WO2011092830A1 - 作業機械の監視診断装置 - Google Patents
作業機械の監視診断装置 Download PDFInfo
- Publication number
- WO2011092830A1 WO2011092830A1 PCT/JP2010/051172 JP2010051172W WO2011092830A1 WO 2011092830 A1 WO2011092830 A1 WO 2011092830A1 JP 2010051172 W JP2010051172 W JP 2010051172W WO 2011092830 A1 WO2011092830 A1 WO 2011092830A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- data
- frequency
- classification
- operation data
- Prior art date
Links
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02F—DREDGING; SOIL-SHIFTING
- E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
- E02F9/20—Drives; Control devices
- E02F9/2025—Particular purposes of control systems not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66C—CRANES; LOAD-ENGAGING ELEMENTS OR DEVICES FOR CRANES, CAPSTANS, WINCHES, OR TACKLES
- B66C13/00—Other constructional features or details
- B66C13/16—Applications of indicating, registering, or weighing devices
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02F—DREDGING; SOIL-SHIFTING
- E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
- E02F9/26—Indicating devices
- E02F9/264—Sensors and their calibration for indicating the position of the work tool
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02F—DREDGING; SOIL-SHIFTING
- E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
- E02F9/26—Indicating devices
- E02F9/267—Diagnosing or detecting failure of vehicles
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0275—Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
- G05B23/0278—Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
Definitions
- the present invention relates to a monitoring and diagnosing device for a working machine that monitors and diagnoses the operating state of a working machine represented by a construction machine such as a hydraulic excavator.
- the inspection and maintenance work can be an obstacle to the operation as long as the equipment state is good.
- an abnormality diagnosis technique that measures the state of the machine using various sensors and monitors whether there is an abnormality. Emphasis is placed on preventive maintenance to prevent equipment failure by detecting an abnormality before failure stop by abnormality diagnosis technology and taking early maintenance measures.
- Patent Document 1 and Patent Document 2 describe an invention for detecting an abnormality of a device using a statistical property or similarity of an input signal indicating an operation state of the device.
- Patent Document 3 describes an invention in which processing is performed interactively with a user in order to make cluster classification appropriate.
- Patent Document 4 describes an invention that eliminates erroneous determination by detecting a sensor abnormality.
- all of the above prior arts use statistical distances such as Mahalanobis-Taguchi method for classification of input data used for abnormality determination.
- the distance is equal or less than the reference value, it is determined that there is no abnormality.
- the statistical distance is the same even if abnormal. Or it may be below the reference value and may be erroneously determined to be normal.
- the present invention has been made in view of the above problems, and its purpose is to prevent misjudgment and properly diagnose even when the input signals at normal operation and abnormal operation are very similar. It is providing the monitoring diagnostic apparatus of the working machine which can perform.
- the present invention inputs work data of a work machine detected by a plurality of sensors in time series, and monitors the work machine for performing an abnormality diagnosis of the work machine using the work data.
- the classification information storage unit that stores the reference classification information
- the frequency information storage unit that stores the reference frequency information
- the reference classification information is read from the classification information storage unit, and is detected by the plurality of sensors.
- the operation data input in series is classified by comparing with the reference classification information, a first data classification unit that generates operation data classification information, and the operation data classification information is aggregated, for each classification of the operation data
- the operation data frequency information to which the appearance frequency information is added is generated, the reference frequency information is read from the frequency information storage unit, and the operation data frequency information is read out.
- a frequency comparison unit that generates operation data frequency comparison information that compares the reference frequency information
- an abnormality diagnosis unit that performs an abnormality diagnosis of the work machine using the operation data classification information and the operation data frequency comparison information.
- the monitoring and diagnosis apparatus further includes a display unit that displays at least one of the operation data frequency comparison information generated by the frequency comparison unit and the diagnosis result data of the abnormality diagnosis unit.
- the user can detect an abnormality or confirm it according to the judgment of the user. Further, when the diagnosis result data is displayed, detailed information on the abnormality can be obtained.
- the abnormality diagnosis unit detects a predetermined difference between the operation data frequency information and the reference frequency information as a result of performing an abnormality diagnosis of the work machine using the operation data frequency comparison information. In this case, it is diagnosed that the operation data is abnormal, and the display unit displays the diagnosis result. Thereby, the user can know the detailed information of the abnormality.
- the display unit displays the operation data classification information related to the difference.
- the first data classification unit extracts only reference classification information selected in advance from the reference classification information stored in the classification information storage unit and is detected by the plurality of sensors.
- the operational data input in series only the operational data corresponding to the preselected reference classification information is extracted and compared with the preselected reference classification information to generate the operational data classification information. .
- the frequency comparison unit can obtain accurate operating data frequency comparison information that is not affected by the no-operation time, and perform an appropriate diagnosis with fewer erroneous determinations. Can do.
- the monitoring / diagnosis device inputs operation data of the work machine detected by the plurality of sensors in a time series, compares and classifies the similarity of the operation data, and stores it in the classification information storage unit.
- a classification information generation unit that generates reference classification information to be stored is further provided.
- the monitoring / diagnosis device classifies the operation data detected by the plurality of sensors and input in time series in comparison with the reference classification information generated by the classification information generation unit, A second data classification unit that generates information, and the operation data classification information is aggregated, information on the appearance frequency for each classification of the operation data is added, and reference frequency information stored in the frequency information storage unit is generated And a frequency information generation unit that performs the operation.
- adaptive learning is performed with respect to the operating state of a machine that behaves in various ways, and erroneous determination is prevented even when the input signal between normal operation and abnormal operation is strong.
- the diagnosis can be performed appropriately.
- FIG. 1 It is a figure which shows the structure of the monitoring diagnostic apparatus concerning the 1st Example of this invention. It is a figure which shows the structure of the operation data input into a monitoring diagnostic apparatus. It is a figure which shows the structure of the classification data (reference classification information) read from a classification information storage part. It is a figure which shows the data structure of the nearest neighbor classification number (operation data classification information) produced by the data classification part. It is a figure which shows the data structure of the normalization statistical distance d (operation data classification information) produced by the data classification part. It is a figure which shows the frequency table produced by the frequency comparison part. It is a figure which shows the time width data and reference frequency table which are read from a frequency information storage part.
- FIG. It is a figure showing the temperature sensor value (operation data) in different periods for the exhaust temperature of each cylinder of the hydraulic excavator engine measured by the temperature sensor and recorded and monitored by the vehicle body controller.
- FIG. It is a figure showing the temperature sensor value (operation data) in different periods for the exhaust temperature of each cylinder of the hydraulic excavator engine measured by the temperature sensor and recorded and monitored by the body controller.
- FIG. It is a figure which compares and shows the frequency of an operation pattern (classification data of operation data) about the period at the time of normal operation and abnormal operation, and is a figure showing the example of a display of frequency comparison data. It is a figure which shows the operation
- FIG. 21 is a diagram showing an example of an output screen displayed when it is determined that there is an abnormality in the frequency ratio compared with the reference frequency ratio data among the frequency comparison data as shown in FIG. It is.
- FIG. 26 is a diagram showing a detailed information display screen that appears when the upper reference link designation shown in FIG. 25 is operated. It is a figure which shows the processing flow of the part which displays the diagnostic result data of the abnormality diagnosis part 103 among the processing functions of the monitoring diagnostic apparatus shown in FIG.
- FIG. 2 is a diagram illustrating a configuration of a frequency information generation device 30.
- FIG. It is a figure which shows the structural example of a monitoring diagnostic apparatus at the time of including the frequency information generation part in the monitoring diagnostic apparatus shown in FIG. 1, and giving the function of a frequency information generation apparatus to a monitoring diagnostic apparatus.
- FIG. 1 is a diagram showing the configuration of a monitoring / diagnosis apparatus according to the first embodiment of the present invention.
- the monitoring / diagnosis apparatus 1 includes a data classification unit 101 (first data classification unit), a classification information storage unit 102, an abnormality determination unit 103, a frequency comparison unit 104, and a frequency information storage unit 105.
- the work machine is provided with a plurality of sensors for detecting the operation state of the work machine, and the detection values (sensor values) of these sensors are digitized and input to the monitoring and diagnosis apparatus 1 as operation data.
- FIG. 2 is a diagram showing a configuration of operation data input to the monitoring / diagnosis apparatus 1.
- information on each sensor value is associated with time information as data items A to C, and sensor values for each data item are associated with time information as time series data.
- the operation data from time 1 to n is described for three types of data items A to C.
- the operation data is divided into two types according to use.
- One is diagnostic data
- the other is learning data.
- It is diagnostic data that is input to the monitoring diagnostic apparatus 1 of the present embodiment, and diagnostic result data is obtained as a result of diagnosing the input diagnostic data.
- the learning data will be described later.
- FIG. 3 is a diagram illustrating a configuration of classification data (reference classification information). As shown in FIG. 3, in the classification data, a data value for each data item and radius data are associated with each classification. This classification data (reference classification information) is created in advance based on operation data as learning data (described later).
- the data classifying unit 101 treats a set of sensor values at each time, for example, at time 1, a group of sensor values A1, B1 and C1 as a single vector among the diagnostic data, and classifies the data.
- a group of data values a1, b1, and c1 is treated as one vector
- a sensor value vector of diagnostic data Compare vectors of classification data values.
- the statistical distance D between the vectors is calculated by a calculation method as shown in Expression 3.
- the vector X shown in Equation 1 has components from x1 to xp
- the vector Y shown in Equation 2 has components from y1 to yp
- Equation 3 calculates the Euclidean distance D between these vectors.
- the data classification unit 101 calculates the statistical distance between the sensor value vector of the diagnostic data at a certain time and each of the data value vectors of all the classification data according to Equation 3, and the classification number that minimizes the statistical distance D This is output to the frequency comparison unit 104 as the nearest neighbor classification number (operation data classification information).
- the nearest neighbor classification number (operation data classification information) output to the frequency comparison unit 104 is associated with time information as time series data, as shown in FIG. 4A.
- the data classification unit 101 uses the statistical distance D (hereinafter referred to as the nearest neighbor distance) between the data value vector of the classification data corresponding to the nearest classification number and the sensor value vector of the diagnostic data. Is calculated by dividing the radius data r of the classification data corresponding to the nearest classification number, and outputs it to the abnormality diagnosis unit 103.
- the normalized statistical distance d (operating data classification information) output to the abnormality diagnosis unit 103 is associated with time information as time series data as shown in FIG. 4B.
- the data classification unit 101 calculates the nearest neighbor classification number and the normalized statistical distance d as the operation data classification information.
- the former is output to the frequency comparison unit 104, and the latter is output to the abnormality diagnosis unit 103.
- the data classification unit 101 extracts only the classification data previously selected by the user from the classification data (reference classification information) stored in the classification information storage unit 102, and also inputs the input diagnostic data (operation Data), only the diagnostic data corresponding to the preselected classification data is extracted, and compared with the preselected classification data, the above-mentioned operation data classification information (nearest neighbor classification number and normalized statistical distance) May be generated.
- the frequency comparison unit 104 aggregates the nearest neighbor classification numbers input from the data classification unit 101 over a predetermined time width.
- the predetermined time width is read from the frequency information storage unit 105 as time width data 601 as shown in FIG.
- the nearest neighbor classification number input from the data classification unit 101 is data from time 1 to time n as shown in FIG.
- the classification numbers k1 to kn shown in FIG. 4 correspond to the times 1 to n, respectively, and are any of the classification numbers 1 to m of the data classification shown in FIG.
- the frequency comparison unit 104 calculates the appearance frequency (number of appearances of each classification number) by counting which of the classification numbers k1 to kn is from classification 1 to m, and a frequency table 501 as shown in FIG.
- the frequencies h1 to hn are tabulated corresponding to the classifications 1 to m, and based on this and the time width data 601 shown in FIG. 6, frequency ratios e1 to em (operation data frequency information) are obtained. calculate. That is, as shown in Equation 5, the frequency ratio is calculated by dividing the frequency for each classification by the time width T. As a result, a comparison independent of the time width T is possible.
- the frequency comparison unit 104 further includes a frequency ratio (operation data frequency information) of the frequency table 501 and a frequency ratio (reference frequency information) of the reference frequency table 602 as shown on the right side of FIG. Are compared to create frequency comparison data (operation data frequency comparison information).
- the reference frequency table 602 shown in FIG. 6 the reference frequency ratios are tabulated from E1 to Em corresponding to the classifications 1 to m.
- the frequency ratio (reference frequency information) in the reference frequency table 602 is created in advance based on operation data as learning data (described later).
- the absolute value of the difference as in Expression 6 may be used, or the determination is performed using the frequency ratio test ratio as in Expression 7. Also good.
- the difference Diff in Expression 6 or the test ratio Rate in Expression 7 is frequency comparison data generated by the frequency comparison unit 104. Further, when the frequency comparison data is used only for displaying on the display device, the frequency comparison data may display the operation data frequency information and the reference frequency information in a graph (see FIG. 21).
- the abnormality diagnosis unit 103 uses the normalized statistical distance output from the data classification unit 101 and the frequency comparison data output from the frequency comparison unit 104 to perform abnormality diagnosis on the operation data. This diagnosis is performed as follows.
- the abnormality diagnosis unit 103 diagnoses that the diagnostic data is in the normal range if the normalized statistical distance output from the data classification unit 101 is 1 or less, and if the normalized statistical distance is greater than 1, the diagnostic data Is diagnosed as not in the normal range, ie, abnormal.
- the reason why 1 is a reference is that normalization processing is performed regardless of the classification number by dividing by the radius data of each nearest neighbor classification number according to Equation 4. This diagnosis is performed on the diagnosis data at each time input to the data classification unit 101.
- the abnormality diagnosing unit 103 aggregates the diagnosis results at each time and is diagnosed as abnormal continuously at a predetermined time, or is diagnosed as abnormal at a predetermined rate or more within a predetermined time.
- the abnormality diagnosis unit 103 sums up the diagnostic information for a predetermined time and diagnoses it as an abnormality, it is used as the output of the monitoring diagnosis apparatus 1 as diagnosis result data using the statistical distance.
- the abnormality diagnosis unit 103 sums up the diagnosis information for a predetermined time and diagnoses it as normal, the frequency comparison data from the frequency comparison unit 104 is received, and the frequency comparison data (here, the frequency comparison data is expressed by Equation 7). It is diagnosed whether a classification number larger or smaller than a predetermined ratio exists.
- the frequency comparison unit 104 if the frequency ratio of the classification of diagnostic data and the frequency ratio of the reference frequency read from the frequency information storage unit 105 are about the same, the test ratio of the corresponding classification should be close to 1. . When the value is larger than 1, for example, 1.5 or 2.0, it can be understood that the frequency ratio of the diagnostic data is high for the frequency ratio of the corresponding classification.
- the frequency ratio of the diagnostic data is low for the frequency ratio of the corresponding classification. Diagnose each classification based on the magnitude of the test ratio, and if the test ratios of all classifications are within the range of the predetermined value, diagnose it as normal, and use this as diagnostic result data using frequency information.
- the output of the monitoring / diagnosis apparatus 1 If the test ratio of any classification is not within the predetermined value range, it is diagnosed as abnormal, and this is set as an output of the monitoring and diagnosing apparatus 1 as diagnosis result data using frequency information.
- FIG. 7 is a diagram showing the flow of the above diagnostic processing (processing flow of the monitoring diagnostic apparatus 1).
- the data classification unit 101 reads diagnostic data from the outside (step s701), reads classification data from the classification information storage unit 102 (step s702), compares the diagnostic data with the classification data, and finds the nearest neighbor. A classification number and a normalized statistical distance are generated (step s703).
- the abnormality diagnosing unit 103 receives the normalized statistical distance from the data classifying unit 101, totals the normalized statistical distance over a predetermined time width (step s704), diagnoses the abnormality (step s705), and diagnoses as abnormal.
- step s708 the process proceeds to step s708, and it is set as an output of the monitoring diagnosis apparatus 1 that there is an abnormality in the operation data regarding the result of the abnormality diagnosis based on the statistical distance.
- the abnormality diagnosing unit 103 sums up the normalized statistical distances and diagnoses the abnormality as a result of the abnormality diagnosis, the process proceeds to step s706.
- the frequency comparison unit 104 receives and compiles the nearest neighbor classification number from the data classification unit 101 with a predetermined time width, and reads the reference frequency ratio from the frequency information storage unit 105 to calculate the frequency ratio of the nearest neighbor classification number.
- the frequency comparison data is generated by comparison (step s706).
- the abnormality diagnosis unit 103 generates a diagnosis result based on the frequency comparison data (step s707), the result of the abnormality diagnosis based on the statistical distance is normal, and the result of the abnormality diagnosis based on the frequency ratio indicates an abnormality in the operation data. Whether it is present or normal is used as diagnosis result data as the output of the monitoring / diagnosis device 1.
- the configuration and operation of the hydraulic excavator will be described with reference to FIGS. 8A and 8B.
- the excavator 8 can perform an operation such as excavation by each operation mechanism provided.
- Bucket 801, arm 802 and boom 803 are operated by hydraulic cylinders 811, 812 and 813.
- the whole part related to excavation is often called a front.
- the hydraulic excavator 8 is equipped with a vehicle body controller (control device: described later) for controlling each operation mechanism and collecting / monitoring information from the sensors. Further, as shown in FIG.
- the hydraulic excavator 8 includes a turning mechanism 804 for rotating the main body 806 and a crawler (crawler belt) device 805 as a traveling mechanism for the entire hydraulic excavator.
- the turning mechanism 804 includes a hydraulic motor (not shown), and the main body 806 can turn left and right with respect to the traveling mechanism by driving the hydraulic motor of the turning mechanism 804.
- the crawler device 805 includes a right crawler 805a and a left crawler 805b, and each moves independently.
- a pressure sensor for measuring the tension of the crawlers 805a and 805b is provided and is monitored by the controller.
- the excavator can move forward.
- the right crawler 805a rotates forward and the left crawler 805b moves backward.
- the entire hydraulic excavator rotates counterclockwise.
- FIG. 9 is a diagram showing a controller network installed in a hydraulic excavator.
- the controller network of the hydraulic excavator includes an engine controller 21, a vehicle body controller 22, a monitor controller 23, an engine measurement unit 24, a hydraulic system measurement unit 25, and a data recording device 9.
- the engine measuring unit 24 is connected to the engine controller 21, and the engine controller 21 is connected to the data recording device 9 via the first common communication line 27A.
- the vehicle body controller 22, the monitor controller 23, and the hydraulic system measurement unit 25 are connected to the data recording device 9 via the second common communication line 27B.
- the engine controller 21 controls the fuel injection amount of the engine by controlling the electronic governor 28.
- the vehicle body controller 22 is driven by the engine and controls a main pump that supplies pressure oil to actuators such as the hydraulic cylinder and the hydraulic motor, and other hydraulic equipment.
- the monitor controller 23 is connected to the display 31 and the operation unit 32, and performs control related to display on the display 31 in accordance with an input operation of the operation unit 32.
- the engine measurement unit 24 inputs and collects detection signals of sensors that detect state quantities of various devices related to the engine system.
- the engine speed is detected as a sensor for detecting these state quantities.
- a rotation sensor 34 and temperature sensors 35a to 35n for detecting the exhaust gas temperature of each cylinder of the engine are shown.
- the hydraulic system measurement unit 25 receives and collects detection signals of sensors that detect state quantities of various devices related to the hydraulic system.
- an operation lever device is used as a sensor for detecting these state quantities.
- the pressure sensors 36a to 36n for detecting the operation pilot pressure (hereinafter referred to as operation pressure) generated by the pressure sensor and the pressure sensor 37 for detecting the track tension pressure are shown.
- the operation lever device commands the operation of the boom, arm, bucket, turning, traveling, etc., and the corresponding control valve is switched according to the generated operation pressure, and the pressure oil supplied to actuators such as hydraulic cylinders, hydraulic motors, etc. By controlling the flow and controlling the operation of the actuator, the operation of the boom, arm, bucket, turning, running, etc. is controlled.
- the data recording device 9 predetermines necessary ones of state quantity data collected by the engine measurement unit 24 and the hydraulic system measurement unit 25, and input data and output data from the engine controller 21, the vehicle body controller 22, and the monitor controller 23.
- the data is input at intervals through the first and second common communication lines 27A and 27B, and these data are stored as sensor data.
- the vehicle body controller 22 is equipped with the above-described diagnosis and monitoring device 1 and accesses the data recording device 9 to store the sensor data (engine) for a predetermined period stored in the data recording device 9 in order to perform the diagnosis processing shown in FIG.
- Information from various sensors collected by the measurement unit 24 and the hydraulic system measurement unit 25 is collected, recorded, and monitored.
- a personal computer 11 can be connected to the data recording device 9, the sensor data stored in the data recording device 9 can be downloaded to the personal computer 11, and the hydraulic excavator can be diagnosed by the monitoring / diagnosis device 1 mounted on the personal computer 11. it can. Furthermore, the sensor data stored in the data recording device 9 can be periodically transmitted to a server in a management office (not shown) via the wireless device 13 and the antenna 14 to diagnose a hydraulic excavator in the management office.
- FIG. 10 and 11 show the operation pressure (operation data) and the track tension pressure measured by the pressure sensors 36a to 36n, 37 and recorded and monitored by the vehicle body controller 22 (diagnosis monitoring device 1).
- FIG. 10 shows normal operation data
- FIG. 11 shows normal operation data when an abnormality occurs.
- 10 and FIG. 11 shows the track tension pressure, and below this, the operation pressures of the boom operation pressure, the arm operation pressure, the bucket operation pressure, the turning operation pressure, and the traveling operation pressure are shown.
- the track tension pressure abnormality 1101 is detected and recorded by the diagnostic monitoring device 1 provided in the vehicle body controller 22.
- the operation data excluding the track tension pressure is learned by the learning device during normal operation, and operation pattern data (reference classification information) and operation frequency data (reference frequency information) are created. 1 is stored in advance in the classification information storage unit 102 and the frequency information storage unit 105 shown in FIG.
- operation pattern data (reference classification information) stored in advance and each pressure sensor value of the operation data are compared, and the most statistical An operation pattern with a short distance is selected, a nearest statistical distance D with the operation pattern is calculated, and a normalized statistical distance d is further calculated.
- FIG. 12 the operation pattern data (reference classification information) stored in advance and each pressure sensor value of the operation data are compared, and the most statistical An operation pattern with a short distance is selected, a nearest statistical distance D with the operation pattern is calculated, and a normalized statistical distance d is further calculated.
- the horizontal axis represents the machine operation time (in the order of input operation data), and the vertical axis represents the normalized statistical distance.
- a moving average value 1202 of (unit time) is shown. Even during an abnormal operation, the moving average value of the normalized statistical distance is equal to or less than the threshold value 1 and it can be seen that there is no significant difference from the operation pattern data during the normal operation.
- FIG. 13 shows the frequency ratio of each operation pattern when the track tension pressure is large (during abnormal operation) and small (during normal operation).
- the horizontal axis represents the machine operation pattern (operation data classification data), and the vertical axis represents the frequency ratio for each operation pattern. It can be seen that the distribution of frequency ratios is completely different between normal operation and abnormal operation. For example, it can be seen that pattern numbers 12, 20, and 21 have a higher frequency during abnormal operation (track (tension strong) than during normal operation (track tension weak). Of these, the operation data pattern of the operation pattern number 21 that has the highest frequency during an abnormal operation is as shown in FIG.
- FIG. 15 shows the operating status of the engine of the hydraulic excavator and the sensor value of the operating pressure.
- the rotational speed of the engine that drives the main pump for obtaining the hydraulic pressure changes according to the operation of the hydraulic excavator. I understand.
- the no-operation section 1501 no operation has occurred, so the engine is also operating in the low speed range. Since the occurrence ratio of the no-operation section may change from time to time, it is appropriate to set only the section that is actually operated as a monitoring diagnosis target. Therefore, the operation data only at the time of work may be analyzed with reference to the operation status of the engine or the pressure sensor value of the operation.
- FIG. 16 shows the operating state of the engine of the hydraulic excavator.
- the period is divided into two, which are divided into “period 1” and “period 2”, respectively.
- FIG. 17 shows operation patterns and their frequencies for the two periods.
- the frequency 1701 of the operation pattern “7” increases from “period 1” to “period 2”.
- the operation of the hydraulic excavator is performed as shown in FIG. It can be seen that this indicates a “no operation state” that has not been performed. That is, it is considered that the no-operation time is increased in “period 2” as compared to “period 1”, and such an operation pattern should be excluded.
- the user excludes the classification data of the no-operation time (when the operation lever device is not operated) from the classification data (reference classification information) and selects other classification data.
- the data classification unit 101 generates the operation data classification information (nearest neighbor classification number and normalized statistical distance) by excluding the classification data and diagnostic data of the no-operation time.
- the frequency comparison unit 104 in FIG. 1 can obtain an accurate frequency hi or frequency ratio ei that is not affected by the no-operation time, and can perform an appropriate diagnosis with fewer erroneous determinations.
- FIG. 19 and 20 show temperature sensor values (in different periods) for the exhaust temperature of each cylinder of the hydraulic excavator engine measured by the temperature sensors 35a to 35n and recorded and monitored by the vehicle body controller 22 (diagnostic monitoring device 1). Operation data).
- FIG. 19 shows operation data for period 3 during normal operation
- FIG. 20 shows operation data for period 4 during abnormal operation.
- FIG. 21 shows a comparison of the frequency of operation patterns (operation data classification data) for periods 3 and 4 in FIGS. 19 and 20. As shown in FIG. 21, the frequency of the operation patterns 13 and 26 is changed.
- FIG. 22 when the operation pattern during abnormal operation is confirmed, the operation patterns 13 and 26 indicate which operation the temperature sensor value has. It can be seen that the value is higher than the pattern. From this, it can be seen that the engine exhaust temperature distribution differs between the two periods.
- abnormality detection can be performed by comparing the frequency of the operation patterns of the hydraulic excavator.
- FIG. 23 is a diagram showing the configuration of the monitoring / diagnosis apparatus according to the second embodiment of the present invention.
- the monitoring / diagnosis apparatus 1a has a display unit 2301 added to the configuration of FIG.
- the display unit 2301 may be, for example, the display 31 shown in FIG. 9, or may be the display of the personal computer 11 when the monitoring / diagnosis apparatus 1 a is mounted on the personal computer 11.
- the display unit 2301 receives the output from the frequency comparison unit 104 or the abnormality diagnosis unit 103 and displays the output contents.
- FIG. 24 is a diagram showing a processing flow of a part for displaying the operation data frequency comparison information generated by the frequency comparison unit 104 on the display unit 2301 among the processing functions of the monitoring diagnosis apparatus shown in FIG.
- the data classification unit 101 reads diagnostic data from the outside (step s2401), reads classification data from the classification information storage unit 102 (step s2402), compares the diagnostic data with the classification data, and finds the nearest neighbor. A classification number and a normalized statistical distance are generated (step s2403).
- the frequency comparison unit 104 receives and compiles the nearest neighbor classification number from the data classification unit 101 with a predetermined time width, and reads the reference frequency ratio from the frequency information storage unit 105 to calculate the frequency ratio of the nearest neighbor classification number.
- the frequency comparison data is generated by comparison (step s2404).
- the display unit 2301 receives the frequency comparison data from the frequency comparison unit 104 and displays it in a display mode as shown in FIG. 21, for example (step s2405). In the display example of FIG. 21, the reference frequency ratio data 2101 (reference frequency information) and the aggregated frequency ratio 2102 are displayed for each classification number.
- FIG. 25 shows diagnosis result data of the abnormality diagnosis unit 103.
- the frequency comparison data as shown in FIG. 21, when the frequency ratio 2102 is abnormal compared to the reference frequency ratio data 2101 (reference frequency information).
- the example of an output screen display at the time of determination is shown. In this example, it is displayed that the frequency of the operation patterns 13 and 26 is increasing, which corresponds to a graph display of frequency data of “Operation” Pattern “No” in FIG. 21 being “13” and “26”.
- Reference link designations 2502 and 2503 are designations for displaying detailed information of the operation patterns “13” and “26”. For example, when the reference link designation 2502 is operated, a detailed information display screen 2604 as shown in FIG. Appears.
- the operation pattern “13” can be referred to, and the increase tendency of the operation pattern can be confirmed with reference to the frequency data 2601 and the reference frequency ratio data 2602.
- the operation pattern “13” similar to FIG. Can be referred to as a sensor data pattern 2603.
- sensor data patterns of other operation patterns are also displayed from the viewpoint of comparison display.
- FIG. 27 is a diagram illustrating a processing flow of a portion that displays the diagnosis result data of the abnormality diagnosis unit 103 among the processing functions of the monitoring diagnosis apparatus illustrated in FIG. 23.
- the data classification unit 101 reads diagnostic data from the outside (step s2701), reads classification data from the classification information storage unit 102 (step s2702), compares the diagnostic data with the classification data, and finds the nearest neighbor. A classification number and a normalized statistical distance are generated (step s2703).
- the abnormality diagnosing unit 103 receives the normalized statistical distance from the data classifying unit 101, totals the normalized statistical distance over a predetermined time width (step s2704), diagnoses the abnormality (step s2705), and diagnoses as abnormal.
- step s2708 the process proceeds to step s2708, and the fact that there is an abnormality in the operation data regarding the result of the abnormality diagnosis based on the statistical distance is output as diagnosis result data to the display unit 2301, and the display unit 2301 displays the diagnosis result data (step s2708). ).
- the abnormality diagnosing unit 103 adds up the normalized statistical distances and diagnoses the abnormality as a result of the abnormality diagnosis, the process proceeds to step s2706.
- the frequency comparison unit 104 receives and compiles the nearest neighbor classification number from the data classification unit 101 with a predetermined time width, and reads the reference frequency ratio from the frequency information storage unit 105 to calculate the frequency ratio of the nearest neighbor classification number.
- Comparison is made to generate frequency comparison data (step s2706).
- the abnormality diagnosis unit 103 generates a diagnosis result based on the frequency comparison data (step s2707), the result of the abnormality diagnosis based on the statistical distance is normal, and the result of the abnormality diagnosis based on the frequency ratio indicates an abnormality in the operation data. Whether it is normal or normal is output to the display unit 2301 as diagnosis result data, and the display unit 2301 displays the diagnosis result data (step s2708).
- the monitoring / diagnosis device 1a shown in FIG. 23 includes the abnormality diagnosis unit 103 and performs abnormality detection by the monitoring / diagnosis device 1a itself. However, the abnormality diagnosis unit 103 is not provided and the output (frequency comparison) of the frequency comparison unit 104 is performed. (Data) only may be displayed. Even in such a configuration, as described above, abnormality detection can be performed based on a user's judgment.
- FIG. 28 is another display example of the frequency comparison data
- the line graph is an operation pattern of the sensor data of the exhaust temperature of the hydraulic excavator in the period 3 and the period 4 shown in FIG. 19 and FIG.
- the frequency comparison data (test ratio Rate) is shown, and the bar graph shows the reference frequency ratio in Expression 7 (reference frequency ratio 2101 in FIG. 21).
- the reference frequency is high in the operation patterns 13, 14, 26, etc., and among them, the test ratio exceeds 1, that is, the increase is in the two operation patterns 13 and 26.
- FIG. 29 shows the configuration of the classification information creation device 29.
- the classification information creation device 29 includes a classification information generation unit 2901 and a classification information storage unit 102.
- the classification information generation unit 2901 generates classification data from the learning data in accordance with the set value stored in the classification information generation unit 2901 in advance when the learning data is input from the outside. Specifically, a cluster of learning data is calculated using a technique such as k-means, the barycentric coordinates in each cluster are obtained, and the barycentric coordinates are held for each data item as shown in FIG.
- each classification data with a classification number corresponds to information of each cluster.
- the radius of each cluster is also obtained and held. For the radius, for example, the Euclidean distance between the barycentric coordinates and the data belonging to each cluster is obtained using Equation 3, and the average value or the maximum value of the Euclidean distance is used.
- the set value stored in the classification information generation unit 2901 in advance corresponds to the number of clusters to be classified when the k-means method is used.
- the generated preset value that is, the number of clusters is m
- m clusters clusters (classification data) are generated.
- the calculated data item value and radius for each classification (cluster) are output to the classification information storage unit 102 and recorded / saved.
- FIG. 30 shows the configuration of the frequency information generating device 30.
- the frequency information generation device 30 includes a data classification unit 3001 (second data classification unit), a classification information storage unit 102, a frequency information generation unit 3002, and a frequency information storage unit 105.
- the data classification unit 3001 has the same function as the data classification unit 101 of the monitoring and diagnosis apparatus 1.
- the data classification unit 3001 When learning data is input from the outside, the data classification unit 3001 reads the classification data stored in advance in the classification information storage unit 102, classifies the learning data, and sequentially outputs the classification numbers as in FIG.
- the frequency information generation unit 3001 receives the classification number output by the data classification unit 3001 corresponding to the learning data, generates frequency data similar to that in FIG. 5, and outputs the frequency data to the frequency information storage unit 105.
- the frequency information storage unit 105 stores the output frequency table data.
- FIG. 31 is a diagram showing a configuration of the monitoring and diagnosing device 1b when the monitoring and diagnosing device 1 is provided with the functions of the classification information creating device 29 and the frequency information generating device 30.
- the data classification unit 101 of the monitoring diagnostic device 1 shown in FIG. 1 is shared with the data classification unit 3001 of the frequency information generating device 30, and the frequency included in the frequency comparison unit 104 in the monitoring diagnostic device 1
- the information generation function is separated as a frequency information generation unit 3001.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Mining & Mineral Resources (AREA)
- Civil Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Structural Engineering (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Mechanical Engineering (AREA)
- Game Theory and Decision Science (AREA)
- Fuzzy Systems (AREA)
- Automation & Control Theory (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
Description
これにより利用者は異常の詳細情報を知ることができる。
8 油圧ショベル
9 データ記録装置
11 パソコン
13 無線機
14 アンテナ
21 エンジンコントローラ
22 車体コントローラ
23 モニタコントローラ
24 エンジン計測ユニット
25 油圧システム計測ユニット
27A 第1共通通信ライン
27B 第2共通通信ライン
28 電子ガバナ
29 分類情報作成装置
30 頻度情報生成装置
31 ディスプレイ
34 回転センサ
35a~35n 温度センサ
36a~26n 圧力センサ
37 圧力センサ
101 データ分類部(第1データ分類部)
102 分類情報記憶部
103 異常判定部
104 頻度比較部
105 頻度情報記憶部
501 頻度表
601 時間幅データ
602 参照頻度表
801 バケット
802 アーム
803 ブーム
804 旋回機構
805 クローラー装置
805a 右側クローラー
805b 左側クローラー
806 本体
811,812,813 油圧シリンダ
1101 トラックテンション圧力異常
1201 正規化統計距離
1501 無操作区間
2101 参照頻度比率データ
2102 頻度比率
2502,2503 参照リンク指定
2601 頻度データ
2602 参照頻度比率データ
2603 センサデータパターン
2604 詳細情報表示画面
2901 分類情報生成部
3001 データ分類部(第2データ分類部)
3002 頻度情報生成部
Claims (8)
- 監視診断装置(動作頻度検出)
複数のセンサ(34,35a~35n,36a~36n,37)によって検出された作業機械の稼動データを時系列的に入力し、この稼動データを用いて前記作業機械の異常診断を行う作業機械の監視診断装置において、
参照分類情報を記憶した分類情報記憶部(102)と、
参照頻度情報を記憶した頻度情報記憶部(105)と、
前記分類情報記憶部から前記参照分類情報を読み出し、前記複数のセンサによって検出され、時系列的に入力した前記稼動データを前記参照分類情報と比較して分類し、稼動データ分類情報を生成する第1データ分類部(101)と、
前記稼動データ分類情報を集計して、前記稼動データの分類ごとの出現頻度の情報を付加した稼動データ頻度情報を生成するとともに、前記頻度情報記憶部から前記参照頻度情報を読み出して、前記稼動データ頻度情報と前記参照頻度情報とを比較した稼動データ頻度比較情報を生成する頻度比較部(104)と、
前記稼動データ分類情報と前記稼動データ頻度比較情報を用いて前記作業機械の異常診断を行う異常診断部(103)とを備えることを特徴とする作業機械の監視診断装置。
- 比較情報を表示
請求項1記載の作業機械の監視診断装置において、
前記頻度比較部(104)が生成する前記稼動データ頻度比較情報および前記異常診断部の診断結果データの少なくとも一方を表示する表示部(2301)を更に備えることを特徴とする作業機械の監視診断装置。
- 頻度に異常がある分類を検出
請求項2記載の作業機械の監視診断装置において、
前記異常診断部(103)は、前記稼動データ頻度比較情報を用いて前記作業機械の異常診断を行った結果、前記稼動データ頻度情報と前記参照頻度情報との間に所定の差異が検出される場合に、前記稼動データに異常があると診断し、
前記表示部(104)はその診断結果を表示することを特徴とする作業機械の監視診断装置。
- 頻度に異常がある分類を強調表示
請求項3記載の作業機械の監視診断装置において、
前記表示部(104)は、前記稼動データ頻度情報と前記参照頻度情報との間に所定の差異が検出される場合に、この差異に関連する前記稼動データ分類情報を表示することを特徴とする作業機械の監視診断装置。
- 監視診断装置(動作頻度検出)
複数のセンサ(34,35a~35n,36a~36n,37)によって検出された作業機械の稼動データを時系列的に入力し、この稼動データを用いて前記作業機械の異常診断を行う作業機械の監視診断装置において、
参照分類情報を記憶した分類情報記憶部(102)と、
参照頻度情報を記憶した頻度情報記憶部(105)と、
前記分類情報記憶部から前記参照分類情報を読み出し、前記複数のセンサによって検出され、時系列的に入力した前記稼動データを前記参照分類情報と比較して分類し、稼動データ分類情報を生成する第1データ分類部(101)と、
前記稼動データ分類情報を集計して、前記稼動データの分類ごとの出現頻度の情報を付加した稼動データ頻度情報を生成するとともに、前記頻度情報記憶部から前記参照頻度情報を読み出して、前記稼動データ頻度情報と前記参照頻度情報とを比較した稼動データ頻度比較情報を生成する頻度比較部(104)と、
前記頻度比較部が生成する前記稼動データ頻度比較情報を表示する表示部(2301)を更に備えることを特徴とする作業機械の監視診断装置。
- 動作時のみ診断
請求項1~5のいずれか1項記載の作業機械の監視診断装置において、
前記第1データ分類部(101)は、前記分類情報記憶部(102)に記憶された参照分類情報のうち、予め選択された参照分類情報のみを抽出するとともに、前記複数のセンサによって検出され、時系列的に入力した前記稼動データのうち、前記予め選択された参照分類情報に対応する稼動データのみを抽出して、前記予め選択された参照分類情報と比較して前記稼動データ分類情報を生成することを特徴とする作業機械の監視診断装置。
- 分類情報生成部
請求項1~6のいずれか1項記載の作業機械の監視診断装置において、
前記複数のセンサによって検出された作業機械の稼動データを時系列的に入力し、この稼動データの類似性を比較して分類し、前記分類情報記憶部に記憶される参照分類情報を生成する分類情報生成部(2901)を更に備えることを特徴とする作業機械の監視診断装置。
- 頻度情報生成部
請求項7記載の作業機械の監視診断装置において、
前記複数のセンサによって検出され、時系列的に入力した稼動データを前記分類情報生成部(2901)によって生成された前記参照分類情報と比較して分類し、稼動データ分類情報を生成する第2データ分類部(3001)と、前記稼動データ分類情報を集計して、前記稼動データの分類ごとの出現頻度の情報を付加し、前記頻度情報記憶部に記憶される参照頻度情報を生成する頻度情報生成部(3002)とを更に備えることを特徴とする作業機械の監視診断装置。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP10844592.5A EP2530209B2 (en) | 2010-01-28 | 2010-01-28 | Operation machine monitoring diagnosis device |
JP2011551630A JP5220929B2 (ja) | 2010-01-28 | 2010-01-28 | 作業機械の監視診断装置 |
AU2010344438A AU2010344438B2 (en) | 2010-01-28 | 2010-01-28 | Operation machine monitoring diagnosis device |
PCT/JP2010/051172 WO2011092830A1 (ja) | 2010-01-28 | 2010-01-28 | 作業機械の監視診断装置 |
US13/575,668 US8838324B2 (en) | 2010-01-28 | 2010-01-28 | Monitoring and diagnosing device for working machine |
CN201080062664.0A CN102741676B (zh) | 2010-01-28 | 2010-01-28 | 作业机械的监视诊断装置 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2010/051172 WO2011092830A1 (ja) | 2010-01-28 | 2010-01-28 | 作業機械の監視診断装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2011092830A1 true WO2011092830A1 (ja) | 2011-08-04 |
Family
ID=44318840
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2010/051172 WO2011092830A1 (ja) | 2010-01-28 | 2010-01-28 | 作業機械の監視診断装置 |
Country Status (6)
Country | Link |
---|---|
US (1) | US8838324B2 (ja) |
EP (1) | EP2530209B2 (ja) |
JP (1) | JP5220929B2 (ja) |
CN (1) | CN102741676B (ja) |
AU (1) | AU2010344438B2 (ja) |
WO (1) | WO2011092830A1 (ja) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012157603A1 (ja) * | 2011-05-16 | 2012-11-22 | 住友重機械工業株式会社 | ショベル、その監視装置及びショベルの出力装置 |
WO2013026282A1 (zh) * | 2011-08-22 | 2013-02-28 | 湖南三一智能控制设备有限公司 | 一种挖掘机自检测***及方法 |
JP2013199804A (ja) * | 2012-03-26 | 2013-10-03 | Sumitomo Heavy Ind Ltd | 作業機械の異常診断装置 |
KR20140083105A (ko) * | 2012-12-24 | 2014-07-04 | 두산인프라코어 주식회사 | 굴삭기 진단 방법 및 장치 |
JP2014184641A (ja) * | 2013-03-22 | 2014-10-02 | Toshiba Mach Co Ltd | 射出成形システムの予防保全装置及び射出成形システムの予防保全方法 |
US20150101314A1 (en) * | 2012-09-17 | 2015-04-16 | Mtu Friedrichshafen Gmbh | Method for operating an internal combustion engine |
JP2016023489A (ja) * | 2014-07-23 | 2016-02-08 | 住友重機械工業株式会社 | ショベル支援装置及びショベル管理方法 |
WO2017122292A1 (ja) * | 2016-01-13 | 2017-07-20 | 三菱電機株式会社 | 運転状態分類装置 |
JP2019183646A (ja) * | 2019-08-06 | 2019-10-24 | 住友重機械工業株式会社 | ショベル支援装置 |
US11480948B2 (en) * | 2017-10-31 | 2022-10-25 | Mitsubishi Heavy Industries, Ltd. | Monitoring target selecting device, monitoring target selecting method, and program |
JP7400064B1 (ja) | 2022-11-18 | 2023-12-18 | エヌ・ティ・ティ・コミュニケーションズ株式会社 | 学習装置、学習方法及び学習プログラム |
JP7441718B2 (ja) | 2020-05-07 | 2024-03-01 | 国立大学法人広島大学 | 故障予測システム及び故障予測方法 |
Families Citing this family (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105026214B (zh) * | 2013-06-21 | 2017-06-30 | 日立建机株式会社 | 工程机械的异常信息控制装置 |
GB201313205D0 (en) | 2013-07-24 | 2013-09-04 | Ent Ltd | Method and system for condition monitoring |
US10032216B2 (en) | 2013-10-07 | 2018-07-24 | State Farm Mutual Automobile Insurance Company | Method and system for a vehicle auction tool with vehicle condition assessments |
US10423989B2 (en) | 2013-10-07 | 2019-09-24 | State Farm Mutual Automobile Insurance Company | Systems and methods to assess the condition of a vehicle |
US20150100506A1 (en) * | 2013-10-07 | 2015-04-09 | State Farm Mutual Automobile Insurance Company | Systems and methods to report vehicle ownership information |
US10140782B2 (en) | 2013-10-07 | 2018-11-27 | State Farm Mutual Automobile Insurance Company | Vehicle sharing tool based on vehicle condition assessments |
US9691025B2 (en) | 2014-09-16 | 2017-06-27 | Caterpillar Inc. | Machine operation classifier |
US9982414B2 (en) * | 2016-05-16 | 2018-05-29 | Caterpillar Inc. | Operation identification of a work machine |
US10099735B2 (en) | 2016-11-01 | 2018-10-16 | Cnh Industrial America Llc | System and method for monitoring track tension for a track assembly of a work vehicle |
US20180225355A1 (en) * | 2017-02-07 | 2018-08-09 | International Business Machines Corporation | Self-improving classification |
KR20190000261A (ko) * | 2017-06-22 | 2019-01-02 | 두산인프라코어 주식회사 | 건설 기계의 에러 점검 시스템 |
JP6777686B2 (ja) * | 2018-05-29 | 2020-10-28 | ファナック株式会社 | 診断装置、診断方法及び診断プログラム |
US11433539B2 (en) * | 2018-07-31 | 2022-09-06 | Nissan Motor Co., Ltd. | Abnormality determination device and abnormality determination method |
US11567482B2 (en) * | 2018-08-31 | 2023-01-31 | Toshiba Mitsubishi-Electric Industrial Systems Corporation | Manufacturing process monitoring apparatus |
US10676048B2 (en) | 2018-10-18 | 2020-06-09 | Northrop Grumman Systems Corporation | Parametric data modeling for model based reasoners |
US10725463B1 (en) * | 2018-10-18 | 2020-07-28 | Northrop Grumman Systems Corporation | High frequency sensor data analysis and integration with low frequency sensor data used for parametric data modeling for model based reasoners |
US10964130B1 (en) | 2018-10-18 | 2021-03-30 | Northrop Grumman Systems Corporation | Fleet level prognostics for improved maintenance of vehicles |
US10814883B1 (en) | 2018-10-18 | 2020-10-27 | Northrop Grumman Systems Corporation | Prognostics for improved maintenance of vehicles |
JP7363032B2 (ja) * | 2019-01-10 | 2023-10-18 | オムロン株式会社 | 情報管理装置、及び情報管理方法 |
US11222202B2 (en) | 2019-01-14 | 2022-01-11 | Deere & Company | Targeted testing and machine-learning systems for detecting and identifying machine behavior |
JP7030072B2 (ja) * | 2019-03-14 | 2022-03-04 | 株式会社日立製作所 | 時系列データ監視システム、および時系列データ監視方法 |
DE102019108278A1 (de) * | 2019-03-29 | 2020-10-01 | Liebherr-Components Biberach Gmbh | Vorrichtung zum Ermitteln des Ist-Zustands und/oder der Restlebensdauer einer Baumaschine |
US11697917B2 (en) * | 2019-07-26 | 2023-07-11 | Deere & Company | Anticipatory modification of machine settings based on predicted operational state transition |
CN110775823B (zh) * | 2019-11-20 | 2021-03-16 | 中国电建集团成都勘测设计研究院有限公司 | 缆机吊零事件分析方法及*** |
US20210325842A1 (en) * | 2020-04-15 | 2021-10-21 | Kabushiki Kaisha Toshiba | Process monitoring device, process monitoring method, and program |
CN112163792A (zh) * | 2020-10-30 | 2021-01-01 | 重庆电子工程职业学院 | 实训场所设备智能管理的方法及*** |
US11409866B1 (en) | 2021-06-25 | 2022-08-09 | Northrop Grumman Systems Corporation | Adaptive cybersecurity for vehicles |
US11681811B1 (en) | 2021-06-25 | 2023-06-20 | Northrop Grumman Systems Corporation | Cybersecurity for configuration and software updates of vehicle hardware and software based on fleet level information |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05256741A (ja) | 1992-03-11 | 1993-10-05 | Toshiba Corp | プラント信号監視方法およびその装置 |
JP2000132558A (ja) | 1998-10-22 | 2000-05-12 | Nri & Ncc Co Ltd | 分類ルール探求式クラスター分析装置 |
JP2002288781A (ja) | 2001-03-27 | 2002-10-04 | Toshiba Corp | センサ異常検出方法及びセンサ異常検出装置 |
JP2005241089A (ja) | 2004-02-25 | 2005-09-08 | Mitsubishi Electric Corp | 機器診断装置、冷凍サイクル装置、機器診断方法、機器監視システム、冷凍サイクル監視システム |
JP2006011849A (ja) * | 2004-06-25 | 2006-01-12 | Kagawa Univ | データ圧縮装置及び方法,データ解析装置及び方法並びにデータ管理システム |
JP2006276924A (ja) * | 2005-03-28 | 2006-10-12 | Hitachi Ltd | 設備機器診断装置及び設備機器診断プログラム |
JP2006349433A (ja) * | 2005-06-15 | 2006-12-28 | Hitachi Appliances Inc | 機器診断システム及び情報表示装置及びその方法 |
JP2007257366A (ja) * | 2006-03-23 | 2007-10-04 | Kagawa Univ | 診断装置及び診断方法 |
JP2008196428A (ja) * | 2007-02-14 | 2008-08-28 | Shin Caterpillar Mitsubishi Ltd | 機体診断方法および機体診断システム |
Family Cites Families (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3973648A (en) | 1974-09-30 | 1976-08-10 | Westinghouse Electric Corporation | Monitoring system for elevator installation |
US4258421A (en) * | 1978-02-27 | 1981-03-24 | Rockwell International Corporation | Vehicle monitoring and recording system |
JPS5762702A (en) * | 1980-10-03 | 1982-04-15 | Hitachi Ltd | Automatic train control device |
DE3639755A1 (de) | 1985-11-22 | 1987-05-27 | Oki Electric Ind Co Ltd | Selbstdiagnoseverfahren fuer ein geraet |
US5070468A (en) | 1988-07-20 | 1991-12-03 | Mitsubishi Jukogyo Kabushiki Kaisha | Plant fault diagnosis system |
JPH07295628A (ja) | 1994-04-22 | 1995-11-10 | Asahi Chem Ind Co Ltd | プラント異常診断方法 |
US5710710A (en) * | 1994-09-21 | 1998-01-20 | Optoelectronics, Inc. | Frequency counter with reduced false correlations |
US6278890B1 (en) * | 1998-11-09 | 2001-08-21 | Medacoustics, Inc. | Non-invasive turbulent blood flow imaging system |
US6285947B1 (en) * | 1999-10-28 | 2001-09-04 | Brunswick Corporation | Prognostication of future failure of an engine indicator parameter |
JP4756793B2 (ja) * | 2000-09-14 | 2011-08-24 | 株式会社小松製作所 | 建設機械の管理装置 |
EP1548419B1 (en) * | 2002-08-30 | 2013-07-24 | NSK Ltd. | Method and device for monitoring status of mechanical equipment and abnormality diagnosing device |
ZA200307740B (en) | 2002-10-29 | 2004-07-02 | Inventio Ag | Device and method for remote maintenance of a lift. |
JP4173121B2 (ja) * | 2003-09-02 | 2008-10-29 | 株式会社小松製作所 | 建設機械の運転システム |
WO2006043511A1 (ja) * | 2004-10-18 | 2006-04-27 | Nsk Ltd. | 機械設備の異常診断システム |
FI118466B (fi) | 2005-04-08 | 2007-11-30 | Kone Corp | Kunnonvalvontajärjestelmä |
JP2007148890A (ja) * | 2005-11-29 | 2007-06-14 | Hitachi Ltd | 機器診断装置 |
US8024095B2 (en) * | 2008-03-07 | 2011-09-20 | Caterpillar Inc. | Adaptive work cycle control system |
WO2009150251A2 (de) | 2008-06-13 | 2009-12-17 | Inventio Ag | Aufzugsanlage und verfahren zur wartung einer solchen aufzugsanlage |
US8396870B2 (en) * | 2009-06-25 | 2013-03-12 | University Of Tennessee Research Foundation | Method and apparatus for predicting object properties and events using similarity-based information retrieval and modeling |
US8943478B2 (en) * | 2009-07-14 | 2015-01-27 | International Business Machines Corporation | Fault detection and localization in dynamic software applications |
US8884759B2 (en) * | 2011-09-12 | 2014-11-11 | Near-Miss Management, Llc | Dynamic prediction of risk levels for manufacturing operations through leading risk indicators |
-
2010
- 2010-01-28 US US13/575,668 patent/US8838324B2/en active Active
- 2010-01-28 JP JP2011551630A patent/JP5220929B2/ja active Active
- 2010-01-28 AU AU2010344438A patent/AU2010344438B2/en active Active
- 2010-01-28 WO PCT/JP2010/051172 patent/WO2011092830A1/ja active Application Filing
- 2010-01-28 EP EP10844592.5A patent/EP2530209B2/en active Active
- 2010-01-28 CN CN201080062664.0A patent/CN102741676B/zh active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05256741A (ja) | 1992-03-11 | 1993-10-05 | Toshiba Corp | プラント信号監視方法およびその装置 |
JP2000132558A (ja) | 1998-10-22 | 2000-05-12 | Nri & Ncc Co Ltd | 分類ルール探求式クラスター分析装置 |
JP2002288781A (ja) | 2001-03-27 | 2002-10-04 | Toshiba Corp | センサ異常検出方法及びセンサ異常検出装置 |
JP2005241089A (ja) | 2004-02-25 | 2005-09-08 | Mitsubishi Electric Corp | 機器診断装置、冷凍サイクル装置、機器診断方法、機器監視システム、冷凍サイクル監視システム |
JP2006011849A (ja) * | 2004-06-25 | 2006-01-12 | Kagawa Univ | データ圧縮装置及び方法,データ解析装置及び方法並びにデータ管理システム |
JP2006276924A (ja) * | 2005-03-28 | 2006-10-12 | Hitachi Ltd | 設備機器診断装置及び設備機器診断プログラム |
JP2006349433A (ja) * | 2005-06-15 | 2006-12-28 | Hitachi Appliances Inc | 機器診断システム及び情報表示装置及びその方法 |
JP2007257366A (ja) * | 2006-03-23 | 2007-10-04 | Kagawa Univ | 診断装置及び診断方法 |
JP2008196428A (ja) * | 2007-02-14 | 2008-08-28 | Shin Caterpillar Mitsubishi Ltd | 機体診断方法および機体診断システム |
Non-Patent Citations (1)
Title |
---|
See also references of EP2530209A4 |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012157603A1 (ja) * | 2011-05-16 | 2012-11-22 | 住友重機械工業株式会社 | ショベル、その監視装置及びショベルの出力装置 |
WO2013026282A1 (zh) * | 2011-08-22 | 2013-02-28 | 湖南三一智能控制设备有限公司 | 一种挖掘机自检测***及方法 |
JP2013199804A (ja) * | 2012-03-26 | 2013-10-03 | Sumitomo Heavy Ind Ltd | 作業機械の異常診断装置 |
CN104884774A (zh) * | 2012-09-17 | 2015-09-02 | Mtu腓特烈港有限责任公司 | 用于运行内燃机的方法 |
US9574508B2 (en) * | 2012-09-17 | 2017-02-21 | Mtu Friedrichshafen Gmbh | Method for operating an internal combustion engine |
US20150101314A1 (en) * | 2012-09-17 | 2015-04-16 | Mtu Friedrichshafen Gmbh | Method for operating an internal combustion engine |
KR20140083105A (ko) * | 2012-12-24 | 2014-07-04 | 두산인프라코어 주식회사 | 굴삭기 진단 방법 및 장치 |
KR102031369B1 (ko) | 2012-12-24 | 2019-10-11 | 두산인프라코어 주식회사 | 굴삭기 진단 방법 및 장치 |
JP2014184641A (ja) * | 2013-03-22 | 2014-10-02 | Toshiba Mach Co Ltd | 射出成形システムの予防保全装置及び射出成形システムの予防保全方法 |
JP2016023489A (ja) * | 2014-07-23 | 2016-02-08 | 住友重機械工業株式会社 | ショベル支援装置及びショベル管理方法 |
WO2017122292A1 (ja) * | 2016-01-13 | 2017-07-20 | 三菱電機株式会社 | 運転状態分類装置 |
US11480948B2 (en) * | 2017-10-31 | 2022-10-25 | Mitsubishi Heavy Industries, Ltd. | Monitoring target selecting device, monitoring target selecting method, and program |
JP2019183646A (ja) * | 2019-08-06 | 2019-10-24 | 住友重機械工業株式会社 | ショベル支援装置 |
JP7441718B2 (ja) | 2020-05-07 | 2024-03-01 | 国立大学法人広島大学 | 故障予測システム及び故障予測方法 |
JP7400064B1 (ja) | 2022-11-18 | 2023-12-18 | エヌ・ティ・ティ・コミュニケーションズ株式会社 | 学習装置、学習方法及び学習プログラム |
Also Published As
Publication number | Publication date |
---|---|
US20120317444A1 (en) | 2012-12-13 |
EP2530209B2 (en) | 2023-04-26 |
EP2530209A1 (en) | 2012-12-05 |
JP5220929B2 (ja) | 2013-06-26 |
AU2010344438B2 (en) | 2014-11-06 |
EP2530209B1 (en) | 2019-03-13 |
EP2530209A4 (en) | 2017-12-13 |
CN102741676B (zh) | 2016-01-20 |
CN102741676A (zh) | 2012-10-17 |
US8838324B2 (en) | 2014-09-16 |
AU2010344438A1 (en) | 2012-08-16 |
JPWO2011092830A1 (ja) | 2013-05-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5220929B2 (ja) | 作業機械の監視診断装置 | |
CN102326066B (zh) | 作业机械的学习诊断***、状态诊断装置及状态学习装置 | |
Bayar et al. | Fault detection, diagnosis and recovery using Artificial Immune Systems: A review | |
JP5220917B2 (ja) | 建設機械の異常検出装置 | |
JP5530019B1 (ja) | 異常予兆検知システム及び異常予兆検知方法 | |
EP1336081B1 (en) | Inferential signal generator for instrumented equipment and processes | |
US6408259B1 (en) | Alert generation for trend performance analysis | |
Brotherton et al. | Anomaly detection for advanced military aircraft using neural networks | |
US9291524B2 (en) | Operation data collection device for construction machines | |
WO2011125130A1 (ja) | プラントの診断装置、診断方法、及び診断プログラム | |
WO2013047408A1 (ja) | ショベル、ショベル管理装置、及びショベル管理方法 | |
CN102880170A (zh) | 基于基线模型和贝叶斯因子的***故障早期预警方法 | |
CN104854524A (zh) | 挖土机的异常判定方法、管理装置及挖土机 | |
KR102102346B1 (ko) | 함정설비의 상태기반 정비지원 시스템 및 방법 | |
US6636842B1 (en) | System and method for controlling an industrial process utilizing process trajectories | |
US6675639B1 (en) | Apparatus and method to detect cylinder faults of internal combustion engines via exhaust temperature monitoring | |
CN107783495B (zh) | 单元控制*** | |
CN117932322B (zh) | 一种面粉设备故障诊断方法及*** | |
Sarwar et al. | Hybrid intelligence for enhanced fault detection and diagnosis for industrial gas turbine engine | |
Al-Shrouf et al. | Online feature-based multisensor object detection system for bucket-wheel excavators | |
WO2022215705A1 (ja) | 性能診断装置、性能診断方法 | |
CN104252573A (zh) | 一种基于分步模式的机械多故障诊断方法 | |
US20240134367A1 (en) | Machine state detecting device | |
Das et al. | CBM+ for helicopter Health management |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201080062664.0 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10844592 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2011551630 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2010344438 Country of ref document: AU |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2010844592 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2010344438 Country of ref document: AU Date of ref document: 20100128 Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13575668 Country of ref document: US |