CN112577739A - Over-temperature fault diagnosis and early warning method for bearing at driving end of wind turbine generator - Google Patents
Over-temperature fault diagnosis and early warning method for bearing at driving end of wind turbine generator Download PDFInfo
- Publication number
- CN112577739A CN112577739A CN202011397837.6A CN202011397837A CN112577739A CN 112577739 A CN112577739 A CN 112577739A CN 202011397837 A CN202011397837 A CN 202011397837A CN 112577739 A CN112577739 A CN 112577739A
- Authority
- CN
- China
- Prior art keywords
- bearing
- temperature
- fault
- over
- early warning
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
- G01K13/04—Thermometers specially adapted for specific purposes for measuring temperature of moving solid bodies
- G01K13/08—Thermometers specially adapted for specific purposes for measuring temperature of moving solid bodies in rotary movement
Abstract
The invention relates to an overtemperature fault diagnosis and early warning method for a bearing at the driving end of an engine of a wind turbine generator, which comprises the following steps: step 1, establishing a nonlinear causal relationship between bearing temperature and related variables based on a multiple regression analysis method to obtain a reference curve of the bearing temperature of a drive end of an engine under the health state of a fan; the relevant variables comprise bearing rotating speed, torque, vibration and power; quantifying the deviation degree of the real-time regression curve of the bearing temperature relative to the healthy reference curve to obtain a healthy index reflecting the potential overtemperature fault of the bearing; and 3, monitoring and early warning the over-temperature fault of the bearing in a mode of setting a threshold value based on the obtained health index reflecting the potential over-temperature fault of the bearing. The invention can effectively ensure the reliable and efficient operation of the wind turbine generator, timely maintain the low-efficiency fan, improve the power generation capacity of the wind field and have good environmental protection and economic benefits.
Description
Technical Field
The invention belongs to the technical field of wind power generation, and particularly relates to an overtemperature fault diagnosis and early warning method for a bearing at the driving end of an engine of a wind turbine generator.
Background
In recent years, the development speed of the wind power industry is obviously slowed down, the current situation of 'wind and fire equivalent' is faced, the wind power operation level is improved, and the operation and maintenance cost is reduced, so that the primary problem faced by the whole industry is solved. The reliability of large components of the fan has great influence on the performance and safety of the unit, and particularly, blades, a main shaft, a generator, a gear box, a frequency converter and the like have high failure rate, long downtime and high failure recovery cost, so that great economic loss is caused to a wind field. Especially, the over-temperature fault of the bearing at the driving end of the engine seriously affects the generating efficiency of the fan and the profitability of the whole wind power plant. Therefore, an overtemperature fault diagnosis and early warning method for a bearing at the driving end of a wind turbine generator is needed.
Disclosure of Invention
The invention aims to provide an overtemperature fault diagnosis and early warning method for a bearing at the driving end of an engine of a wind turbine generator, so as to solve the technical problem.
The invention provides an overtemperature fault diagnosis and early warning method for a bearing at the driving end of an engine of a wind turbine generator, which is characterized by comprising the following steps:
step 1, establishing a nonlinear causal relationship between bearing temperature and related variables based on a multiple regression analysis method to obtain a reference curve of the bearing temperature of a drive end of an engine under the health state of a fan; the relevant variables comprise bearing rotating speed, torque, vibration and power;
quantifying the deviation degree of the real-time regression curve of the bearing temperature relative to the healthy reference curve to obtain a healthy index reflecting the potential overtemperature fault of the bearing;
and 3, monitoring and early warning the over-temperature fault of the bearing in a mode of setting a threshold value based on the obtained health index reflecting the potential over-temperature fault of the bearing.
Further, the reference curve is obtained by establishing a non-linear causal relationship between bearing temperature and power.
By means of the scheme, reliable and efficient operation of the wind turbine generator can be effectively guaranteed through the over-temperature fault diagnosis and early warning method for the bearing at the driving end of the engine of the wind turbine generator, the low-efficiency fan is timely maintained, the generated energy of a wind field is improved, and the wind turbine generator system has good environmental protection and economic benefits.
The foregoing is a summary of the present invention, and in order to provide a clear understanding of the technical means of the present invention and to be implemented in accordance with the present specification, the following is a detailed description of the preferred embodiments of the present invention.
Drawings
FIG. 1 is a flow chart of an over-temperature fault diagnosis and early warning method for a bearing at the driving end of a wind turbine generator set engine according to the invention;
FIG. 2 is a graph comparing a regression curve for early over-temperature anomalies and late over-temperature faults with a healthy reference curve in accordance with an embodiment of the present invention;
FIG. 3 is a graph of the health indicator of bearing temperature deviation from normal over time in an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Referring to fig. 1, the embodiment provides a method for diagnosing and early warning over-temperature fault of a bearing at a driving end of an engine of a wind turbine generator, which includes:
step S1, establishing a nonlinear causal relationship between bearing temperature and related variables based on a multiple regression analysis method to obtain a reference curve of the temperature of the bearing at the driving end of the engine under the health state of the fan; the relevant variables comprise bearing rotating speed, torque, vibration and power;
s2, quantifying the deviation degree of the real-time regression curve of the bearing temperature relative to the healthy reference curve to obtain a healthy index reflecting the potential overtemperature fault of the bearing;
and step S3, monitoring and early warning the over-temperature fault of the bearing in a mode of setting a threshold value based on the obtained health index reflecting the potential over-temperature fault of the bearing.
By the method for diagnosing and early warning the over-temperature fault of the bearing at the driving end of the engine of the wind turbine generator, the reliable and efficient operation of the wind turbine generator can be effectively guaranteed, the low-efficiency fan can be maintained in time, the generated energy of a wind field is improved, and the method has good environmental protection and economic benefits.
The present invention is described in further detail below.
When the potential faults of the important components cause the fan to deviate from normal operation, certain SCADA parameters are shifted from the normal operation, and the health states of the important components of the fan can be represented through the shift, so that the early warning and diagnosis of specific faults can be carried out.
The technical route of the embodiment is that a Correlation degree between a characteristic variable and a health state is measured by nonlinear Correlation Techniques such as Pearson's Correlation, then a feature vector combination corresponding to a fault is found by using a Clustering technique, and then a feature vector under normal operation of a unit is fitted to a health value by using a multivariate Regression Analysis, a Neural network or a Bayesian network. When the unit deviates from normal operation and enters an abnormal state, the difference between the fitting value and the health value obtained in real time is larger than a threshold value, the component can be judged to have potential fault risk to send out early warning, and the development change trend of a fault mode can be analyzed by combining historical fault data.
Take the failure mode of over-temperature of the bearing at the driving end of the engine as an example. In the embodiment, a multiple regression analysis method is used for establishing a nonlinear causal relationship between the bearing temperature and variables such as the bearing rotating speed, the bearing torque, the bearing vibration and the bearing power, and monitoring and early warning the overtemperature fault of the bearing. As shown in fig. 2, the abscissa is power, the ordinate is bearing temperature, the 2-1 curve is a reference curve of the bearing temperature of the driving end of the engine in the healthy state of the fan obtained by fitting a training sample, the 2-2 curve is a regression curve of early overtemperature abnormality, and the 2-3 curve is a regression curve of the later development stage of the overtemperature fault, so that the deviation between the 2-3 curve and the reference curve is large (the bearing temperature on the middle and high power section is high), and the process of the overtemperature abnormality from early deviation to fault shutdown is reflected.
According to the method, for different fault types, a Bayesian network, a multivariate regression analysis method or a neural network is selected to predict the development trend of the fault of the fan, maintenance is timely arranged in the early stage of the fault, and the problem that the shutdown is caused by serious faults is effectively avoided.
Taking the overtemperature fault of the bearing at the driving end of the engine as an example, quantifying the deviation degree of a real-time regression curve of the temperature of the bearing relative to a healthy reference curve to obtain a healthy index reflecting the potential overtemperature fault of the bearing. Fig. 3 is a change curve of the overtemperature health index with time, the abscissa is time, the ordinate is a degree value deviating from normal, data 30 days before the overtemperature fault occurs are selected for analysis, and as shown in the figure, the temperature of the bearing is sharply deviated from a normal value 4 days before the fault occurs, so that early warning of the overtemperature fault of the bearing can be realized by setting a threshold value.
By the method for diagnosing and early warning the over-temperature fault of the bearing at the driving end of the engine of the wind turbine generator, the reliable and efficient operation of the wind turbine generator can be effectively guaranteed, the low-efficiency fan can be maintained in time, the generated energy of a wind field is improved, and the method has good environmental protection and economic benefits.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, it should be noted that, for those skilled in the art, many modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (2)
1. The overtemperature fault diagnosis and early warning method for the bearing at the driving end of the engine of the wind turbine generator is characterized by comprising the following steps of:
step 1, establishing a nonlinear causal relationship between bearing temperature and related variables based on a multiple regression analysis method to obtain a reference curve of the bearing temperature of a drive end of an engine under the health state of a fan; the relevant variables comprise bearing rotating speed, torque, vibration and power;
quantifying the deviation degree of the real-time regression curve of the bearing temperature relative to the healthy reference curve to obtain a healthy index reflecting the potential overtemperature fault of the bearing;
and 3, monitoring and early warning the over-temperature fault of the bearing in a mode of setting a threshold value based on the obtained health index reflecting the potential over-temperature fault of the bearing.
2. The method for diagnosing and pre-warning the over-temperature fault of the bearing at the driving end of the wind turbine generator according to claim 1, wherein the health reference curve is obtained by establishing a non-linear causal relationship between the temperature and the power of the bearing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011397837.6A CN112577739A (en) | 2020-12-03 | 2020-12-03 | Over-temperature fault diagnosis and early warning method for bearing at driving end of wind turbine generator |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011397837.6A CN112577739A (en) | 2020-12-03 | 2020-12-03 | Over-temperature fault diagnosis and early warning method for bearing at driving end of wind turbine generator |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112577739A true CN112577739A (en) | 2021-03-30 |
Family
ID=75126883
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011397837.6A Pending CN112577739A (en) | 2020-12-03 | 2020-12-03 | Over-temperature fault diagnosis and early warning method for bearing at driving end of wind turbine generator |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112577739A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115185313A (en) * | 2022-08-05 | 2022-10-14 | 五凌电力有限公司 | Trend tracking early warning method and device for bearing bush temperature of hydroelectric generating set |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110313726A1 (en) * | 2009-03-05 | 2011-12-22 | Honeywell International Inc. | Condition-based maintenance system for wind turbines |
CN108680358A (en) * | 2018-03-23 | 2018-10-19 | 河海大学 | A kind of Wind turbines failure prediction method based on bearing temperature model |
CN110674842A (en) * | 2019-08-26 | 2020-01-10 | 明阳智慧能源集团股份公司 | Wind turbine generator main shaft bearing fault prediction method |
CN110735769A (en) * | 2019-09-18 | 2020-01-31 | 西安察柏科技咨询有限公司 | method, device and system for predicting fan faults |
CN111537219A (en) * | 2020-01-20 | 2020-08-14 | 内蒙古工业大学 | Fan gearbox performance detection and health assessment method based on temperature parameters |
CN111582392A (en) * | 2020-05-12 | 2020-08-25 | 河北工业大学 | Multi-working-condition health state online monitoring method for key components of wind turbine generator |
-
2020
- 2020-12-03 CN CN202011397837.6A patent/CN112577739A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110313726A1 (en) * | 2009-03-05 | 2011-12-22 | Honeywell International Inc. | Condition-based maintenance system for wind turbines |
CN108680358A (en) * | 2018-03-23 | 2018-10-19 | 河海大学 | A kind of Wind turbines failure prediction method based on bearing temperature model |
CN110674842A (en) * | 2019-08-26 | 2020-01-10 | 明阳智慧能源集团股份公司 | Wind turbine generator main shaft bearing fault prediction method |
CN110735769A (en) * | 2019-09-18 | 2020-01-31 | 西安察柏科技咨询有限公司 | method, device and system for predicting fan faults |
CN111537219A (en) * | 2020-01-20 | 2020-08-14 | 内蒙古工业大学 | Fan gearbox performance detection and health assessment method based on temperature parameters |
CN111582392A (en) * | 2020-05-12 | 2020-08-25 | 河北工业大学 | Multi-working-condition health state online monitoring method for key components of wind turbine generator |
Non-Patent Citations (2)
Title |
---|
丁佳煜 等: "基于轴承温度模型的风电机组故障预测研究", 《可再生能源》 * |
王新: "基于回归参数算法的风机轴承超温故障预警", 《数字技术与应用》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115185313A (en) * | 2022-08-05 | 2022-10-14 | 五凌电力有限公司 | Trend tracking early warning method and device for bearing bush temperature of hydroelectric generating set |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Leahy et al. | Diagnosing wind turbine faults using machine learning techniques applied to operational data | |
Uluyol et al. | Power curve analytic for wind turbine performance monitoring and prognostics | |
Kusiak et al. | The prediction and diagnosis of wind turbine faults | |
Cambron et al. | Control chart monitoring of wind turbine generators using the statistical inertia of a wind farm average | |
Zhang et al. | SCADA-data-based wind turbine fault detection: A dynamic model sensor method | |
Bi et al. | Detection and classification of faults in pitch-regulated wind turbine generators using normal behaviour models based on performance curves | |
CN112727702A (en) | Health management and fault early warning method for wind turbine generator | |
CN108564313A (en) | The method and device of Wind turbines status monitoring and health evaluating based on fault tree | |
CN103711645A (en) | Wind generating set state evaluation method based on modeling parameter feature analysis | |
CN116044802B (en) | State fault monitoring and diagnosing system for mine ventilator | |
CN111608899A (en) | Water pump running state abnormity discrimination method based on efficiency analysis | |
Sun et al. | Abnormal detection of wind turbine operating conditions based on state curves | |
US11340570B2 (en) | System and method for operating a wind turbine | |
Wiggelinkhuizen et al. | CONMOW: Condition monitoring for offshore wind farms | |
CN112577739A (en) | Over-temperature fault diagnosis and early warning method for bearing at driving end of wind turbine generator | |
US20090125206A1 (en) | Automatic detection and notification of turbine internal component degradation | |
Wang et al. | Maximizing the total power generation of faulty wind turbines via reduced power operation | |
Bezzaoucha et al. | Failure causes based wind turbine components classification and failure propagation: For proactive maintenance implementatio | |
Wiggelinkhuizen et al. | CONMOW Final Report | |
Laguna et al. | Early detection of gearbox damage, development of ANN forecast maintenance tool | |
Schlechtingen et al. | Condition monitoring with ordinary wind turbine SCADA data–A neuro-fuzzy approach | |
Bilendo et al. | Wind turbine anomaly detection based on SCADA data | |
CN114295367A (en) | Wind turbine generator gearbox working condition online monitoring method | |
Kuseyri | Condition monitoring of wind turbines: Challenges and opportunities | |
Patil et al. | Wind Turbine Faults, Faults Diagnosis and Fault Management Systems: A Review |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210330 |
|
RJ01 | Rejection of invention patent application after publication |