CN114429238A - Wind turbine generator fault early warning method based on space-time feature extraction - Google Patents
Wind turbine generator fault early warning method based on space-time feature extraction Download PDFInfo
- Publication number
- CN114429238A CN114429238A CN202111477655.4A CN202111477655A CN114429238A CN 114429238 A CN114429238 A CN 114429238A CN 202111477655 A CN202111477655 A CN 202111477655A CN 114429238 A CN114429238 A CN 114429238A
- Authority
- CN
- China
- Prior art keywords
- data
- wind turbine
- model
- turbine generator
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000000605 extraction Methods 0.000 title claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 238000003062 neural network model Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000012847 principal component analysis method Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 5
- 230000002159 abnormal effect Effects 0.000 claims abstract description 3
- 230000006870 function Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000011176 pooling Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 2
- 230000004913 activation Effects 0.000 claims description 2
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 230000007423 decrease Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 claims description 2
- 238000011478 gradient descent method Methods 0.000 claims description 2
- 238000009499 grossing Methods 0.000 claims description 2
- 238000011423 initialization method Methods 0.000 claims description 2
- 238000007619 statistical method Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a wind turbine generator fault early warning method based on space-time feature extraction, which comprises the following steps of: firstly, acquiring a wind turbine generator data set through a wind turbine generator monitoring and data acquisition system, preprocessing data, and detecting and eliminating abnormal points; performing dimensionality reduction processing on the operation data of the wind turbine generator by using a principal component analysis method; then, dividing the data set into a multivariable input layer and a univariate output layer, reserving time sequence correlation and space correlation of data, and building and training a data prediction neural network model of a wind turbine generator monitoring and data acquisition system; and finally, measuring the fitting degree of the model to the data by using the average absolute percentage error index, reserving the optimal model, and setting a model threshold value to obtain a fault early warning model. According to the method, the time characteristics and the space characteristics of the wind turbine data are comprehensively considered, the potential state of the wind turbine is more comprehensively and accurately reflected, and the fault early warning capability of the wind turbine is improved.
Description
Technical Field
The invention provides a wind turbine generator fault early warning method based on space-time feature extraction, and belongs to the field of quality monitoring.
Background
Wind energy is an important renewable energy source, the global wind energy use scale is rapidly increased in recent decades, the power generation capacity of onshore and offshore wind generating sets is continuously increased, and due to the huge maintenance cost of potential faults of the wind generating sets, effective and reliable fault early warning methods of the wind generating sets have to be developed so as to reduce the operation and maintenance cost of wind power plants. However, most of the conventional wind turbine fault early warning technologies only use a single type of signal as a fault feature, and the performance of the conventional wind turbine fault early warning technology may be limited by the signal feature. In order to solve the problem, a wind turbine generator fault early warning method based on space-time feature extraction is designed, so that the potential state of the wind turbine generator is reflected more comprehensively and accurately, and the fault early warning capability of the wind turbine generator is improved.
Disclosure of Invention
The invention designs a wind turbine generator fault early warning method based on space-time characteristic extraction, aiming at the problem of single fault characteristic of the traditional wind turbine generator fault early warning technology.
In order to achieve the above object, the invention adopts the following five steps, as shown in fig. 1.
Step 1: the method comprises the steps of preprocessing data of a wind turbine monitoring and data acquisition system, dividing a plurality of wind speed intervals between cut-in wind speeds and cut-out wind speeds, classifying all data points into each wind speed interval according to the wind speeds, then carrying out statistical analysis on the data points in each interval to obtain expected values of wind speeds and power, fitting a wind speed-power curve of the wind turbine, carrying out statistical standard deviation of difference distribution according to fan operation data, and detecting and removing abnormal points according to 3 division standards.
Step 2: the method comprises the steps of carrying out dimension reduction processing on wind turbine generator monitoring and data acquisition system data, carrying out dimension reduction processing on wind turbine generator operation data in order to improve the calculation efficiency of a model, adopting a principal component analysis method to orthogonally transform wind turbine generator data parameters into a group of linear irrelevant variables, and ensuring that the information contribution rate after dimension reduction is more than 95%.
And step 3: a neural network model for monitoring and data prediction of a wind turbine generator system is built, time sequence correlation is reserved on a data processing layer, data are divided into a multivariable input layer and a univariate output layer, the width of a sliding window is determined according to the size of the input layer, and then the spatial correlation of the data layer is reserved. The 2-dimensional data is transformed into 4-dimensions, which include an input layer, an output layer, a convolution kernel and a step size. The convolution layer of the model is 32 layers, the ReLU is selected as an activation function, the pooling layer is the maximum pooling layer, then the model is flattened into a linear layer, the random discarding rate of the linear layer is 0.5, and the final output layer is 1.
And 4, step 4: training a data prediction neural network model of a wind turbine monitoring and data acquisition system, and dividing data into a 60% training set and a 40% verification set. And training the model by using a training set, judging the quality of the model by using a verification set, and determining an optimal model. And finally, selecting a parameter of an Xavier initialization method initialization model, selecting an Adam optimizer to update the parameter of the model, determining that a loss function is a square loss function, adopting a small batch gradient descent method, wherein the batch size is 64, iterating for 50 cycles, and the learning rate is 0.001.
And 5: and measuring the fitting degree of the model to data by using the average absolute percentage error index, adjusting the model structure and the hyper-parameter to enable the model to obtain the best effect, smoothing the error by using an exponential weighted moving average method, and setting a model threshold value to obtain a fault early warning model.
Wherein the "3 division standard" in step 1 is shown in FIG. 2. The method is characterized in that 3 intervals are determined according to a fitting curve, data are expanded, and the accuracy of the operation data of the wind turbine generator is not guaranteed.
The "principal component analysis method" described in step 2 includes the following steps:
2-1: standardizing the raw data to obtain index values
Conversion into a standardized index
。
Wherein
,
。
Namely, it is
，
Are respectively the first
Sample mean and standard deviation of individual indices.
2-2: calculating a matrix of correlation coefficients
。
Matrix of correlation coefficients
。
In the formula
Is the first
An index and
correlation coefficient of each index.
2-3: the eigenvalues and eigenvectors are computed.
The eigenvalues are sorted from large to small.
Calculating a matrix of correlation coefficients
Characteristic value of
And corresponding feature vectors
Wherein
Is composed of feature vectors
A new index variable.
In the formula
Is the first main component of the mixture of the first and second components,
the total weight of the major components, …,
is the mth principal component.
2-4: selecting
（
) One masterAnd (4) calculating a comprehensive evaluation value.
Calculating characteristic values
The information contribution rate and the cumulative contribution rate. Referred to as principal component
The information contribution rate of (1).
And calculating a comprehensive score.
Wherein
Is as follows
Information contribution rate of each principal component.
The "wind turbine monitoring and data acquisition system data neural network model" in step 3 is shown in fig. 3. The constitution of the multi-variable input layer and the single-variable output layer is shown in the figure 4.
The step of training the wind turbine monitoring and data acquisition system data neural network model in step 4 is shown in fig. 5.
Wherein, the specific calculation method of the "average absolute percentage error" in the step 5 is as follows:
the Mean Absolute Percentage Error (MAPE) is used to calculate the degree of deviation between the predicted and true results.
Taking the fitting degree of the wind turbine generator model as an example,
represents the actual wind turbine generator temperature value,
representing the model predicted wind turbine temperature values. Wherein, the smaller the MAPE value is, the better the accuracy of the prediction model is.
The specific algorithm of the "exponentially weighted moving average" in step 5 is as follows:
the "exponentially weighted moving average" is a moving average weighted exponentially downward, the weighted influence of each numerical value decreases exponentially with time, and the weighted influence of data at a time closer to the current time is larger.
Taking the prediction of the temperature data of the wind turbine as an example, in the formula
Is composed of
Actual temperature values at the time; coefficient of performance
The weight descending speed is represented, and the smaller the value is, the faster the weight descending speed is;
is composed of
The moving average is exponentially weighted by time of day. Taking in general
In this algorithm we take
。
Drawings
FIG. 1 is a block flow diagram of the method of the present invention
FIG. 2 is a diagram of the "3 division criteria" described in step 1
FIG. 3 is a data neural network model diagram of a wind turbine monitoring and data acquisition system
FIG. 4 is a diagram of the input layer of the neural network model multivariate and the output layer of the univariate
FIG. 5 is a model diagram of a data neural network for training a wind turbine monitoring and data acquisition system.
Claims (7)
1. A wind turbine generator fault early warning method based on space-time feature extraction is characterized by comprising the following steps: step 1: the method comprises the steps that data of a wind turbine monitoring and data acquisition system are preprocessed, a plurality of wind speed intervals are drawn between cut-in wind speed and cut-out wind speed, all data points are classified into the wind speed intervals according to the wind speeds, then statistical analysis is conducted on the data points in the intervals to obtain expected values of the wind speeds and power, a wind speed-power curve of the wind turbine is fitted, and abnormal points are detected and removed according to standard deviation of difference value distribution of fan operation data statistics and 3 division standards; step 2: the method comprises the steps that data of a wind turbine monitoring and data acquisition system are subjected to dimensionality reduction, in order to improve the calculation efficiency of a model, the operation data of the wind turbine needs to be subjected to dimensionality reduction, a principal component analysis method is adopted, the data parameters of the wind turbine are orthogonally transformed into a group of linear irrelevant variables, and the information contribution rate after dimensionality reduction is ensured to be more than 95%; and step 3: building a data prediction neural network model of a wind turbine generator monitoring and data acquisition system, firstly, preserving time sequence correlation on a data processing layer, then dividing data into a multivariable input layer and a univariate output layer, determining the width of a sliding window according to the size of the input layer, further preserving the spatial correlation of the data layer, converting 2-dimensional data into 4-dimensional data, wherein the 2-dimensional data comprises the input layer, the output layer, a convolution kernel and a step length, the convolution layer of the model is 32 layers, a ReLU is selected as an activation function, the pooling layer is a maximum pooling layer, then the model is flattened into a linear layer, the random discard rate of the linear layer is 0.5, and the final output layer is 1; and 4, step 4: training a data prediction neural network model of a wind turbine generator monitoring and data acquisition system, dividing data into a 60% training set and a 40% verification set, judging whether the model is good or bad by using the verification set, determining an optimal model, finally determining parameters of an initialization model by selecting an Xavier initialization method, updating the parameters of the model by selecting an Adam optimizer, determining a loss function as a square loss function, iterating for 50 periods by adopting a small-batch gradient descent method, wherein the batch size is 64, and the learning rate is 0.001; and 5: and measuring the fitting degree of the model to data by using the average absolute percentage error index, adjusting the model structure and the hyper-parameter to enable the model to obtain the best effect, smoothing the error by using an exponential weighted moving average method, and setting a model threshold value to obtain a fault early warning model.
2. The wind turbine generator fault early warning method based on space-time feature extraction as claimed in claim 1, characterized in that: the 3 division standard in the step 1 refers to that the fitted wind speed power curve of the wind turbine generator is used as a reference, wind power plant data are obtained in a range of 3, and data which are not in the range are removed.
3. The wind turbine generator system fault early warning method based on space-time feature extraction as claimed in claim 1, wherein: the principal component analysis method described in step 2 is to firstly standardize the data, calculate the mean value and standard deviation of the sample indexes, then calculate the correlation coefficient matrix of each sample index, then form new principal components according to the eigenvalues and eigenvectors of the correlation coefficient matrix, finally calculate the information contribution rate of the principal components, cumulatively calculate the cumulative contribution rate of all the principal components, and select the corresponding principal components as input variables.
4. The wind turbine generator system fault early warning method based on space-time feature extraction as claimed in claim 1, wherein: the "multivariate input layer and univariate output layer" in step 3 refers to that for the same wind turbine generator, after the data dimension reduction, the same wind turbine generator has a certain number of characteristic attributes, the characteristic attributes include time information of the wind turbine generator in the period and characteristic information of different spatial positions, the characteristic attributes are used as an input layer of the model multivariate, the temperature information of the wind turbine generator is used as an output value (predicted value) of the model, and the output value is related to the temperature information in the previous period, so the output layer is a univariate output layer.
5. The wind turbine generator system fault early warning method based on space-time feature extraction as claimed in claim 1, wherein: the method for training the data neural network model of the wind turbine monitoring and data acquisition system in the step 4 is specifically divided into five steps, wherein the five steps are respectively random initialization weight, forward propagation is carried out to obtain all samples, a loss function is calculated, backward propagation is carried out to calculate partial derivatives, and the weight is updated.
6. The wind turbine generator system fault early warning method based on space-time feature extraction as claimed in claim 1, wherein: the "average absolute percentage error" in step 5 means that the predicted value of the model is subtracted from the actual value of the group of data, then the actual value is divided by the predicted value, and finally the average of the ratio of the group of data is taken to judge whether the model fits well or not.
7. The wind turbine generator system fault early warning method based on space-time feature extraction as claimed in claim 1, wherein: the "exponentially weighted moving average" in step 5 is a moving average weighted exponentially and the weighted influence of the predicted temperature value decreases exponentially with time, and the influence of the predicted value at the previous time is defined to be 0.95.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111477655.4A CN114429238A (en) | 2021-12-06 | 2021-12-06 | Wind turbine generator fault early warning method based on space-time feature extraction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111477655.4A CN114429238A (en) | 2021-12-06 | 2021-12-06 | Wind turbine generator fault early warning method based on space-time feature extraction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114429238A true CN114429238A (en) | 2022-05-03 |
Family
ID=81310721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111477655.4A Pending CN114429238A (en) | 2021-12-06 | 2021-12-06 | Wind turbine generator fault early warning method based on space-time feature extraction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114429238A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115034337A (en) * | 2022-08-10 | 2022-09-09 | 江西科骏实业有限公司 | Method and device for identifying state of traction motor in rail transit vehicle and medium |
| CN115293286A (en) * | 2022-08-20 | 2022-11-04 | 华南理工大学 | Offshore wind turbine monitoring data processing method based on big data feature extraction |
| CN117006002A (en) * | 2023-09-27 | 2023-11-07 | 广东海洋大学 | Digital twinning-based offshore wind turbine monitoring method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073158A (en) * | 2017-12-05 | 2018-05-25 | 上海电机学院 | Based on PCA and KNN density algorithm Wind turbines Method for Bearing Fault Diagnosis |
| 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 |
| 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 | Wind turbine generator gearbox bearing temperature state monitoring method based on deep learning model |
| CN112784373A (en) * | 2021-01-19 | 2021-05-11 | 河北大学 | Fault early warning method for wind turbine generator gearbox |
-
2021
- 2021-12-06 CN CN202111477655.4A patent/CN114429238A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073158A (en) * | 2017-12-05 | 2018-05-25 | 上海电机学院 | Based on PCA and KNN density algorithm Wind turbines Method for Bearing Fault Diagnosis |
| 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 |
| 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 | Wind turbine generator gearbox bearing temperature state monitoring method based on deep learning model |
| CN112784373A (en) * | 2021-01-19 | 2021-05-11 | 河北大学 | Fault early warning method for wind turbine generator gearbox |
Non-Patent Citations (2)
| Title |
|---|
| 许开成: "《锂渣在混凝土中再生利及耐久性研究》", 30 December 2020, 华中科技大学出版社 * |
| 陈本通: "《企业的经营预测》", 28 February 1986, 福建人民出版社 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115034337A (en) * | 2022-08-10 | 2022-09-09 | 江西科骏实业有限公司 | Method and device for identifying state of traction motor in rail transit vehicle and medium |
| CN115034337B (en) * | 2022-08-10 | 2022-11-01 | 江西科骏实业有限公司 | Method, device and medium for identifying state of traction motor in rail transit vehicle |
| CN115293286A (en) * | 2022-08-20 | 2022-11-04 | 华南理工大学 | Offshore wind turbine monitoring data processing method based on big data feature extraction |
| CN117006002A (en) * | 2023-09-27 | 2023-11-07 | 广东海洋大学 | Digital twinning-based offshore wind turbine monitoring method and system |
| CN117006002B (en) * | 2023-09-27 | 2024-02-09 | 广东海洋大学 | Digital twinning-based offshore wind turbine monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108022001B (en) | Short-term load probability density prediction method based on PCA (principal component analysis) and quantile regression forest | |
| CN114429238A (en) | Wind turbine generator fault early warning method based on space-time feature extraction | |
| US11840998B2 (en) | Hydraulic turbine cavitation acoustic signal identification method based on big data machine learning | |
| CN110414788B (en) | Electric energy quality prediction method based on similar days and improved LSTM | |
| CN106503867A (en) | A kind of genetic algorithm least square wind power forecasting method | |
| CN116757534A (en) | Intelligent refrigerator reliability analysis method based on neural training network | |
| CN113107626B (en) | Load prediction method of combined cycle generator set based on multivariable LSTM | |
| CN115048874B (en) | Aircraft design parameter estimation method based on machine learning | |
| CN104865827B (en) | Oil pumping unit oil extraction optimization method based on multi-working-condition model | |
| CN112396234A (en) | User side load probability prediction method based on time domain convolutional neural network | |
| CN110020680B (en) | PMU data classification method based on random matrix theory and fuzzy C-means clustering algorithm | |
| CN109240276B (en) | Multi-block PCA fault monitoring method based on fault sensitive principal component selection | |
| CN114117852B (en) | Regional heat load rolling prediction method based on finite difference working domain division | |
| CN110070202A (en) | A method of economic output is predicted by electricity consumption data | |
| CN109298633A (en) | Chemical production process fault monitoring method based on adaptive piecemeal Non-negative Matrix Factorization | |
| CN115294671A (en) | Air compressor outlet pressure prediction method and prediction system | |
| CN113379116A (en) | Cluster and convolutional neural network-based line loss prediction method for transformer area | |
| CN112288157A (en) | Wind power plant power prediction method based on fuzzy clustering and deep reinforcement learning | |
| CN114865620B (en) | Wind power plant generating capacity prediction method based on machine learning algorithm | |
| CN115081331A (en) | Wind turbine generator running state abnormity detection method based on state parameter reconstruction error | |
| CN113642238A (en) | Micrometeorological factor-based radial basis function neural network power transmission line icing prediction method | |
| CN114266194A (en) | Intelligent energy consumption prediction method for enterprise production system | |
| CN116629843B (en) | Remote early warning and maintenance decision support system of intelligent diesel generator set | |
| CN117096860A (en) | Overhead transmission line current-carrying capacity interval prediction method and equipment based on LSSVM model | |
| CN116757337A (en) | House construction progress prediction system based on artificial intelligence |
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: 20220503 |
|
| RJ01 | Rejection of invention patent application after publication |