CN112699598A - Intelligent diagnosis method and device for abnormal oil temperature of gear box - Google Patents
Intelligent diagnosis method and device for abnormal oil temperature of gear boxDownload PDFInfo
- Publication number
- CN112699598A CN112699598ACN202011467739.5ACN202011467739ACN112699598ACN 112699598 ACN112699598 ACN 112699598ACN 202011467739 ACN202011467739 ACN 202011467739ACN 112699598 ACN112699598 ACN 112699598A
- Authority
- CN
- China
- Prior art keywords
- oil temperature
- wind turbine
- gearbox
- intelligent diagnosis
- turbine generator
- 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
- G06—COMPUTING OR CALCULATING; 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
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Wind Motors (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to an intelligent diagnosis method and device for abnormal oil temperature of a gear box.
Background
With the development of economy, the global energy crisis environment crisis increasingly prominent, and wind energy is more and more emphasized by countries in the world due to the advantages of low cost, cleanness, safety, renewability and the like, and becomes the fastest renewable energy in the world at present. The wind turbine generator gearbox serving as a speed change mechanism is subjected to alternating load and impact load for a long time, and is easy to cause faults such as gear abrasion, pitting corrosion and bearing surface damage, so that the gear box fault accounts for a higher proportion in mechanical faults of the wind turbine generator. The problems of unit limited power operation, fault shutdown and the like caused by high oil temperature of the gear box are obvious, each wind power plant is disturbed, and the generated energy of the unit and the income of the wind power plant are seriously influenced.
Therefore, the gearbox oil temperature is analyzed, the abnormal change of the gearbox oil temperature is identified, and early signs of the wind turbine generator gearbox fault, particularly the fault of accessory components, can be sensed in advance. The temperature signal indicates whether all the components of the wind turbine generator are healthy or not, the temperature and the temperature rise of all the components and subsystems are regular and recyclable, and the temperature change of the fan components can be used for judging the health state of the fan.
Disclosure of Invention
The invention aims to provide an intelligent diagnosis method and device for abnormal oil temperature of a gearbox, which can accurately judge the health state of a fan according to the change of the oil temperature.
In order to solve the technical problem, the invention provides an intelligent diagnosis method for abnormal oil temperature of a gearbox, which comprises the following steps: dividing the operation working conditions of the wind turbine generator into different working conditions according to the unit operation data; selecting Random Forest, Adaboost, GBDT and KNN regression prediction models as candidate models; evaluating the candidate models under different working conditions through the selected evaluation indexes, and selecting a prediction model from the candidate models according to an evaluation result; and deploying a prediction model by using a container technology, and predicting the oil temperature abnormity by using the deployed prediction model.
In some embodiments, further comprising: the method comprises the steps of preparing unit operation data before dividing operation conditions of the wind turbine into different conditions according to the unit operation data.
In some embodiments, the unit operational data includes: SCADA operation data, fault maintenance records and unit technical specification documents.
In some embodiments, further comprising: before the operation working conditions of the wind turbine generator are divided into different working conditions according to the operation data of the wind turbine generator, after the operation data of the wind turbine generator are prepared, indexes of which the correlation is larger than a preset threshold value are selected by adopting a pearson correlation analysis method and a wind turbine generator design mechanism causal analysis combination method.
In some embodiments, further comprising: before the operation working conditions of the wind turbine generator are divided into different working conditions according to the operation data of the wind turbine generator, an abnormal value processing method, a missing value processing method and a repeated value processing method are carried out after an index with the correlation larger than a preset threshold value is selected by adopting a pearson correlation analysis method and a wind turbine generator design mechanism causal analysis combination method.
In some embodiments, the outlier processing comprises: and identifying the threshold value according to the technical specification document of the wind turbine generator and the normal value range of the index provided by the maintenance experience of the fan.
In some embodiments, the different operating conditions include: the system comprises a region to be started, a maximum wind energy capture region, a constant power operation region and a strong wind cutting region.
In some embodiments, evaluating the indicator comprises: the absolute error is averaged.
In some embodiments, predicting the oil temperature anomaly with the deployed prediction model comprises: and determining a residual error threshold value for residual errors obtained by a test set in the model training process by using a 3 sigma method.
In addition, the invention also provides an intelligent diagnosis device for abnormal oil temperature of the gearbox, which comprises: one or more processors; a storage device for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the intelligent diagnosis method for gearbox oil temperature abnormality according to the foregoing description.
After adopting such design, the invention has at least the following advantages:
according to the method, the machine learning regression model is innovatively applied to oil temperature abnormity diagnosis, meanwhile, a designated early warning strategy is divided according to the working conditions of the wind turbine generator based on the design and the operation mechanism of the wind turbine generator, and finally, model deployment and management are performed by adopting a container technology, so that the accurate judgment of the running health state of the fan is completed.
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 view of wind turbine operating conditions;
FIG. 2 is a schematic diagram of a gearbox oil temperature distribution situation of a maximum wind energy capture area in a wind power plant in Hebei;
FIG. 3 is a schematic diagram of the distribution of the oil temperature of a gearbox in a constant power operation area in a wind farm in Hebei;
FIG. 4 is a schematic diagram of a trend of oil temperature change of a gearbox of a certain wind turbine;
FIG. 5 is a schematic flow chart diagram of a method for intelligently diagnosing abnormal oil temperature of a gearbox;
FIG. 6 is a schematic structural diagram of an intelligent diagnosis device for abnormal oil temperature of a gearbox.
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 oil temperature of the gearbox of the wind turbine generator mainly comprises the following four steps: 1. preparing data; 2. establishing a model; 3. deploying a model; 4. and (5) early warning strategy. The data preparation method mainly comprises the steps of selecting effective data according to wind turbine SCADA operation data, fault overhaul records and turbine technical specification documents; the model establishment is divided into: data processing, model construction and model evaluation; the models are deployed and managed by using a container technology, so that the models are isolated from each other; and the early warning strategy determines a residual error threshold value through residual errors obtained in model training and gives fault early warning according to the accumulated time length.
1. Data preparation
The method comprises the following steps of (1) performing fault early warning model data characteristic engineering on accessory parts of a gearbox, wherein required data are mainly selected according to causal analysis of a wind turbine mechanism, and mechanism related data comprise: the method comprises the steps of wind turbine SCADA operation data, fault overhaul records and turbine technical specification documents.
1.1, preparing fan operation data: and selecting the SCADA system 10 min data as target data. And selecting indexes such as a fan ID, a wind field ID, a power factor, the active power of a generator, the rotating speed of the generator, the wind speed, the oil temperature of a gear box, the temperature of a main bearing and the like by taking a single type of wind turbine generator as a unit.
1.2 fault record table preparation: and selecting and storing historical fault records of all fans of the wind field. The data includes information such as wind farm, wind turbine I D, model, start time, end time, fault message, shutdown reason, shutdown type, etc.
1.3 preparing technical specification documents of the unit: the selected unit technical specification document comprises unit operation parameter conditions. The core parameter description comprises: power factor, wind speed, generator speed, wind wheel speed, generator power, etc.
2. Model building
The model establishment is divided into 3 steps by referring to a data mining standard process CRISP-DM (cross-index standard process for data mining): 1) preparing data; 2) establishing a model; 3) and (6) evaluating the model.
2.1 data processing: the data preparation process mainly comprises the processes of abnormal value processing, feature selection, normal operation data definition and the like.
a. Abnormal value processing: the outlier identification strategy includes: threshold identification and data statistics observation identification. And identifying the threshold value according to the technical specification document of the wind turbine generator and the normal value range of the index provided by the maintenance experience of the fan. Replace the outliers with NaN values.
b. Missing value processing: deleting the data of the whole record if the data of the whole column is missing, and filling the data if the missing value exists in the individual record in the data.
c. Repeated value processing: and if all index column values of any two or more rows are equal, deleting all the two or more rows.
d. Selecting characteristics: and filtering out low-correlation and lacking indexes and columns with empty index values by adopting a pearson correlation analysis method and a wind generating set design mechanism causal analysis combined method, and reserving indexes with correlation values larger than 0.5.
TABLE 1 Primary selection index List of Fault early warning data set of gearbox body
e. Dividing working conditions: firstly, normal operation data must meet the parameter requirements of wind turbine technical specification, and secondly, the wind turbine is divided into four regions according to different operation modes of the wind turbine under different wind speed conditions: the system comprises a region to be started, a maximum wind energy capture region, a constant power operation region and a high wind cutting region, and a working condition schematic diagram is shown in figure 1.
In the research, working conditions are distinguished according to wind speeds, a wind turbine generator is divided into a maximum wind energy capture area and a constant power operation area in an operation state, and upper and lower limit values of the oil temperature of a gear box are respectively determined by adopting a 2 sigma method. Specifically, as shown in fig. 2 and 3, μ represents an oil temperature mean value, and σ represents a variance.
2.2 model building
Selecting Random Forest, Adaboost, GBDT and KNN regression prediction models as candidate models, determining the optimal parameters of each model through a grid search method, and selecting the optimal regression model.
2.3 model evaluation
The model evaluation indexes of the regression model of the research mainly comprise:
a. mean Square Error (MSE)
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.
b. Root Mean Square Error (RMSE)
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.
c. Mean Absolute Error (MAE)
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.
And training and testing the four regression models by adopting a K-Fold cross validation method, so that the classification model with the minimum MAE value is selected as the identification model finally applied to the unit operation fault data. Specific results are shown in tables 2 and 3 (wherein K is 5), and the default parameters of the random forest regression model are selected to have a good prediction effect in the maximum wind energy tracking and constant power region.
TABLE 2 results of K-Fold cross validation of MAE values for four regression models in the maximum wind energy tracking region
| Regression model | Model 1 | Model 2 | Model 3 | Model 4 | Model 5 |
| Random forest regression | 0.391 | 0.394 | 0.397 | 0.394 | 0.391 |
| AdaBoost regression | 0.408 | 0.412 | 0.414 | 0.412 | 0.407 |
| Gradient boosting decision tree regression | 0.57 | 0.571 | 0.577 | 0.573 | 0.57 |
| KNN regression | 0.896 | 0.896 | 0.902 | 0.898 | 0.899 |
TABLE 3 results of K-Fold cross validation of MAE values for four regression models in constant power region
| Regression model | Model 1 | Model 2 | Model 3 | Model 4 | Model 5 |
| Random forest regression | 0.466 | 0.457 | 0.475 | 0.482 | 0.478 |
| AdaBoost regression | 0.501 | 0.495 | 0.476 | 0.497 | 0.481 |
| Gradient boosting decision tree regression | 0.594 | 0.578 | 0.595 | 0.601 | 0.602 |
| KNN regression | 0.981 | 0.967 | 0.981 | 0.984 | 0.967 |
3. Model deployment
The deployment of the gearbox oil temperature abnormity model adopts a container technology, the technology uniformly encapsulates the python code, the model and a third party library on which the model depends into a portable mirror image, the mirror image can be operated on any Linux machine with a container environment, the algorithm model can be started only by deploying the mirror image, and other environments do not need to be deployed.
4. Early warning strategy
And inputting the data of different working conditions into corresponding prediction models to obtain a predicted value of the oil temperature of the gearbox, calculating a residual error between an actual value and the predicted value of the oil temperature of the gearbox on the basis, and carrying out mean value polymerization on the residual error for 1 hour. And determining a residual error threshold value by using a 3 sigma method for residual errors obtained by a test set in the process of model training, and giving an alarm if the residual error threshold value is exceeded for more than 3 hours accumulated within 7 days, thereby realizing fault early warning of the accessory parts. A gear box oil temperature change trend graph of the unit is derived by means of a visualization function of the gear box oil temperature change trend in the original data set corresponding to the prediction result, and the result is shown in figure 4 (a horizontal line represents a gear box oil temperature alarm threshold).
The specific process flow of the invention is shown in fig. 5.
Fig. 6 shows the structure of the intelligent diagnosis device for abnormal oil temperature of the gearbox. Referring to fig. 6, for example, theintelligent diagnosis device 600 for gearbox oil temperature abnormality can be used as a main intelligent diagnosis machine for gearbox oil temperature in a wind turbine system. As described herein, theintelligent diagnosis device 600 for gearbox oil temperature abnormality can be used for realizing the function of abnormality diagnosis of the gearbox oil temperature in the wind turbine system. Theintelligent diagnosis device 600 for gearbox oil temperature abnormality may be implemented in a single node, or the function of theintelligent diagnosis device 600 for gearbox oil temperature abnormality may be implemented in a plurality of nodes in a network. Those skilled in the art will appreciate that the term intelligent diagnosis device for gearbox oil temperature abnormality includes a broad meaning of the apparatus, and theintelligent diagnosis device 600 for gearbox oil temperature abnormality shown in fig. 6 is only one example thereof. The intelligentdiagnostic device 600 for gearbox oil temperature anomaly is included for clarity of presentation and is not intended to limit the application of the present invention to a particular intelligent diagnostic device embodiment for gearbox oil temperature anomaly or to a class of intelligent diagnostic device embodiments for gearbox oil temperature anomaly. At least some of the features/methods described herein may be implemented in a network device or component, such as the intelligentdiagnostic device 600 for gearbox oil temperature anomalies. For example, the features/methods of the present invention may be implemented in hardware, firmware, and/or software running installed on hardware. Theintelligent diagnosis device 600 for gearbox oil temperature abnormality can be any device that processes, stores and/or forwards data frames through a network, such as a server, a client, a data source, and the like. As shown in FIG. 6, the gearbox oil temperature anomaly intelligentdiagnostic device 600 may include a transceiver (Tx/Rx)610, which may be a transmitter, a receiver, or a combination thereof. Tx/Rx 610 may be coupled to a plurality of ports 650 (e.g., an uplink interface and/or a downlink interface) for transmitting and/or receiving frames from other nodes.Processor 630 may be coupled to Tx/Rx 610 to process frames and/or determine to which nodes to send frames.Processor 630 may include one or more multi-core processors and/ormemory devices 632, which may serve as data stores, buffers, and the like. Theprocessor 630 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. An intelligent diagnosis method for abnormal oil temperature of a gearbox is characterized by comprising the following steps:
dividing the operation working conditions of the wind turbine generator into different working conditions according to the unit operation data;
selecting Random Forest, Adaboost, GBDT and KNN regression prediction models as candidate models;
evaluating the candidate models under different working conditions through the selected evaluation indexes, and selecting a prediction model from the candidate models according to an evaluation result;
and deploying a prediction model by using a container technology, and predicting the oil temperature abnormity by using the deployed prediction model.
2. The intelligent diagnosis method for abnormal oil temperature of gearbox according to claim 1, further comprising:
the method comprises the steps of preparing unit operation data before dividing operation conditions of the wind turbine into different conditions according to the unit operation data.
3. The intelligent diagnosis method for abnormal oil temperature of the gearbox according to claim 2, wherein the unit operation data comprises: SCADA operation data, fault maintenance records and unit technical specification documents.
4. The intelligent diagnosis method for abnormal oil temperature of gearbox according to claim 2, further comprising:
before the operation working conditions of the wind turbine generator are divided into different working conditions according to the operation data of the wind turbine generator, after the operation data of the wind turbine generator are prepared, indexes of which the correlation is larger than a preset threshold value are selected by adopting a pearson correlation analysis method and a wind turbine generator design mechanism causal analysis combination method.
5. The intelligent diagnosis method for gearbox oil temperature abnormality according to claim 4, further comprising:
before the operation working conditions of the wind turbine generator are divided into different working conditions according to the operation data of the wind turbine generator, an abnormal value processing method, a missing value processing method and a repeated value processing method are carried out after an index with the correlation larger than a preset threshold value is selected by adopting a pearson correlation analysis method and a wind turbine generator design mechanism causal analysis combination method.
6. The intelligent diagnosis method for abnormal oil temperature of gearbox according to claim 5, characterized in that abnormal value processing comprises: and identifying the threshold value according to the technical specification document of the wind turbine generator and the normal value range of the index provided by the maintenance experience of the fan.
7. The intelligent diagnosis method for abnormal oil temperature of the gearbox according to claim 1, wherein different working conditions comprise: the system comprises a region to be started, a maximum wind energy capture region, a constant power operation region and a strong wind cutting region.
8. The intelligent diagnosis method for the abnormal oil temperature of the gearbox according to claim 1, wherein the evaluation index comprises: the absolute error is averaged.
9. The intelligent diagnosis method for the abnormal oil temperature of the gearbox according to claim 1, wherein the prediction of the abnormal oil temperature by using the deployed prediction model comprises the following steps:
and determining a residual error threshold value for residual errors obtained by a test set in the model training process by using a 3 sigma method.
10. The utility model provides a gearbox oil temperature anomaly 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 gearbox oil temperature anomaly intelligent diagnostic method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011467739.5ACN112699598A (en) | 2020-12-14 | 2020-12-14 | Intelligent diagnosis method and device for abnormal oil temperature of gear box |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011467739.5ACN112699598A (en) | 2020-12-14 | 2020-12-14 | Intelligent diagnosis method and device for abnormal oil temperature of gear box |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112699598Atrue CN112699598A (en) | 2021-04-23 |
Family
ID=75507878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011467739.5APendingCN112699598A (en) | 2020-12-14 | 2020-12-14 | Intelligent diagnosis method and device for abnormal oil temperature of gear box |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112699598A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114295367A (en)* | 2021-11-12 | 2022-04-08 | 华能新能源股份有限公司 | Wind turbine generator gearbox working condition online monitoring method |
| CN120143801A (en)* | 2025-05-15 | 2025-06-13 | 中国建筑科学研究院有限公司 | Fault diagnosis methods, devices, equipment, media and products for building electromechanical systems |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110907170A (en)* | 2019-11-30 | 2020-03-24 | 华能如东八仙角海上风力发电有限责任公司 | A kind of wind turbine gearbox bearing temperature condition monitoring and fault diagnosis method |
| CN110907066A (en)* | 2019-11-30 | 2020-03-24 | 华能如东八仙角海上风力发电有限责任公司 | Method for monitoring the temperature state of wind turbine gearbox bearing based on deep learning model |
- 2020
- 2020-12-14CNCN202011467739.5Apatent/CN112699598A/enactivePending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110907170A (en)* | 2019-11-30 | 2020-03-24 | 华能如东八仙角海上风力发电有限责任公司 | A kind of wind turbine gearbox bearing temperature condition monitoring and fault diagnosis method |
| CN110907066A (en)* | 2019-11-30 | 2020-03-24 | 华能如东八仙角海上风力发电有限责任公司 | Method for monitoring the temperature state of wind turbine gearbox bearing based on deep learning model |
Non-Patent Citations (1)
| Title |
|---|
| 王灿;李韶武;张天阳;吕微;: "风电机组齿轮箱油温异常诊断方法与预警策略研究", 船舶工程, no. 1, pages 543 - 546* |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114295367A (en)* | 2021-11-12 | 2022-04-08 | 华能新能源股份有限公司 | Wind turbine generator gearbox working condition online monitoring method |
| CN114295367B (en)* | 2021-11-12 | 2024-09-06 | 华能新能源股份有限公司 | Wind turbine generator system gear box working condition on-line monitoring method |
| CN120143801A (en)* | 2025-05-15 | 2025-06-13 | 中国建筑科学研究院有限公司 | Fault diagnosis methods, devices, equipment, media and products for building electromechanical systems |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7514242B2 (en) | Method and system for predicting risk of observable damage in wind turbine gearbox components | |
| Ayo-Imoru et al. | A survey of the state of condition-based maintenance (CBM) in the nuclear power industry | |
| Tautz‐Weinert et al. | Using SCADA data for wind turbine condition monitoring–a review | |
| Liu et al. | Research on fault diagnosis of wind turbine based on SCADA data | |
| Zaher et al. | Online wind turbine fault detection through automated SCADA data analysis | |
| Chen et al. | Automated on‐line fault prognosis for wind turbine pitch systems using supervisory control and data acquisition | |
| Schlechtingen et al. | Wind turbine condition monitoring based on SCADA data using normal behavior models. Part 1: System description | |
| Zhou et al. | A novel grey prognostic model based on Markov process and grey incidence analysis for energy conversion equipment degradation | |
| CN103019135B (en) | Life prediction method and system for fan components | |
| CN110362045B (en) | A fault discrimination method for offshore doubly-fed wind turbines considering marine meteorological factors | |
| Butler et al. | A feasibility study into prognostics for the main bearing of a wind turbine | |
| Shi et al. | Study of wind turbine fault diagnosis and early warning based on SCADA data | |
| Borchersen et al. | Model‐based fault detection for generator cooling system in wind turbines using SCADA data | |
| Peco Chacón et al. | State of the art of artificial intelligence applied for false alarms in wind turbines | |
| d N Santos et al. | Data-driven farm-wide fatigue estimation on jacket foundation OWTs for multiple SHM setups | |
| Yang et al. | Fault early warning of wind turbine gearbox based on multi‐input support vector regression and improved ant lion optimization | |
| Du et al. | A SCADA data based anomaly detection method for wind turbines | |
| CN115578084A (en) | Wind Turbine Frequency Converter Fault Early Warning Method Based on Deep Convolutional Autoencoder | |
| Leahy et al. | Cluster analysis of wind turbine alarms for characterising and classifying stoppages | |
| CN104571084B (en) | Main air compressor fault rootstock depth diagnostic method and device | |
| CN112699598A (en) | Intelligent diagnosis method and device for abnormal oil temperature of gear box | |
| CN112696481A (en) | Intelligent diagnosis method and device for shaft temperature abnormity of wind turbine generator gearbox | |
| CN116771610A (en) | Method for adjusting fault evaluation value of variable pitch system of wind turbine | |
| CN115985072A (en) | Wind turbine cabin temperature monitoring and early warning method and system based on machine learning | |
| Du et al. | A SOM based Anomaly detection method for wind turbines health management through SCADA data |
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:20210423 | |
| RJ01 | Rejection of invention patent application after publication |