CN112765878A - Intelligent diagnosis method and device for abnormity of generator bearing of wind turbine generator - Google Patents
Intelligent diagnosis method and device for abnormity of generator bearing of wind turbine generator Download PDFInfo
- Publication number
- CN112765878A CN112765878A CN202110030463.2A CN202110030463A CN112765878A CN 112765878 A CN112765878 A CN 112765878A CN 202110030463 A CN202110030463 A CN 202110030463A CN 112765878 A CN112765878 A CN 112765878A
- Authority
- CN
- China
- Prior art keywords
- generator
- bearing
- wind turbine
- intelligent diagnosis
- training
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 29
- 230000005856 abnormality Effects 0.000 claims abstract description 26
- 238000007637 random forest analysis Methods 0.000 claims abstract description 22
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 239000000872 buffer Substances 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/06—Wind turbines or wind farms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Wind Motors (AREA)
Abstract
The invention provides an intelligent diagnosis method and device for abnormity of a generator bearing of a wind turbine generator. The method comprises the following steps: acquiring training data required by model training; training a random forest model by using training data; and predicting the abnormality of the generator bearing by using the random forest model obtained by training. The intelligent diagnosis method and device for the abnormity of the generator bearing of the wind turbine generator can automatically, timely and quickly analyze the state of the fan.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to an intelligent diagnosis method and device for abnormity of a generator bearing of a wind turbine generator.
Background
With the accumulated use of fan power generation equipment, the faults of the wind generating set occur more, certain parts lose the original precision or performance, the equipment cannot run normally, the technical performance is reduced, and the production is interrupted or the efficiency is reduced to influence the production.
The generator bearing has drive end and non-drive end both sides, and generator bearing wearing and tearing, bearing displacement, lubricated scheduling problem can lead to the temperature rise at generator both ends, consequently through establishing generator bearing temperature early warning model, can discover the abnormal state of generator bearing through the operating condition discovery.
The existing fault detection method for the wind turbine generator mainly comprises the steps of adding more detection sensor hardware, manually analyzing and evaluating the running condition of the wind turbine generator through vibration data collected by a sensor, and generally requiring a professional to evaluate the wind turbine generator regularly.
Disclosure of Invention
The invention aims to provide a method and a device for intelligently diagnosing the abnormity of a generator bearing of a wind turbine generator, which can automatically, timely and quickly analyze the state of a fan.
In order to solve the technical problem, the invention provides an intelligent diagnosis method for abnormity of a generator bearing of a wind turbine generator, which comprises the following steps: acquiring training data required by model training; training a random forest model by using training data; and predicting the abnormality of the generator bearing by using the random forest model obtained by training.
In some embodiments, the training data comprises: SCADA system data and fault maintenance records.
In some embodiments, the SCADA system data comprises: SCADA System 10min data.
In some embodiments, the troubleshooting record includes: down time, down cause.
In some embodiments, training the random forest model using the training data comprises: selecting characteristic data from the training data; and establishing a random forest model by using the selected characteristic data.
In some embodiments, the feature data comprises: the temperature of a non-driving-end bearing of the generator, the temperature of a driving-end bearing of the generator, the active power of the generator, the rotating speed of the generator, the pitch angle, the wind speed, the temperature of an engine room and the temperature outside the engine room.
In some embodiments, the random forest model is established by using the selected feature data, and the method comprises the following steps: the original data set is put back and randomly sampled to form K groups of subdata sets; randomly sampling m features from the N features of the sample; constructing an optimal learning model for each subdata set; and obtaining a final result according to the K optimal learning models for the new input data.
In some embodiments, further comprising: and after training the random forest model by using the training data, evaluating the prediction accuracy of the random forest model obtained by training.
In some embodiments, the evaluation is performed according to the following parameters: mean square error, root mean square error, mean absolute error.
In addition, the invention also provides an intelligent diagnosis device for the abnormity of the generator bearing of the wind turbine generator, which comprises: one or more processors; the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors realize the intelligent diagnosis method for bearing abnormity of the wind turbine generator according to the foregoing description.
After adopting such design, the invention has at least the following advantages:
according to the invention, data are innovatively input into the random forest model to obtain the predicted value of the temperature of the generator bearing, and the random forest model is utilized to obtain the accurate prediction of the temperature of the generator bearing, so that the accurate diagnosis of the fault is further carried out.
Drawings
The foregoing is only an overview of the technical solutions of the present invention, and in order to make the technical solutions of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and the detailed description.
FIG. 1 is a schematic diagram of a model building process;
FIG. 2 is a real-time map of original values, predicted values, and residuals;
FIG. 3 is a schematic diagram of an intelligent diagnosis device for bearing abnormality of a generator of a wind turbine.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The intelligent diagnosis method for the abnormal temperature of the generator bearing of the wind turbine generator mainly comprises the following three steps: data preparation, model establishment and model evaluation.
1. Data preparation
The data required for the generator bearing model includes two categories: firstly, the SCADA system has 10min data, including running data of a fan, unit information and the like; and secondly, fault maintenance records comprise information such as shutdown time, shutdown reasons and the like.
2. Model building
2.1 feature selection
The number of characteristic variables should be small and highly correlated with the generator bearing temperature, and variables that can sufficiently predict the generator bearing temperature are selected as the characteristic variables, and the characteristic variables are selected as shown in the following table.
| Generator non-drive end bearing temperature |
| Generator drive end bearing temperature |
| Active power of generator |
| Rotating speed of generator |
| Pitch angle |
| Wind speed |
| Cabin temperature |
| Outside cabin temperature |
2.2 model building
Random forest is a flexible and easy-to-use machine learning algorithm that can yield good results in most cases. The working principle of the random forest is to generate a plurality of models, study and make predictions independently, and the predictions are finally integrated to make up for the deficiencies and avoid limitations. Random forest model:
(1) the original data set is put back and randomly sampled to form K groups of subdata sets;
(2) randomly sampling m features from the N features of the sample;
(3) constructing an optimal learning model for each subdata set;
(4) and obtaining a final result according to the K optimal learning models for the new input data.
2.3 model evaluation
The following errors are selected as indexes for evaluating the prediction accuracy of the random forest.
(1) The MSE (mean square error) refers to an expectation value of the square of the difference between the estimated value of the parameter and the true value of the parameter, the MSE can evaluate the change degree of data, and the smaller the value of the MSE is, the better the accuracy of the prediction model is.
(2) RMSE (root mean square error) is the arithmetic square root of the mean square error.
(3) The MAE (mean absolute error) can better reflect the actual situation of the error of the predicted value.
In the formula: y isiIn order to be the true value of the value,
for the prediction value, m is the length of the sequence.
Fig. 3 shows the structure of the intelligent diagnosis device for bearing abnormality of the generator of the wind turbine. Referring to fig. 3, for example, the intelligent diagnosis device 300 for bearing abnormality of a wind turbine generator can be used as an intelligent diagnosis host for bearing abnormality in a wind turbine system. As described herein, the wind turbine generator bearing abnormality intelligent diagnosis apparatus 300 may be used to implement an intelligent diagnosis function for generator bearing abnormality in a wind turbine system. The intelligent diagnosis device for bearing abnormality of wind turbine generator 300 may be implemented in a single node, or the function of the intelligent diagnosis device for bearing abnormality of wind turbine generator 300 may be implemented in a plurality of nodes in a network. Those skilled in the art will appreciate that the term intelligent diagnosis apparatus for bearing abnormality of wind turbine generator includes a broad meaning of the device, and the intelligent diagnosis apparatus 300 for bearing abnormality of wind turbine generator shown in fig. 3 is only one example thereof. The intelligent diagnosis device 300 for bearing abnormality of wind turbine generator is included for clarity, and is not intended to limit the application of the present invention to a specific intelligent diagnosis device embodiment for bearing abnormality of wind turbine generator or a certain type of intelligent diagnosis device embodiment for bearing abnormality of wind turbine generator. At least some of the features/methods described herein may be implemented in a network device or component, such as the wind turbine generator bearing anomaly intelligent diagnostic device 300. For example, the features/methods of the present invention may be implemented in hardware, firmware, and/or software running installed on hardware. The intelligent diagnosis device 300 for bearing abnormality of wind turbine generator can be any device that processes, stores and/or forwards data frames through a network, such as a server, a client, a data source, etc. As shown in FIG. 3, the wind turbine generator bearing anomaly intelligent diagnostic apparatus 300 may include a transceiver (Tx/Rx)310, which may be a transmitter, a receiver, or a combination thereof. Tx/Rx 310 may be coupled to a plurality of ports 350 (e.g., an uplink interface and/or a downlink interface) for transmitting and/or receiving frames from other nodes. Processor 330 may be coupled to Tx/Rx 310 to process frames and/or determine to which nodes to send frames. The processor 330 may include one or more multi-core processors and/or memory devices 332, which may serve as data stores, buffers, and the like. The processor 330 may be implemented as a general-purpose processor, or may be part of one or more Application Specific Integrated Circuits (ASICs) and/or Digital Signal Processors (DSPs).
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the present invention in any way, and it will be apparent to those skilled in the art that the above description of the present invention can be applied to various modifications, equivalent variations or modifications without departing from the spirit and scope of the present invention.
Claims (10)
1. The intelligent diagnosis method for the abnormity of the generator bearing of the wind turbine generator is characterized by comprising the following steps of:
acquiring training data required by model training;
training a random forest model by using training data;
and predicting the abnormality of the generator bearing by using the random forest model obtained by training.
2. The intelligent diagnosis method for the abnormality of the bearing of the generator of the wind turbine generator according to claim 1, wherein the training data comprises: SCADA system data and fault maintenance records.
3. The intelligent diagnosis method for the bearing abnormality of the wind turbine generator according to claim 2, wherein the SCADA system data includes: SCADA System 10min data.
4. The intelligent diagnosis method for the abnormality of the bearing of the generator of the wind turbine generator according to claim 2, wherein the fault repair record comprises: down time, down cause.
5. The intelligent diagnosis method for the abnormality of the bearing of the generator of the wind turbine generator as set forth in claim 1, wherein training the random forest model by using the training data comprises:
selecting characteristic data from the training data;
and establishing a random forest model by using the selected characteristic data.
6. The intelligent diagnosis method for the bearing abnormality of the wind turbine generator according to claim 5, wherein the characteristic data includes: the temperature of a non-driving-end bearing of the generator, the temperature of a driving-end bearing of the generator, the active power of the generator, the rotating speed of the generator, the pitch angle, the wind speed, the temperature of an engine room and the temperature outside the engine room.
7. The intelligent diagnosis method for the abnormality of the generator bearing of the wind turbine generator as set forth in claim 5, wherein the establishing of the random forest model by using the selected feature data comprises:
the original data set is put back and randomly sampled to form K groups of subdata sets;
randomly sampling m features from the N features of the sample;
constructing an optimal learning model for each subdata set;
and obtaining a final result according to the K optimal learning models for the new input data.
8. The intelligent diagnosis method for the bearing abnormality of the wind turbine generator according to claim 1, further comprising:
and after training the random forest model by using the training data, evaluating the prediction accuracy of the random forest model obtained by training.
9. The intelligent diagnosis method for the abnormality of the bearing of the generator of the wind turbine generator according to claim 8, characterized in that the evaluation is performed according to the following parameters: mean square error, root mean square error, mean absolute error.
10. The utility model provides a wind turbine generator system generator bearing abnormity intelligent diagnosis device which characterized in that includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the intelligent diagnosis method for bearing abnormality of wind turbine generator according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110030463.2A CN112765878A (en) | 2021-01-11 | 2021-01-11 | Intelligent diagnosis method and device for abnormity of generator bearing of wind turbine generator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110030463.2A CN112765878A (en) | 2021-01-11 | 2021-01-11 | Intelligent diagnosis method and device for abnormity of generator bearing of wind turbine generator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112765878A true CN112765878A (en) | 2021-05-07 |
Family
ID=75701264
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110030463.2A Pending CN112765878A (en) | 2021-01-11 | 2021-01-11 | Intelligent diagnosis method and device for abnormity of generator bearing of wind turbine generator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112765878A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| CN108932580A (en) * | 2018-06-05 | 2018-12-04 | 浙江运达风电股份有限公司 | Wind turbines pitch variable bearings wear monitoring and method for early warning based on data modeling |
| CN110298485A (en) * | 2019-05-29 | 2019-10-01 | 国电联合动力技术有限公司 | Based on the pitch-controlled system failure prediction method for improving depth random forests algorithm |
| 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 |
| US20200201950A1 (en) * | 2018-12-21 | 2020-06-25 | Utopus Insights, Inc. | Scalable system and method for forecasting wind turbine failure using scada alarm and event logs |
-
2021
- 2021-01-11 CN CN202110030463.2A patent/CN112765878A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| CN108932580A (en) * | 2018-06-05 | 2018-12-04 | 浙江运达风电股份有限公司 | Wind turbines pitch variable bearings wear monitoring and method for early warning based on data modeling |
| US20200201950A1 (en) * | 2018-12-21 | 2020-06-25 | Utopus Insights, Inc. | Scalable system and method for forecasting wind turbine failure using scada alarm and event logs |
| CN110298485A (en) * | 2019-05-29 | 2019-10-01 | 国电联合动力技术有限公司 | Based on the pitch-controlled system failure prediction method for improving depth random forests algorithm |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2019413432B2 (en) | Scalable system and engine for forecasting wind turbine failure | |
| CN110991666B (en) | Fault detection method, training device, training equipment and training equipment for model, and storage medium | |
| CN102434387A (en) | Draught fan detection and diagnosis system | |
| CN110689141B (en) | Fault diagnosis method and equipment for wind generating set | |
| CN111400961B (en) | Wind generating set blade fault judging method and device | |
| CN111709190A (en) | Wind turbine generator operation data image identification method and device | |
| JPH113113A (en) | Diagnostic method for deterioration of equipment and device therefor | |
| CN104564542A (en) | Fault diagnosis system and fault diagnosis method based on massive data technology | |
| KR102545672B1 (en) | Method and apparatus for machine fault diagnosis | |
| CN116771610A (en) | Method for adjusting fault evaluation value of variable pitch system of wind turbine | |
| CN112765878A (en) | Intelligent diagnosis method and device for abnormity of generator bearing of wind turbine generator | |
| CN114320773B (en) | Wind turbine generator system fault early warning method based on power curve analysis and neural network | |
| CN113218653B (en) | Offshore wind power gear box monitoring method and device based on low-frequency disturbance elimination | |
| CN113777351B (en) | Fault diagnosis method and device for wind speed sensor of wind power plant | |
| CN112699598A (en) | Intelligent diagnosis method and device for abnormal oil temperature of gear box | |
| CN115962100A (en) | Wind turbine generator system state monitoring system | |
| Zhang | Comparison of data-driven and model-based methodologies of wind turbine fault detection with SCADA data | |
| CN114233581A (en) | Intelligent patrol alarm system for fan engine room | |
| CN111639110A (en) | Wind turbine generator fault early warning method and device | |
| CN113074940A (en) | Rolling bearing health state estimation system and method based on OS-ELM | |
| CN113719425A (en) | Fan blade fault prediction method and system and storage medium | |
| CN116886735B (en) | Hydropower station operation monitoring system based on double star-type Ethernet structure | |
| CN113821420B (en) | Performance comparison and data conversion method for CMS system of wind turbine generator | |
| CN117993895B (en) | Full life cycle management system of power grid equipment | |
| CN116757681B (en) | Real-time monitoring and diagnosing method and system for generating efficiency of wind turbine generator |
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 |