CN112881044B - Abnormality diagnosis method for variable rotation speed equipment - Google Patents
Abnormality diagnosis method for variable rotation speed equipment Download PDFInfo
- Publication number
- CN112881044B CN112881044B CN202010546081.0A CN202010546081A CN112881044B CN 112881044 B CN112881044 B CN 112881044B CN 202010546081 A CN202010546081 A CN 202010546081A CN 112881044 B CN112881044 B CN 112881044B
- Authority
- CN
- China
- Prior art keywords
- value
- characteristic value
- variable speed
- speed device
- line
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 230000005856 abnormality Effects 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000003745 diagnosis Methods 0.000 title claims description 16
- 239000000203 mixture Substances 0.000 claims abstract description 25
- 230000002159 abnormal effect Effects 0.000 claims abstract description 24
- 238000012216 screening Methods 0.000 claims description 12
- 238000002405 diagnostic procedure Methods 0.000 claims 3
- 238000012544 monitoring process Methods 0.000 claims 1
- 238000004364 calculation method Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000000540 analysis of variance Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 239000000498 cooling water Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a method for diagnosing abnormality of variable speed equipment. The method includes a model building stage and an online operation stage. In the model building phase, first, historical operation data of the variable-rotation-speed device are acquired, and each historical operation data comprises a historical rotation speed value and a corresponding historical operation state signal. Then, a historical operating state characteristic value is calculated from the historical operating data. Next, a Gaussian mixture model is calculated from the historical operating state characteristic values. In the on-line operation stage, firstly, an on-line rotation speed value and a corresponding on-line operation state signal of the rotation speed changing equipment during on-line operation are obtained, and an on-line operation state characteristic value is calculated according to the on-line rotation speed value and the corresponding on-line operation state signal. And then judging whether the variable speed device is abnormal in on-line operation according to the Gaussian mixture model and the on-line operation state characteristic value. Thus, abnormal operation of the variable speed device can be detected efficiently.
Description
Technical Field
The invention relates to an abnormality diagnosis method for variable speed equipment.
Background
For efficient maintenance and management of equipment, a related diagnostic system is typically built to detect if an abnormality has occurred in the equipment. Generally, when a device performs on-line operation, a diagnostic system monitors the device in whole or in part to obtain signals representing the operation state of the device, and analyzes the signals to determine whether the device is abnormal. The known abnormality diagnosis method can detect abnormality relatively efficiently for a constant rotation speed device and diagnose abnormality. However, the conventional abnormality diagnosis method cannot efficiently detect the abnormality of the variable rotation speed device.
Therefore, there is a need for a method of diagnosing abnormality of a variable speed device to efficiently detect abnormal operation of the variable speed device.
Disclosure of Invention
According to an aspect of the present invention, an embodiment of the present invention provides a method for diagnosing an abnormality of a variable speed device to efficiently detect an abnormal operation of the variable speed device. The abnormal diagnosis method of the variable speed equipment comprises a model establishment stage and an online operation stage. In the abnormality diagnosis method of the variable rotation speed device, a model establishment stage is first performed. In the model building stage, firstly, a plurality of pieces of historical operation data of the variable-speed equipment are obtained, and each piece of historical operation data comprises a historical rotation speed value and a corresponding historical operation state signal. Then, a historical operating state characteristic value is calculated from the historical operating data. Next, a Gaussian mixture model is calculated from the historical operating state characteristic values. Then, an online operation phase is performed. In the on-line operation stage, firstly, on-line operation data of the variable rotation speed equipment during on-line operation is obtained, wherein the on-line operation data comprises an on-line rotation speed value and a corresponding on-line operation state signal. Then, at least one on-line operation state characteristic value is calculated according to the on-line operation data. And then judging whether the variable speed device is abnormal in on-line operation according to the Gaussian mixture model and the on-line operation state characteristic value.
In some embodiments, the historical operating state signal and the on-line operating state characteristic value are vibration signals of the variable speed device.
In some embodiments, the model building phase further includes a first regularization step to regularize the historical operating state feature values.
In some embodiments, the online job phase further includes a second regularization step to regularize the online behavior feature values.
In some embodiments, the historical operating data corresponds to the condition of normal operation of the rotating equipment.
In some embodiments, the model building stage further includes a feature screening step to remove at least one redundant feature value from the historical operating condition feature values.
In some embodiments, the aforementioned feature screening step comprises: selecting a target characteristic value, wherein the target characteristic value is one of historical operating state characteristic values; calculating an entropy (entropy) value of the target characteristic value, and judging whether the entropy value is smaller than a preset entropy threshold value or not; and when the entropy value is smaller than the preset entropy threshold value, determining the target characteristic value as at least one redundant characteristic value so as to remove the target characteristic value.
In some embodiments, the foregoing feature screening step further comprises: selecting a first target characteristic value and a second target characteristic value, wherein the first target characteristic value and the second target characteristic value are two of the historical operating state characteristic values; calculating an average correlation coefficient (correlation coefficient) between the first target feature value and the second target feature value; judging whether the average correlation coefficient is larger than a preset coefficient threshold value or not; when the average correlation coefficient is greater than a preset coefficient threshold, one of the first target feature value and the second target feature value is judged to be a redundant feature value so as to be removed.
In some embodiments, the step of determining whether the variable speed device is abnormal during the online operation according to the gaussian mixture model and the online operation state feature value includes: determining a standard boundary line according to a plurality of boundary points of the Gaussian mixture model; judging whether the on-line running state characteristic value exceeds a standard boundary line or not; when the on-line operation state characteristic value exceeds the standard boundary line, it is determined that abnormality occurs in the variable rotation speed device.
In some embodiments, the step of determining whether the variable speed device is abnormal during the on-line operation according to the gaussian mixture model and the on-line operation state characteristic value comprises: calculating weighted probability according to the Gaussian mixture model and the on-line running state characteristic value; judging whether the weighted probability is smaller than a preset probability threshold value or not; and when the weighted probability is smaller than a preset probability threshold, determining that the variable speed device is abnormal.
Drawings
The foregoing and other objects, features, advantages and embodiments of the invention will be apparent from the following detailed description of the drawings in which:
fig. 1 is a flowchart illustrating an abnormality diagnosis method of a variable speed device according to an embodiment of the present invention.
FIG. 2 is a flowchart illustrating steps for calculating a historical operating state characteristic value according to an embodiment of the invention;
FIG. 3 is a graph showing historical operating state characteristics according to an embodiment of the invention;
FIG. 4 is a diagram illustrating determining a hybrid model quantity value according to an embodiment of the invention;
FIG. 5 is a flowchart showing steps for determining whether a job of a device is abnormal according to a Gaussian mixture model according to an embodiment of the invention;
FIG. 6 is a schematic diagram showing a calculation of standard boundary lines according to an embodiment of the present invention; and
fig. 7 is a flowchart showing a step of determining whether the operation of the device is abnormal according to the gaussian mixture model according to an embodiment of the present invention.
The main reference numerals illustrate:
100-a variable speed equipment abnormality diagnosis method, 110-a model establishment stage, 111-113-steps, 112 a-112 b-steps, 120-an on-line operation stage, 121-123-steps, 123 a-123 d-steps and 123 e-123 h-steps.
Detailed Description
The following detailed description of the embodiments is provided in connection with the accompanying drawings, but the embodiments are not intended to limit the scope of the invention, and the description of the structure and operation is not intended to limit the order in which the invention may be practiced, any structure in which elements are rearranged to produce a device with equivalent efficiency, which is also within the scope of the invention. Moreover, the drawings are for illustrative purposes only and are not drawn to scale.
The terms "first," "second," …, and the like, as used herein, do not denote a particular order or sequence, but rather are merely used to distinguish one element or operation from another in the same technical terms.
Referring to fig. 1, a flow chart illustrating a method 100 for diagnosing an abnormality of a variable speed device according to an embodiment of the invention is shown. The rotational speed changing device abnormality diagnosis method 100 is applicable to devices in which rotational speed changes, such as a cooling fan of a cooling water tower or a combustion fan for blowing. The variable speed device abnormality diagnosis method 100 includes a model building stage 110 and an online operation stage 120. The model building stage 110 may collect historical operating data for the variable speed device and use the historical operating data to build a model of the device operation. In the on-line operation stage 120, when the device is on-line for operation, the foregoing model may be used to determine whether an abnormality occurs in the device.
In the model building stage 110, step 111 is first performed to obtain a plurality of historical operating data of the variable speed device. Each of the historical operating data includes a historical rotational speed value and a corresponding historical operating state signal. For example, step 111 records the operation status signals of the variable rotation speed device at different rotation speeds. The operation state signal includes, but is not limited to, a vibration signal, a sound signal, a heat signal, or the like. Taking the vibration signal as an example, step 111 records the relationship between the vibration acceleration value of the device and time (vibration signal) at a rotational speed of the device. And measuring the vibration acceleration value under a plurality of different equipment rotating speeds to obtain the historical operation data.
Next, step 112 is performed to calculate a historical operating state characteristic value from the historical operating data. In some embodiments of the present invention, the historical operating state characteristic value may be calculated according to a predetermined plurality of bandwidth ranges. Referring to fig. 2, a flow chart of step 112 according to an embodiment of the invention is shown. In step 112, step 112a is first performed to divide the historical operating state signal by a filter (e.g., a band pass/rejection filter) according to the predetermined bandwidth range. Then, step 112b is performed to calculate a historical operating state characteristic value of the historical operating state signal corresponding to each bandwidth range. In an embodiment of the present invention, the historical operating state characteristic values include, but are not limited to, mean square, root mean square, skewness, kurtosis index, skewness index, and mess (Wiener score). The specific details are shown in the following table one:
list one
In Table one above, x i Representing historical operating state signals (time domain), f i Represents the energy corresponding to the ith frequency, beta represents kurtosis, f x Representing the skewness. Further, assume that the number of signals isN, and the preset bandwidth range is: 0-1 KHz, 1-2 KHz, …, 5-6 KHz, the historical operating state characteristic values shown in FIG. 3 can be obtained, wherein the historical operating state characteristic values shown in FIG. 3 are regularized. The regularized equation is as follows:
in the above-described regularized equation,the J-th feature, μ representing the i-th data J Sum sigma J Representing the calculated mean and standard deviation for this feature, +.>Representing the regularized value. It should be noted that in other embodiments of the present invention, frequency division may not be performed. In other words, fig. 3 may have only one frequency band, i.e., the full frequency band 0-6 khz.
Referring back to fig. 1, after step 112, step 113 is performed to calculate a corresponding gaussian mixture model according to the historical operating state feature values for the bandwidth range of step 112. In order to make the gaussian mixture model approach to the distribution of data points, the mixture model quantity value M needs to be determined first. The method for determining the mixed model quantity value M is to continuously adjust the magnitude of the mixed model quantity value M, and then calculate the red well information rule (Akaike Information Criterion) or the Bayesian information rule (Bayesian information criterion; BIC) value of the Gaussian mixed model and the corresponding red well information rule. The equations for AIC and BIC are as follows:
in the above AIC value/BIC value equation, D f And N is the number of parameters (Free parameters) and the number of data points of a single gaussian distribution respectively,which is representative of the data point, S i Represents the rotational speed, i=1 to N, μ m Representing a gaussian distribution center, Σ m Represents a matrix of covariates, pi m Representing the pi-related coefficients. The mahalanobis distance between the data point and the center of the gaussian distribution is expressed as follows:
as shown in fig. 4, after the AIC value/BIC value curve is calculated, a straight line is taken between the head and the tail of the AIC value/BIC value curve, and then a point (i.e., a curve inflection point) farthest from the straight line on the curve is found, so that the value of the mixed model quantity value M can be determined. In the embodiment of fig. 4, the hybrid model quantity value M is determined to be 6.
Additionally, in some embodiments of the present invention, a feature screening step may be performed between steps 112 and 113 to remove unwanted redundant feature values. In some embodiments of the present invention, the aforementioned historical operating data are all data of normal operation of the device, and the feature filtering step may be performed as follows: firstly, selecting a target characteristic value to be processed from the historical operating state characteristic values. Then, an entropy (entropy) value of the target feature value is calculated, and whether the entropy value is smaller than a preset entropy threshold value is judged. In the present embodiment, the preset entropy threshold is 0.5, but embodiments of the present invention are not limited thereto. And when the entropy value is smaller than the preset entropy threshold value, judging the target characteristic value as a redundant characteristic value, and removing the target characteristic value.
In some embodiments of the invention, the relationship between any two eigenvalues can be confirmed again by averaging the correlation coefficients (correlation coefficient). Specifically, first, a first target characteristic value and a second target characteristic value are arbitrarily selected from the historical operating state characteristic values, and an average correlation coefficient between the first target characteristic value and the second target characteristic value is calculated. Then judging whether the average correlation coefficient is larger than a preset coefficient threshold value. When the average correlation coefficient is larger than a preset coefficient threshold value, one of the first target characteristic value and the second target characteristic value is judged to be a redundant characteristic value, and the redundant characteristic value is removed.
In some embodiments of the present invention, the feature screening step may use a variance analysis (Analysis of variance; ANOVA) or mutual information (Mutual Information; MI) to determine the discriminatory feature values and remove other redundant feature values without discriminatory power.
Returning to FIG. 1, after the modeling stage 110, an in-line operation stage 120 follows. In the on-line operation stage 120, step 121 is first performed to obtain on-line operation data of the variable rotation device during on-line operation. The on-line operation data includes an on-line rotational speed value and a corresponding on-line operation status signal. Then, step 122 is performed to calculate an on-line operation state characteristic value according to the on-line operation data. Since step 122 is similar to step 112 described above, no further description is provided herein. Then, step 123 is performed to determine whether an abnormality occurs in the variable speed device during online operation according to the gaussian mixture model and the online operation state feature value.
Fig. 5 is a flowchart illustrating a step 123 according to an embodiment of the invention. In step 123, step 123a is first performed to determine a standard boundary line from a plurality of boundary points of the gaussian mixture model. In this embodiment, step 123 is to determine the boundary line between the normal condition and the abnormal condition (i.e., the standard boundary line described above). For example, as shown in fig. 6, the boundary points of the gaussian model are connected and the outermost points are retained to obtain the normal upper boundary by the calculation method of the boundary with the mahalanobis distance of 2. This normal upper boundary may be referred to as the standard boundary line. Next, step 123b is performed to determine whether the on-line operation state characteristic value exceeds the standard boundary line. If the on-line operation state characteristic value exceeds the standard boundary line, step 123c is performed to determine that the operation of the variable speed device is abnormal. For example, when the single on-line operation state characteristic value exceeds this standard boundary line, it is possible to determine that abnormality occurs in the apparatus. If the operation is not completed, the process proceeds to step 123d, where it is determined that the operation of the device is normal. In addition, considering that the number of boundary points may be too large, a standard boundary line may be obtained using a smooth curve method (Spline) or a polygon method (polygon).
Fig. 7 is a flowchart illustrating a step 123 according to another embodiment of the invention. In this embodiment, step 123 is to use the weighted probability to determine whether the device is abnormal. In step 123 of the present embodiment, step 123e is first performed to calculate the weighted probability according to the gaussian mixture model and the on-line running state feature value. The calculation equation of the weighted probability P is as follows:
then, step 123f is performed to determine whether the weighted probability is smaller than a predetermined probability threshold. In the present embodiment, the preset probability threshold is 0.5, but the embodiment of the invention is not limited thereto. When the weighted probability is smaller than the preset probability threshold, step 123g is performed to determine that the operation of the variable speed device is abnormal. If not, step 123h is performed to determine that the operation of the variable speed device is normal.
In some embodiments, the weighted probabilities may be used to determine whether an abnormality occurs in the operation of the variable speed device using multiple indicators (eigenvalues) at the same time. Taking step 123 shown in fig. 7 as an example, when step 123 shown in fig. 7 employs a plurality of indexes to determine whether the operation of the variable speed device is abnormal, the predetermined probability threshold may be 0.01, and the characteristic value is the sameWherein w is the rotational speedThe weight, the value of which is consistent with that when the Gaussian mixture model is built.
As can be seen from the above description, the abnormality diagnosis method for the variable speed device according to the embodiment of the invention uses the gaussian mixture model to determine whether the variable speed device is abnormal. The embodiment of the invention provides different characteristic screening steps aiming at different historical operation data. For example, if the historical operating data only includes data of normal operation of the variable rotation speed device, the entropy value or the average correlation coefficient may be used to perform feature screening. For example, if the historical operation data includes data of normal and abnormal operation of the variable speed device, the characteristic may be selected by a variance analysis method or a mutual information method. In addition, in some embodiments of the present invention, the feature screening step is not limited to screening features, but may be performed with respect to other descriptors (e.g., frequency bands).
While the present invention has been described with reference to several embodiments, it should be understood that the invention is not limited thereto, but may be modified or altered in various ways without departing from the spirit and scope of the invention.
Claims (9)
1. A variable speed device abnormality diagnosis method for monitoring a variable speed device, characterized by comprising:
the model building stage comprises the following steps:
acquiring a plurality of history operation data of the variable speed equipment, wherein each history operation data comprises a history rotation speed value and a corresponding history operation state signal, and the history operation data are all data of normal operation of the variable speed equipment;
calculating a plurality of historical operating state feature values according to the plurality of historical operating data; and
calculating a Gaussian mixture model according to the plurality of historical operating state characteristic values; and performing an online operation phase comprising:
acquiring online operation data of the variable speed device during online operation, wherein the online operation data comprises an online rotation speed value and a corresponding online operation state signal;
calculating at least one on-line operating state characteristic value according to the on-line operating data; and
judging whether the variable speed device is abnormal in online operation or not according to the standard boundary line or the weighted probability of the Gaussian mixture model and the at least one online operation state characteristic value;
wherein the step of calculating the gaussian mixture model from the plurality of historical operating state characteristic values comprises:
calculating a red well information rule value curve or a Bayesian information rule value curve according to the plurality of historical operating state characteristic values;
finding out a curve inflection point of the red well information rule value curve or the Bayesian information rule Bayesian value curve; and
and determining a mixed model quantity value of the Gaussian mixed model according to the curve inflection point.
2. The abnormality diagnosis method of a variable speed device according to claim 1, wherein the historical operating state signal and the on-line operating state characteristic value are vibration signals of the variable speed device.
3. The variable speed device anomaly diagnostic method of claim 1, wherein the model building stage further comprises a first regularization step to regularize the plurality of historical operating state feature values.
4. A variable speed device anomaly diagnostic method as claimed in claim 3 wherein the online working phase further comprises a second regularization step to regularize the at least one online operational state characteristic value.
5. The variable speed device anomaly diagnostic method of claim 1, wherein the modeling stage further comprises a feature screening step to remove at least one redundant feature value from the historical operating condition feature values.
6. The variable speed device abnormality diagnosis method according to claim 5, characterized in that the feature screening step includes:
selecting a target feature value, wherein the target feature value is one of the plurality of historical operating state feature values:
calculating the entropy value of the target characteristic value, and judging whether the entropy value is smaller than a preset entropy threshold value or not; and
and when the entropy value is smaller than the preset entropy threshold value, judging the target characteristic value as the at least one redundant characteristic value so as to remove the target characteristic value.
7. The variable speed device abnormality diagnosis method according to claim 6, characterized in that the feature screening step further comprises:
selecting a first target characteristic value and a second target characteristic value, wherein the first target characteristic value and the second target characteristic value are two of the plurality of historical operating state characteristic values;
calculating an average correlation coefficient between the first target characteristic value and the second target characteristic value;
judging whether the average correlation coefficient is larger than a preset coefficient threshold value or not; and
and when the average correlation coefficient is greater than the preset coefficient threshold value, determining that one of the first target characteristic value and the second target characteristic value is the at least one redundant characteristic value, so as to remove the at least one redundant characteristic value.
8. The method of diagnosing an abnormality of a variable speed device according to claim 1, wherein the step of determining whether the variable speed device is abnormal when operating on line based on the gaussian mixture model and the at least one on-line operation state characteristic value comprises:
determining the standard boundary line according to a plurality of boundary points of the Gaussian mixture model;
judging whether the at least one on-line running state characteristic value exceeds the standard boundary line; and
and when the at least one on-line operation state characteristic value exceeds the standard boundary line, determining that the variable speed device is abnormal.
9. The method of diagnosing an abnormality of a variable speed device according to claim 1, wherein the step of determining whether the variable speed device is abnormal when operating on line based on the gaussian mixture model and the at least one on-line operation state characteristic value comprises:
calculating the weighted probability according to the Gaussian mixture model and the at least one on-line running state characteristic value;
judging whether the weighted probability is smaller than a preset probability threshold; and
and when the weighted probability is smaller than the preset probability threshold, judging that the variable speed device is abnormal.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW108143789 | 2019-11-29 | ||
TW108143789A TWI749416B (en) | 2019-11-29 | 2019-11-29 | Method for diagnosing abnormality of equipment having variable rotation speeds |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112881044A CN112881044A (en) | 2021-06-01 |
CN112881044B true CN112881044B (en) | 2024-02-06 |
Family
ID=76042882
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010546081.0A Active CN112881044B (en) | 2019-11-29 | 2020-06-16 | Abnormality diagnosis method for variable rotation speed equipment |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112881044B (en) |
TW (1) | TWI749416B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI819824B (en) * | 2022-09-30 | 2023-10-21 | 中國鋼鐵股份有限公司 | Method for applying different rotation-speed-vibration thresholds to diagnose abnormality of equipment with variable rotation speeds |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06307921A (en) * | 1993-04-27 | 1994-11-04 | Toshiba Corp | Diagnostic monitoring system for rotating machine |
CN102768115A (en) * | 2012-06-27 | 2012-11-07 | 华北电力大学 | Method for dynamically monitoring health status of wind turbine gearbox in real time |
CN107341349A (en) * | 2017-06-30 | 2017-11-10 | 上海交通大学 | Method, system, memory and the controller of blower fan health evaluating |
CN109909803A (en) * | 2019-04-17 | 2019-06-21 | 北京天泽智云科技有限公司 | A kind of machine tool chief axis method for detecting abnormality |
CN110222980A (en) * | 2019-06-05 | 2019-09-10 | 上海电气集团股份有限公司 | The health evaluating method and system of rail traffic bearing |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008081419A2 (en) * | 2006-12-28 | 2008-07-10 | Optimaltest Ltd. | Systems and methods for test time outlier detection and correction in integrated circuit testing |
TW201231330A (en) * | 2011-01-19 | 2012-08-01 | rong-zhong Chen | Vehicle engine operation status monitoring and adjusting method |
TWI579549B (en) * | 2012-07-23 | 2017-04-21 | rong-zhong Chen | Monitoring the operation of the vehicle |
CN103758696B (en) * | 2014-01-09 | 2016-05-25 | 华北电力大学 | Aerogenerator unit safe status evaluation method based on SCADA temperature parameter |
CN107526667B (en) * | 2017-07-28 | 2020-04-28 | 阿里巴巴集团控股有限公司 | Index abnormality detection method and device and electronic equipment |
TWI669606B (en) * | 2017-11-20 | 2019-08-21 | 財團法人資訊工業策進會 | Diagnostic method for machine and diagnostic system thereof |
CN110110160B (en) * | 2017-12-29 | 2020-04-14 | 阿里巴巴集团控股有限公司 | Method and device for determining data exception |
-
2019
- 2019-11-29 TW TW108143789A patent/TWI749416B/en active
-
2020
- 2020-06-16 CN CN202010546081.0A patent/CN112881044B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06307921A (en) * | 1993-04-27 | 1994-11-04 | Toshiba Corp | Diagnostic monitoring system for rotating machine |
CN102768115A (en) * | 2012-06-27 | 2012-11-07 | 华北电力大学 | Method for dynamically monitoring health status of wind turbine gearbox in real time |
CN107341349A (en) * | 2017-06-30 | 2017-11-10 | 上海交通大学 | Method, system, memory and the controller of blower fan health evaluating |
CN109909803A (en) * | 2019-04-17 | 2019-06-21 | 北京天泽智云科技有限公司 | A kind of machine tool chief axis method for detecting abnormality |
CN110222980A (en) * | 2019-06-05 | 2019-09-10 | 上海电气集团股份有限公司 | The health evaluating method and system of rail traffic bearing |
Also Published As
Publication number | Publication date |
---|---|
TWI749416B (en) | 2021-12-11 |
TW202121093A (en) | 2021-06-01 |
CN112881044A (en) | 2021-06-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107560849B (en) | Wind turbine generator bearing fault diagnosis method of multichannel deep convolutional neural network | |
CN110276416B (en) | Rolling bearing fault prediction method | |
CN108334059B (en) | Particle swarm optimization-based BP neural network model fault diagnosis method | |
CN110647943B (en) | Cutting tool wear monitoring method based on evolution data cluster analysis | |
CN107609574A (en) | Wind turbines fault early warning method based on data mining | |
CN112418277A (en) | Method, system, medium, and apparatus for predicting remaining life of rotating machine component | |
CN111597651A (en) | Rolling bearing performance degradation evaluation method based on HWPSO-SVDD model | |
CN108204341B (en) | method and device for identifying operating state of wind power plant | |
CN116311594B (en) | Ship subsystem state analysis method, device and storage medium | |
CN112881044B (en) | Abnormality diagnosis method for variable rotation speed equipment | |
CN111125895B (en) | On-line assessment method for service power characteristics of complete wind driven generator | |
CN112459971A (en) | Abnormal vibration detection method for tower of wind generating set | |
CN109855873B (en) | Fault diagnosis method and device for turbine main shaft | |
CN112326241B (en) | Nuclear power main pump bearing fault early warning method based on fusion degradation index | |
CN112633098A (en) | Fault diagnosis method and system for rotary machine and storage medium | |
CN108492026B (en) | Soft measurement method based on integrated orthogonal component optimization regression analysis | |
CN110597232A (en) | Frequency converter cooling water pump fault alarm method based on dynamic confidence rule base | |
CN104111109B (en) | A kind of vibration condition recognition methods based on different order statistic and support vector machine | |
CN115374653B (en) | NSET model-based wind driven generator temperature early warning method and related device | |
Zhang et al. | Gearbox health condition identification by neuro-fuzzy ensemble | |
CN116862284A (en) | Marine diesel engine health state assessment method based on SOM network and rule fusion | |
TWI819824B (en) | Method for applying different rotation-speed-vibration thresholds to diagnose abnormality of equipment with variable rotation speeds | |
TW202416067A (en) | Method for applying different rotation-speed-vibration thresholds to diagnose abnormality of equipment with variable rotation speeds | |
CN111400959B (en) | Blade fault diagnosis method and device for wind generating set | |
WO2004072858A1 (en) | Condition identifying metod and condition identifying system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |