ、前記機械要素が異常であるときの前記最低値の時間的推移よりも大きい値に設定し、
    　前記設定部は、さらに、前記第２閾値を、前記機械要素が正常であるときの前記最低値の時間的変化率よりも大きく、かつ、前記機械要素が異常であるときの前記最低値の時間的変化率よりも小さい値に設定する、請求項２に記載の状態監視システム。     The diagnostic unit is configured to diagnose an abnormality of the machine element when the evaluation value exceeds a first threshold value and a temporal change rate of the evaluation value exceeds a second threshold value,
    The setting unit is configured such that the first threshold value is smaller than the temporal transition of the minimum value when the mechanical element is normal and the temporal transition of the minimum value when the mechanical element is abnormal. Is set to a large value,
    The setting unit further sets the second threshold value to be larger than a temporal change rate of the minimum value when the machine element is normal and the time of the minimum value when the machine element is abnormal. The state monitoring system according to claim 2, wherein the state monitoring system is set to a value smaller than the dynamic change rate.
  5. 　装置を構成する機械要素の状態を監視する状態監視システムであって、
    　前記機械要素の振動波形を計測するための振動センサと、
    　前記機械要素の異常を診断するための処理装置とを備え、
    　前記処理装置は、
    　前記振動センサから出力される振動波形データの実効値と閾値とを比較することによって、前記機械要素の異常を診断する診断部と、
    　前記閾値を設定する設定部とを含み、
    　前記設定部は、
    　前記振動センサから出力されるｎ個（ｎは２以上の整数）の前記振動波形データの実効値の移動平均値を演算する第１演算部と、
    　前記ｎ個の振動波形データの実効値の標準偏差を演算する第２演算部と、
    　前記第１演算部により演算された前記移動平均値および前記第２演算部により演算された前記標準偏差に基づいて、前記閾値を演算する第３演算部とを含む、状態監視システム。     A state monitoring system for monitoring the state of machine elements constituting the apparatus,
    A vibration sensor for measuring a vibration waveform of the machine element;
    A processing device for diagnosing an abnormality of the machine element,
    The processor is
    A diagnostic unit for diagnosing an abnormality of the machine element by comparing the effective value of the vibration waveform data output from the vibration sensor with a threshold value;
    A setting unit for setting the threshold,
    The setting unit
    A first calculation unit that calculates a moving average value of effective values of n pieces of vibration waveform data (n is an integer of 2 or more) output from the vibration sensor;
    A second calculator that calculates a standard deviation of effective values of the n pieces of vibration waveform data;
    A state monitoring system comprising: a third calculation unit that calculates the threshold value based on the moving average value calculated by the first calculation unit and the standard deviation calculated by the second calculation unit.
  6. 　前記第３演算部は、前記移動平均値に対して、前記標準偏差に予め定められた係数を乗算した値を加算することにより、前記閾値を演算する、請求項５に記載の状態監視システム。 The state monitoring system according to claim 5, wherein the third calculation unit calculates the threshold value by adding a value obtained by multiplying the standard deviation by a predetermined coefficient to the moving average value.
  7. 　前記設定部は、前記第３演算部により演算された前記閾値を保存する記憶部をさらに含み、
    　前記診断部は、
    　前記記憶部から、前記振動センサから出力される前記振動波形データの実効値と運転条件が同じである過去の前記振動波形データの実効値に基づいて演算された前記閾値を読み出し、
    　前記記憶部から読み出した前記閾値と、前記振動センサから出力される前記振動波形データの実効値とを比較することにより、前記機械要素の異常を診断する、請求項５または６に記載の状態監視システム。     The setting unit further includes a storage unit that stores the threshold value calculated by the third calculation unit,
    The diagnostic unit
    From the storage unit, the threshold value calculated based on the effective value of the past vibration waveform data that has the same operating conditions as the effective value of the vibration waveform data output from the vibration sensor is read,
    The state monitoring according to claim 5 or 6, wherein an abnormality of the mechanical element is diagnosed by comparing the threshold value read from the storage unit with an effective value of the vibration waveform data output from the vibration sensor. system.
  8. 　装置を構成する機械要素の状態を監視する状態監視システムであって、
    　前記機械要素の振動波形を計測するための振動センサと、
    　前記機械要素の異常を診断するための処理装置とを備え、
    　前記処理装置は、
    　一定時間内に前記振動センサから出力される振動波形データを特徴付ける評価値を、時間的に連続して演算するように構成された評価値演算部と、
    　前記評価値演算部により演算される前記評価値の時間的変化の傾向が変化したことをトリガとして前記振動波形データの計測を開始することにより、前記振動波形データを用いて前記機械要素の異常を診断するように構成された診断部とを含む、状態監視システム。     A state monitoring system for monitoring the state of machine elements constituting the apparatus,
    A vibration sensor for measuring a vibration waveform of the machine element;
    A processing device for diagnosing an abnormality of the machine element,
    The processor is
    An evaluation value characterizing the vibration waveform data output from the vibration sensor within a predetermined time, an evaluation value calculation unit configured to continuously calculate in time,
    By starting measurement of the vibration waveform data triggered by a change in the tendency of temporal change in the evaluation value calculated by the evaluation value calculation unit, the abnormality of the mechanical element is detected using the vibration waveform data. A condition monitoring system, comprising: a diagnosis unit configured to diagnose.
  9. 　前記処理装置は、前記一定時間内における前記振動波形データを格納するための記憶部をさらに含み、
    　前記診断部は、前記評価値の時間的変化の傾向が変化した時点の直前の前記一定時間内における前記振動波形データを、前記記憶部から取得する、請求項８に記載の状態監視システム。     The processing device further includes a storage unit for storing the vibration waveform data within the predetermined time,
    The state monitoring system according to claim 8, wherein the diagnosis unit acquires the vibration waveform data within the predetermined time immediately before the time point when the tendency of the evaluation value changes with time from the storage unit.
  10. 　前記診断部は、前記評価値の時間的変化率が閾値以上となったことを検出して、前記振動波形データの計測を開始する、請求項８または９に記載の状態監視システム。 The state monitoring system according to claim 8 or 9, wherein the diagnosis unit detects that the temporal change rate of the evaluation value is equal to or greater than a threshold and starts measurement of the vibration waveform data.
  11. 　前記診断部は、前記診断部は、前記評価値の時間的変化率が第１の閾値以上となり、かつ、前記評価値の大きさが第２の閾値以上となったことを検出して、前記振動波形データの計測を開始する、請求項８または９に記載の状態監視システム。 The diagnostic unit detects that the temporal change rate of the evaluation value is equal to or greater than a first threshold and the magnitude of the evaluation value is equal to or greater than a second threshold; The state monitoring system according to claim 8 or 9, wherein measurement of vibration waveform data is started.
  12. 　前記評価値演算部は、前記一定時間内における前記振動波形データを統計処理することにより、前記評価値を演算する、請求項８～１１のいずれか１項に記載の状態監視システム。 The state monitoring system according to any one of claims 8 to 11, wherein the evaluation value calculation unit calculates the evaluation value by statistically processing the vibration waveform data within the predetermined time.
  13. 　前記評価値演算部は、
    　前記一定時間内における前記振動波形データを複数のセグメントデータに分割し、各セグメントデータに対して複数の特徴量を含む特徴量ベクトルを生成し、
    　前記装置が正常であるときの前記振動波形データに対して生成された前記特徴量ベクトルを用いて、正常と異常とを分類する分類境界を設定し、
    　前記一定時間内における前記振動波形データに対して生成された複数の前記特徴量ベクトルの各々について、前記分類境界からの距離である異常度を算出し、
    　複数の前記異常度を統計処理することにより、前記評価値を生成する、請求項８～１１のいずれか１項に記載の状態監視システム。     The evaluation value calculator is
    Dividing the vibration waveform data within the predetermined time into a plurality of segment data, and generating a feature quantity vector including a plurality of feature quantities for each segment data;
    Using the feature vector generated for the vibration waveform data when the device is normal, setting a classification boundary for classifying normal and abnormal,
    For each of the plurality of feature vectors generated with respect to the vibration waveform data within the predetermined time, an abnormality degree that is a distance from the classification boundary is calculated,
    The state monitoring system according to any one of claims 8 to 11, wherein the evaluation value is generated by statistically processing a plurality of the abnormalities.
  14. 　前記記憶部は、所定の時間間隔で、前記振動センサから与えられる前記振動波形データを格納するとともに、格納されている前記一定時間内における前記振動波形データのうち最も古い前記振動波形データを消去する、請求項９に記載の状態監視システム。 The storage unit stores the vibration waveform data provided from the vibration sensor at a predetermined time interval, and erases the oldest vibration waveform data among the stored vibration waveform data within the predetermined time. The state monitoring system according to claim 9.
  15. 　請求項１～１４のいずれか１項に記載の状態監視システムを備える、風力発電装置。 A wind turbine generator comprising the state monitoring system according to any one of claims 1 to 14.
PCT/JP2017/010659 2016-03-17 2017-03-16 Condition monitoring system and wind power generation device WO2017159784A1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201780018017.1A CN108780025B (en) 2016-03-17 2017-03-16 State monitoring system and wind power generation device
US16/085,878 US11460005B2 (en) 2016-03-17 2017-03-16 Condition monitoring system and wind turbine generation apparatus
EP17766780.5A EP3431952B1 (en) 2016-03-17 2017-03-16 Condition monitoring system and wind turbine generation apparatus

Applications Claiming Priority (10)

Application Number Priority Date Filing Date Title
JP2016-053691 2016-03-17
JP2016-053679 2016-03-17
JP2016053691 2016-03-17
JP2016053679A JP6639288B2 (en) 2016-03-17 2016-03-17 Condition monitoring system and wind power generator
JP2016058250 2016-03-23
JP2016-058250 2016-03-23
JP2017-049838 2017-03-15
JP2017049838A JP6824076B2 (en) 2016-03-23 2017-03-15 Condition monitoring system and wind power generator
JP2017049833A JP6820771B2 (en) 2016-03-17 2017-03-15 Condition monitoring system and wind power generator
JP2017-049833 2017-03-15

Publications (2)

Publication Number Publication Date
WO2017159784A1 WO2017159784A1 (en) 2017-09-21
WO2017159784A9 true WO2017159784A9 (en) 2018-04-12

Family

ID=59851711

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2017/010659 WO2017159784A1 (en) 2016-03-17 2017-03-16 Condition monitoring system and wind power generation device

Country Status (1)

Country Link
WO (1) WO2017159784A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111456914A (en) * 2020-03-23 2020-07-28 上海电气风电集团股份有限公司 Monitoring system and method for mechanical parts inside wind turbine cabin

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107705149A (en) * 2017-09-22 2018-02-16 平安科技（深圳）有限公司 Data method for real-time monitoring, device, terminal device and storage medium
CN109347952A (en) * 2018-10-17 2019-02-15 深圳众宝城贸易有限公司 Rotary equipment bearings abnormal vibration intelligent prompt system
CN109406096B (en) * 2018-11-21 2020-01-14 大连理工大学 Floating type offshore wind turbine generator measuring device and method thereof
CN109599015B (en) * 2018-11-21 2020-04-14 大连理工大学 Hybrid model experimental device and method for floating offshore wind turbine generator system
CN110697075B (en) * 2019-09-29 2022-11-25 中国直升机设计研究所 Helicopter HUMS vibration threshold value generation method
WO2021117752A1 (en) * 2019-12-11 2021-06-17 Ntn株式会社 Rolling bearing state monitoring method and rolling bearing state monitoring device
CN112525334B (en) * 2020-11-18 2023-06-02 西安因联信息科技有限公司 Dynamic equipment vibration multistable detection method
CN113777488B (en) * 2021-09-14 2023-12-12 中国南方电网有限责任公司超高压输电公司昆明局 State evaluation method and device for valve cooling main pump motor and computer equipment
CN113688791B (en) * 2021-09-22 2024-03-01 西安热工研究院有限公司 Method for identifying CMS abnormal data packet of wind turbine generator
CN116624343B (en) * 2023-06-14 2023-10-13 华北电力大学 Wind turbine generator tower abnormal vibration monitoring and health degree evaluation method and system

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08110262A (en) * 1994-10-12 1996-04-30 Toshiba Corp On-line rotary object diagnostic device
US6370957B1 (en) * 1999-12-31 2002-04-16 Square D Company Vibration analysis for predictive maintenance of rotating machines
JP2002022617A (en) * 2000-07-05 2002-01-23 Mitsubishi Electric Corp Apparatus for diagnosing bearing
JP2003050157A (en) * 2001-08-07 2003-02-21 Mitsubishi Electric Corp Bearing diagnostic apparatus
JP5308852B2 (en) * 2009-02-03 2013-10-09 オークマ株式会社 Method and device for determining lubrication state of rolling bearing
JP5725833B2 (en) * 2010-01-04 2015-05-27 Ntn株式会社 Rolling bearing abnormality diagnosis device, wind power generation device and abnormality diagnosis system
JP2017026421A (en) * 2015-07-21 2017-02-02 日本精工株式会社 Bearing abnormality diagnosis device

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111456914A (en) * 2020-03-23 2020-07-28 上海电气风电集团股份有限公司 Monitoring system and method for mechanical parts inside wind turbine cabin

Also Published As

Publication number Publication date
WO2017159784A1 (en) 2017-09-21

Similar Documents

Publication Publication Date Title
WO2017159784A9 (en) Condition monitoring system and wind power generation device
EP3431952B1 (en) Condition monitoring system and wind turbine generation apparatus
JP6820771B2 (en) Condition monitoring system and wind power generator
JP6885833B2 (en) Condition monitoring system and data processing equipment
WO2018142986A1 (en) State monitoring system and wind power generating device
US20150322924A1 (en) Method of monitoring the condition of a wind turbine
JP6728808B2 (en) Measuring and diagnosing device and measuring and diagnosing method
US9791856B2 (en) Fault frequency set detection system and method
JP6835265B2 (en) Measurement and diagnostic equipment and measurement and diagnosis method
EP3788328B1 (en) System and process for pattern matching bearing vibration diagnostics
US11047768B2 (en) Abnormality diagnosis device and abnormality diagnosis method
JP6824076B2 (en) Condition monitoring system and wind power generator
JP2018120407A (en) State monitoring method and state monitoring apparatus
JP7098399B2 (en) Status monitoring device and status monitoring method
DK181393B1 (en) Establishing health indicator of a rotating component
JP6639288B2 (en) Condition monitoring system and wind power generator
JP6639265B2 (en) Abnormality diagnosis device and abnormality diagnosis method
JP7408519B2 (en) Condition monitoring device and condition monitoring method
JP2018120406A (en) State monitoring method and state monitoring apparatus
WO2024043051A1 (en) Monitoring device and monitoring method
JP6639266B2 (en) Abnormality diagnosis device and abnormality diagnosis method
WO2019044575A1 (en) State-monitoring device and state-monitoring method
JP6808405B2 (en) Monitoring device for rotating equipment
JP6736987B2 (en) Condition monitoring device for rotating parts of wind power generator
CN115143049A (en) Transmission chain state identification method and device of wind generating set

Legal Events

Date Code Title Description
NENP Non-entry into the national phase in:

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2017766780

Country of ref document: EP

ENP Entry into the national phase in:

Ref document number: 2017766780

Country of ref document: EP

Effective date: 20181017

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17766780

Country of ref document: EP

Kind code of ref document: A1