CN113688791B - Method for identifying CMS abnormal data packet of wind turbine generator - Google Patents
Method for identifying CMS abnormal data packet of wind turbine generator Download PDFInfo
- Publication number
- CN113688791B CN113688791B CN202111106148.XA CN202111106148A CN113688791B CN 113688791 B CN113688791 B CN 113688791B CN 202111106148 A CN202111106148 A CN 202111106148A CN 113688791 B CN113688791 B CN 113688791B
- Authority
- CN
- China
- Prior art keywords
- data
- data packet
- abnormal
- value
- threshold
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000001514 detection method Methods 0.000 claims abstract description 39
- 230000035772 mutation Effects 0.000 claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims description 19
- 230000005856 abnormality Effects 0.000 claims description 10
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 238000007689 inspection Methods 0.000 abstract description 3
- 239000000306 component Substances 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000003862 health status Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/17—Function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Abstract
The invention discloses a method for identifying CMS abnormal data packets of a wind turbine generator, which establishes an abnormal data packet inspection and identification algorithm by carrying out amplitude over-low abnormal detection, zero drift abnormal detection, positive and negative data unbalance abnormal detection, data flashover abnormal detection, data mutation abnormal detection, singular value abnormal detection and multipoint repeated abnormal detection on each data packet, and automatically eliminates the abnormal data packet. The method has the technical advantages that vibration data packets under various abnormal conditions caused by abnormal sensors, abnormal acquisition devices, abnormal network output, external environment interference, yaw, pitch change and the like of the wind turbine generator can be automatically identified from mass CMS data, abnormal data and fault data can be automatically distinguished, the fault data are saved while the abnormal interference data are removed, the loss of the fault data is avoided, and a high-quality data sample is provided for fault diagnosis based on the CMS data.
Description
Technical Field
The invention belongs to the field of data anomaly detection, relates to an anomaly data detection method, and particularly relates to a method for identifying CMS anomaly data packets of a wind turbine generator.
Background
At present, the wind turbine generator is provided with a state monitoring system, which is called CMS for short. The CMS monitors the wind turbine generator components in real time mainly by additionally arranging vibration sensors and rotation speed sensors on the components such as a bearing, a gear box and a generator of the wind turbine generator, and can identify the health status of each core component of the wind turbine generator and the whole health status of the wind turbine generator by analyzing vibration data, and according to a reasonable An Paiyun-dimensional plan of the health status of the components, the defects of over-maintenance and under-maintenance of the traditional operation and maintenance mode are avoided. In practice, the quality of vibration data is directly related to whether the monitoring result is reliable or not. The abnormal vibration data is used for evaluating the state of the unit, so that the health state of the unit cannot be identified, even the false alarm fault of the monitoring system can be caused sometimes, the application experience of the vibration monitoring system in preventive maintenance of the wind turbine is seriously affected, and great trouble is brought to operation and maintenance personnel. The CMS data often has anomalies in the vibration data due to sensor damage, sensor drop, network transmission anomalies, edge data acquisition hardware defects, and the like.
In order to improve the accuracy and efficiency of fault diagnosis based on CMS data, before performing time domain, frequency domain and time-frequency domain analysis on the CMS data, it is first required to determine whether the CMS data packet is an abnormal data packet, that is, detect the quality of the CMS data packet, and analyze whether the CMS data packet has abnormal conditions such as zero drift, data interruption, data mutation, imbalance of positive and negative data, etc. If the abnormality exists, the CMS data packet is an abnormal data packet, and is rejected, so that the workload of vibration analysis and false alarm faults caused by the workload are reduced. The traditional method for detecting the data quality mainly comprises methods such as unbalance analysis, periodicity inspection, AR model prediction and the like, but the methods are not suitable for abnormal detection of CMS data, because the CMS data are non-stable data, the data fluctuation is large, the periodicity of vibration data and the data distribution characteristic of the component can be changed when different types of faults occur, the component cannot be detected by single data stationarity, periodicity and normal property, and the future value of the component cannot be accurately predicted by using an AR model. In addition, although the detection of anomalies in data quality by differential methods, correlation analysis methods, multiple sensor comparison analysis methods, spectrum analysis methods, and the like is also practically applied, the above methods are not well suited for the detection of anomalies in vibration data due to the characteristics of small correlation of vibration data, rapid data change, impact of the data itself, complex frequency components, and the like.
From the analysis, the prior art has poor applicability to abnormal detection of CMS data, can not effectively identify abnormal conditions such as zero drift, data interruption, data mutation, imbalance of positive and negative data and the like from complex vibration data, and can not meet the quality abnormal detection requirement of monitoring data of a CMS system of a wind turbine generator.
Disclosure of Invention
In order to solve the problems in the prior art, the invention aims to provide a method for identifying CMS abnormal data packets of a wind turbine generator, which establishes an abnormal data packet inspection and identification algorithm by carrying out amplitude over-low abnormal detection, zero drift abnormal detection, positive and negative data unbalance abnormal detection, data flashover abnormal detection, data mutation abnormal detection, singular value abnormal detection and multipoint repeated abnormal detection on each data packet, and automatically eliminates the abnormal data packet.
In order to achieve the above purpose, the invention adopts the technical proposal that,
the method for identifying the abnormal data packet of the CMS of the wind turbine generator comprises the steps of carrying out amplitude over-low abnormality detection, zero drift abnormality detection, positive and negative data unbalance abnormality detection, data flashover abnormality detection, data mutation abnormality detection, singular value abnormality detection and multipoint repeated abnormality detection on each data packet, judging whether the data packet is an abnormal data packet according to a detection result, and carrying out automatic identification and rejection on the abnormal data packet, and specifically comprises the following steps of:
1) Collecting CMS data of the wind turbine generator to obtain vibration data packets D= { x of each measuring point 1 ,x 2 ,…,x n For each vibration data packet, finding out all wave crest data and wave trough data in the vibration data packet;
2) Calculating the average value of the wave peak data in each vibration data packetMean value>
3) Setting a peak data effective value threshold A + And trough data effective value thresholdThe first abnormality judgment is carried out on the vibration data packet, and the method comprises the following steps:
(1) If the average value of the peak dataLess than or equal to the peak data effective value threshold A + Or mean value of trough data +.>Greater than or equal to the trough data effective value threshold A - The data packet is an abnormal data packet, and the data packet is not stored and analyzed;
(2) If the average value of the peak dataGreater than the peak data effective value threshold A + And mean value of trough data +.>Less than the trough data effective value threshold A - Then the next analysis and judgment are carried out;
4) Dividing a vibration data packet into equal parts a, wherein a is a configurable parameter, and calculating the number Np of data greater than 0 and the number Nn of data less than 0 for each equal part of data;
5) Calculating the difference rate of the number Np of data greater than 0 and the number Nn of data less than 0 in each equal part of data:
wherein: r (i) is the difference rate between Np and Nn in the ith aliquot; t is the number of data points in each data;
6) The absolute value of the mean of each aliquot was calculated:
wherein:absolute value of mean value of the ith aliquot data; x is x j Is the data in the vibration data packet;
7) Finding the maximum value r of the difference rate according to the difference rate and the absolute value of the mean value of each equal part of the data calculated in the step 5) and the step 6) max Maximum value of absolute value of sum means
8) Setting a difference rate threshold r * And absolute value threshold of mean valueAnd performing second abnormal judgment on the vibration data packet, wherein the second abnormal judgment comprises the following steps of:
(1) If the maximum value r of the difference rate max Greater than or equal to the difference rate threshold r * Or the maximum value of the absolute value of the meanAbsolute value threshold greater than or equal to the mean +.>The data packet is an abnormal data packet, and the data packet is not stored and analyzed;
(2) If the maximum value r of the difference rate max Less than the difference rate threshold r * And the maximum value of the absolute value of the mean valueAbsolute value threshold value less than the mean value +.>Then the next analysis and judgment are carried out;
9) The root mean square value of each aliquot, i.e., the effective value of each aliquot, is calculated:
wherein: x is X rms (i) Is the effective value of the ith equal part data;
10 Based on the a effective values calculated in step 9), find the maximum value among the effective valuesAnd minimum value
11 A valid value fluctuation threshold f is set, and the vibration data packet is analyzed and judged for the third time, comprising the following steps:
(1) If the maximum value of the effective valueGreater than or equal to the minimum value->F times, the data packet is an abnormal data packet, and the data packet is not stored and analyzed;
(2) If the maximum value of the effective valueLess than the minimum->F times of the number, then carrying out the next analysis and judgment;
12 Finding the maximum value x of all absolute values of data in the vibration data packet max ；
13 Calculating the mutation coefficient of the vibration data packet:
wherein: k is the mutation coefficient of the vibration data packet;
14 Setting a mutation coefficient threshold k of the vibration data packet max And carrying out fourth analysis and judgment on the vibration data packet, wherein the fourth analysis and judgment comprises the following steps of:
(1) If the mutation coefficient k of the vibration data packet is greater than or equal to the mutation coefficient threshold k max The data packet is an abnormal data packet, and the data packet is not stored and analyzed;
(2) If the mutation coefficient k of the vibration data packet is smaller than the mutation coefficient threshold k max Then the next analysis and judgment are carried out;
15 Differential operation of the vibration data packet):
D diff ＝{(x 2 -x 1 ),(x 3 -x 2 ),…,(x n -x n-1 )}
wherein: d (D) diff The data packet is obtained after differential operation;
16 Finding the number of data equal to 0 in the data packet after the differential operation:
wherein: n (N) 0 The number of data equal to 0 in the data packet after the difference operation;
17 Setting the multipoint repetition threshold N 0max The fifth analysis and judgment are carried out on the vibration data packet, and the method comprises the following steps:
(1) If the number N of data equal to 0 in the data packet 0 Greater than or equal to the multipoint repetition threshold N 0max The data packet is an abnormal data packet, and the data packet is not stored and analyzed;
(2) If the number N of the repeated points in the data packet 0 Less than the multiple point repetition threshold N 0max Number of timesThe data packet is normal data, and the data packet is stored.
The CMS abnormal data packet refers to abnormal vibration data caused by abnormal sensor, abnormal acquisition device, abnormal network output, external environment interference and yaw and pitch variation of the wind turbine, and the normal data packet refers to vibration data acquired by the sensor in a normal state, including vibration data in a normal running state of the wind turbine and vibration data in a fault running state of the wind turbine.
The peak data effective value threshold A + And trough data effective value threshold A - The value of (A) is A + ＝1、A - -1; difference rate threshold r * =0.5; threshold of absolute valueThe effective value fluctuation threshold f=2; mutation coefficient threshold value k max =25; multiple point repetition threshold N 0max =0.1n, n is the number of data points in packet D.
Compared with the existing data quality anomaly detection method, the invention provides a method for identifying the CMS anomaly data packet of the wind turbine, which has the technical advantages that the method can automatically identify vibration data packets under various anomaly conditions caused by sensor anomalies, acquisition device anomalies, network output anomalies, external environment interference, yaw, pitch and the like of the wind turbine from massive CMS data, can automatically distinguish the anomaly data and fault data, can save the fault data while eliminating the anomaly interference data, avoid the loss of the fault data, and provide high-quality data samples for fault diagnosis based on the CMS data.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is further illustrated by the following description in conjunction with specific embodiments and the accompanying drawings.
As shown in fig. 1, in the method for identifying the CMS abnormal data packet of the wind turbine, d= { x is set 1 ,x 2 ,…,x n Is one data within a sampling periodA packet, wherein x i I=1, 2, …, n, waveform data of the data packet, and anomaly detection of the data packet D includes the steps of:
(1) Find waveform data (x 1 ,x 2 ,…,x n ) All peak data in (a)
Wherein,the j-th peak data in the waveform data; k is the number of peak data.
(2) Find waveform data (x 1 ,x 2 ,…,x n ) All trough data in (1)
Wherein,is the j-th trough data in the waveform data.
(3) Calculating the average value of the peak data
(4) Calculating the mean value of trough data
(5) Setting a peak data effective value threshold A + And trough data effective value threshold A - For example A + ＝1、A - = -1 ifOr->The data packet D is abnormal data of the sensor, the data packet is not stored and analyzed, and the calculation is stopped; otherwise, i.e.)>And->Turning to the step (6);
(6) Dividing the data packet D into equal parts a, configuring the parameter a, and calculating the number N of data greater than 0 in each equal part p And a number N of data smaller than 0 n ：
(7) In each aliquot, N is calculated p And N n Absolute value of the difference ratio and the mean:
(8) Finding the maximum sum of r (i) in all aliquotsIs the maximum value of (2):
(9) Setting a difference rate threshold r * ，r * For configurable parameters, e.g. r * =0.5, and absolute value threshold of mean valueFor configurable parameters, e.g.>If r max ≥r * Or->The data packet D is abnormal data of the sensor, the data packet is not stored and analyzed, and the calculation is stopped; otherwise turning to step (10);
(10) Dividing the data packet D into a equal parts, and calculating the root mean square value of each equal part data, namely the effective value of each equal part data:
(11) Finding a root mean square value data X rms (i) Maximum and minimum values of (a)
(12) Such asFruit setThe data packet D is abnormal data of the sensor, and the data packet is not stored and analyzed; otherwise, turning to step (13);
(13) Finding the maximum value of all absolute values of data in the data packet D:
(14) Calculating the mutation coefficient of the data packet D:
(15) Setting a mutation coefficient threshold k max ，k max For configurable parameters, e.g. k max =25, if k+_k max The data packet D is abnormal data of the sensor, the data packet is not stored and analyzed, and the calculation is stopped; otherwise, turning to step (16);
(16) Performing differential operation on the data packet D:
D diff ＝{(x 2 -x 1 ),(x 3 -x 2 ),…,(x n -x n-1 )}
(17) Find D diff Number of data equal to 0:
(18) Setting a multipoint repetition threshold N 0max ，N 0max For configurable parameters, e.g. N 0max =0.1n, N is the number of data points in packet D, if N 0 ≥N 0max The data packet D is abnormal data of the sensor, the data packet is not stored and analyzed, and the calculation is stopped; otherwise, the data packet D is normal data, the data packet D is stored, and the calculation is stopped.
Claims (3)
1. The method is characterized by comprising the steps of carrying out amplitude over-low anomaly detection, zero drift anomaly detection, positive and negative data unbalance anomaly detection, data flash anomaly detection, data mutation anomaly detection, singular value anomaly detection and multipoint repeated anomaly detection on each data packet, judging whether the data packet is an anomaly data packet according to a detection result, and carrying out automatic identification and rejection on the anomaly data packet, and specifically comprises the following steps of:
1) Collecting CMS data of the wind turbine generator to obtain vibration data packets D= { x of each measuring point 1 ,x 2 ,…,x n For each vibration data packet, finding out all wave crest data and wave trough data in the vibration data packet;
2) Calculating the average value of the wave peak data in each vibration data packetMean value>
3) Setting a peak data effective value threshold A + And trough data effective value threshold A - The first abnormality judgment is carried out on the vibration data packet, and the method comprises the following steps:
(1) If the average value of the peak dataLess than or equal to the peak data effective value threshold A + Or mean value of trough data +.>Greater than or equal to the trough data effective value threshold A - The data packet is an abnormal data packet, and the data packet is not stored and analyzed;
(2) If the average value of the peak dataGreater than the peak data effective value threshold A + And mean value of trough data +.>Less than the trough data effective value threshold A - Then the next analysis and judgment are carried out;
4) Dividing a vibration data packet into equal parts a, wherein a is a configurable parameter, and calculating the number Np of data greater than 0 and the number Nn of data less than 0 for each equal part of data;
5) Calculating the difference rate of the number Np of data greater than 0 and the number Nn of data less than 0 in each equal part of data:
wherein: r (i) is the difference rate between Np and Nn in the ith aliquot; t is the number of data points in each data;
6) The absolute value of the mean of each aliquot was calculated:
wherein:absolute value of mean value of the ith aliquot data; x is x j Is the data in the vibration data packet;
7) Finding the maximum value r of the difference rate according to the difference rate and the absolute value of the mean value of each equal part of the data calculated in the step 5) and the step 6) max Maximum value of absolute value of sum means
8) Setting a difference rate threshold r * And absolute value threshold of mean valueAnd performing second abnormal judgment on the vibration data packet, wherein the second abnormal judgment comprises the following steps of:
(1) If the maximum value r of the difference rate max Greater than or equal to the difference rate threshold r * Or the maximum value of the absolute value of the meanAbsolute value threshold greater than or equal to the mean +.>The data packet is an abnormal data packet, and the data packet is not stored and analyzed;
(2) If the maximum value r of the difference rate max Less than the difference rate threshold r * And the maximum value of the absolute value of the mean valueAbsolute value threshold value less than the mean value +.>Then the next analysis and judgment are carried out;
9) The root mean square value of each aliquot, i.e., the effective value of each aliquot, is calculated:
wherein: x is X rms (i) Is the effective value of the ith equal part data;
10 Based on the a effective values calculated in step 9), find the maximum value among the effective valuesAnd minimum->
11 A valid value fluctuation threshold f is set, and the vibration data packet is analyzed and judged for the third time, comprising the following steps:
(1) If the maximum value of the effective valueGreater than or equal to the minimum value->F times, the data packet is an abnormal data packet, and the data packet is not stored and analyzed;
(2) If the maximum value of the effective valueLess than the minimum->F times of the number, then carrying out the next analysis and judgment;
12 Finding the maximum value x of all absolute values of data in the vibration data packet max ；
13 Calculating the mutation coefficient of the vibration data packet:
wherein: k is the mutation coefficient of the vibration data packet;
14 Setting a mutation coefficient threshold k of the vibration data packet max And carrying out fourth analysis and judgment on the vibration data packet, wherein the fourth analysis and judgment comprises the following steps of:
(1) If the mutation coefficient k of the vibration data packet is greater than or equal to the mutation coefficient threshold k max The data packet is an abnormal data packet, and the data packet is not stored and analyzed;
(2) If the mutation coefficient k of the vibration data packet is smaller than the mutation coefficient threshold k max Then the next analysis and judgment are carried out;
15 Differential operation of the vibration data packet):
D diff ＝{(x 2 -x 1 ),(x 3 -x 2 ),…,(x n -x n-1 )}
wherein: d (D) diff The data packet is obtained after differential operation;
16 Finding the number of data equal to 0 in the data packet after the differential operation:
wherein: n (N) 0 The number of data equal to 0 in the data packet after the difference operation;
17 Setting the multipoint repetition threshold N 0max The fifth analysis and judgment are carried out on the vibration data packet, and the method comprises the following steps:
(1) If the number N of data equal to 0 in the data packet 0 Greater than or equal to the multipoint repetition threshold N 0max The data packet is an abnormal data packet, and the data packet is not stored and analyzed;
(2) If the number N of the repeated points in the data packet 0 Less than the multiple point repetition threshold N 0max The data packet is normal data, and the data packet is stored.
2. The method for identifying the abnormal data packet of the CMS of the wind turbine generator according to claim 1, wherein the abnormal data packet of the CMS refers to abnormal vibration data caused by abnormal sensor, abnormal acquisition device, abnormal network output, external environment interference and yaw and pitch of the wind turbine generator, and the normal data packet refers to vibration data acquired by the sensor in a normal state, and the normal data packet includes vibration data in a normal operation state of the wind turbine generator and vibration data in a fault operation state of the wind turbine generator.
3. The method for identifying CMS abnormal data packets of a wind turbine generator according to claim 1, wherein the peak data effective value threshold A + And trough data effective value threshold A - The value of (A) is A + ＝1、A - -1; difference rate threshold r * =0.5; threshold of absolute valueThe effective value fluctuation threshold f=2; mutation coefficient threshold value k max =25; multiple point repetition threshold N 0max =0.1n, n is the number of data points in packet D.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111106148.XA CN113688791B (en) | 2021-09-22 | 2021-09-22 | Method for identifying CMS abnormal data packet of wind turbine generator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111106148.XA CN113688791B (en) | 2021-09-22 | 2021-09-22 | Method for identifying CMS abnormal data packet of wind turbine generator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113688791A CN113688791A (en) | 2021-11-23 |
| CN113688791B true CN113688791B (en) | 2024-03-01 |
Family
ID=78587011
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111106148.XA Active CN113688791B (en) | 2021-09-22 | 2021-09-22 | Method for identifying CMS abnormal data packet of wind turbine generator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113688791B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116503384B (en) * | 2023-06-21 | 2023-12-29 | 惠州市金思维科技有限公司 | Method and system for rapidly extracting lead screw defect area based on computer vision |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017159784A1 (en) * | 2016-03-17 | 2017-09-21 | Ntn株式会社 | Condition monitoring system and wind power generation device |
| CN110674891A (en) * | 2019-10-16 | 2020-01-10 | 北京天泽智云科技有限公司 | Data quality abnormity detection method for monitoring system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3082330B1 (en) * | 2018-06-07 | 2022-12-30 | Thales Sa | AERONAUTICAL CYBERSECURITY |
-
2021
- 2021-09-22 CN CN202111106148.XA patent/CN113688791B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017159784A1 (en) * | 2016-03-17 | 2017-09-21 | Ntn株式会社 | Condition monitoring system and wind power generation device |
| CN110674891A (en) * | 2019-10-16 | 2020-01-10 | 北京天泽智云科技有限公司 | Data quality abnormity detection method for monitoring system |
Non-Patent Citations (1)
| Title |
|---|
| 基于健康样本的风电机组状态评估与异常检测系统;安学利;唐拥军;吴光军;陈海元;;大电机技术;20150315(02);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113688791A (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2868921B1 (en) | Wind turbine and method for evaluating health state of blade thereof | |
| CN107016235B (en) | Equipment running state health degree evaluation method based on multi-feature adaptive fusion | |
| CN110674891B (en) | Data quality abnormity detection method for monitoring system | |
| CN102706560B (en) | The state monitoring method and device of a kind of wind power generating set | |
| CN111504645B (en) | Rolling bearing fault diagnosis method based on frequency domain multipoint kurtosis | |
| CN111922095A (en) | Vibration diagnosis method for abnormal torsional vibration fault of roller of cold rolling mill | |
| CN107844067B (en) | A kind of gate of hydropower station on-line condition monitoring control method and monitoring system | |
| CN113688791B (en) | Method for identifying CMS abnormal data packet of wind turbine generator | |
| CN115935243B (en) | Fault analysis method based on data processing | |
| CN103941722A (en) | Method monitoring and diagnosing equipment failure through component characteristic frequency multiplication amplitude trend | |
| CN108844612A (en) | A kind of identification method of transformer internal faults based on mathematical statistics probabilistic model | |
| CN110578659B (en) | System and method for processing SCADA data of wind turbine generator | |
| CN117233541B (en) | Power distribution network power line running state measurement method and measurement system | |
| CN207992717U (en) | A kind of gate of hydropower station on-line condition monitoring system | |
| CN116593829B (en) | Transmission line hidden danger on-line monitoring system based on data analysis | |
| CN113280910A (en) | Real-time monitoring method and system for long product production line equipment | |
| CN117477769A (en) | Early warning method and system for electric power system | |
| CN110259435B (en) | Well condition change identification method based on oil pumping unit electrical parameters | |
| CN114689321A (en) | Bearing fault diagnosis method and device for wind generating set and electronic equipment | |
| You et al. | Fault diagnosis method of escalator step system based on vibration signal analysis | |
| CN113447264B (en) | Online acoustic monitoring and diagnosing method for tooth breakage fault of planetary gear box | |
| Li et al. | Research and application on rapid recognition of CNC machine tools’ running state | |
| Qin et al. | Fault frequency identification of rolling bearing using reinforced ensemble local mean decomposition | |
| CN114969140B (en) | Method for detecting and analyzing performance data of fluent strip products | |
| Du | Detect Gear Fault in Wind Turbine Gearbox based on Time Synchornous Averaging Without Phase Signal. |
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 |