CN117077532A - Multi-model fusion method for life prediction of wind turbine generator - Google Patents
Multi-model fusion method for life prediction of wind turbine generator Download PDFInfo
- Publication number
- CN117077532A CN117077532A CN202311075725.2A CN202311075725A CN117077532A CN 117077532 A CN117077532 A CN 117077532A CN 202311075725 A CN202311075725 A CN 202311075725A CN 117077532 A CN117077532 A CN 117077532A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- wind turbine
- turbine generator
- service life
- 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
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 62
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000011156 evaluation Methods 0.000 claims abstract description 13
- 230000004927 fusion Effects 0.000 claims abstract description 10
- 238000013480 data collection Methods 0.000 claims abstract description 9
- 238000010276 construction Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000012544 monitoring process Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000011426 transformation method Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000000556 factor analysis Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 8
- 238000012417 linear regression Methods 0.000 description 6
- 238000007637 random forest analysis Methods 0.000 description 6
- 238000012706 support-vector machine Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
- G06F2119/04—Ageing analysis or optimisation against ageing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Wind Motors (AREA)
Abstract
The invention provides a multi-model fusion method for predicting the service life of a wind turbine, which can comprehensively utilize various data and models and improve the stability and reliability of service life prediction. The method comprises the following steps: s101, data collection and preprocessing S102, model construction and model training S103, model fusion and model evaluation S104, model application and model updating.
Description
Technical Field
The invention relates to the technical field of service life of wind turbines, in particular to a multi-model fusion method for service life prediction of wind turbines.
Background
The wind turbine generator is a device for converting wind energy into electric energy, and life prediction is an important content of operation and maintenance of a wind farm, and relates to safety, reliability and economy of the wind farm. The service life of the wind turbine generator is influenced by various factors such as structure, materials, load, environment and the like, so that the service life prediction technology has great difficulty, and various methods and data are required to be comprehensively applied.
At present, the life prediction technology of the wind turbine generator mainly comprises the following steps:
life prediction technology based on fatigue cumulative damage theory: the technology utilizes the Miner fatigue cumulative damage theory to calculate the damage degree and the residual life of key components of the wind turbine generator according to the load spectrum and the material characteristics of the wind turbine generator. This technique requires accurate load data and material parameters to be acquired and has limited applicability to complex nonlinear damage mechanisms and multiaxial load conditions.
Life prediction techniques based on state monitoring and operation monitoring: the technology utilizes fault early warning and development trend prediction information given by a state monitoring system and an operation monitoring system, and combines the traditional structural life assessment technical means to realize more comprehensive and accurate residual life assessment of actual operation equipment. The technology needs to acquire a large amount of real-time data and historical data, and has high requirements on data quality and analysis methods.
Life prediction techniques based on machine learning: the technology utilizes a machine learning model, such as linear regression, a support vector machine, a neural network, a random forest and the like, establishes a life prediction model according to historical data and current data of the wind turbine generator, and predicts the future life. This technique requires the acquisition of sufficient training data and test data, and requires high demands on model selection and parameter adjustment.
The technology has advantages and disadvantages, but cannot fully utilize multi-source data and various characteristics of the wind turbine generator, and cannot effectively process the problems of data incompleteness, uncertainty, nonlinearity and the like.
Disclosure of Invention
Aiming at the problems, the invention provides a multi-model fusion method for predicting the service life of a wind turbine, which can comprehensively use various data and models and improve the stability and reliability of service life prediction.
The multi-model fusion method for predicting the service life of the wind turbine generator is characterized by comprising the following steps of:
s101, data collection and preprocessing
Collecting data from various data sources of the running state, the environmental parameters and the fault records of the wind turbine generator, and performing pretreatment operations of data cleaning, data normalization and feature extraction to obtain a data set suitable for model input;
s102, model construction and model training
Selecting a proper machine learning model, namely model selection, according to different data characteristics and prediction targets, and respectively carrying out model training on a data set to obtain a plurality of sub-models;
s103, model fusion and model evaluation
Adopting one or more model fusion methods to synthesize the outputs of a plurality of sub-models to obtain a final life prediction result, and evaluating the performance and accuracy of the models by the methods of cross verification and error analysis;
s104, model application and model update
And deploying the model into a monitoring system of the wind farm, predicting the service life of the wind turbine at regular intervals, and adjusting and updating the model according to actual running conditions and feedback information.
It is further characterized by:
in the data collection step, various data are acquired from the wind turbine generator in real time or periodically by using a mode of a sensor, a monitoring system and a log file, and are stored in a database or a cloud platform;
in the data cleaning step, quality inspection and correction are carried out on data by using an anomaly detection, missing value filling and noise filtering method, and incomplete, inaccurate or irrelevant data are removed or corrected;
in the data normalization step, the data are subjected to scale adjustment and distribution transformation by using maximum and minimum value normalization, standardization and logarithmic transformation methods, so that the dimensional and deviation effects of the data are eliminated;
in the feature extraction step, the data is subjected to dimension reduction and transformation by using a principal component analysis, factor analysis and wavelet transformation method, and main features and information of the data are extracted;
in the model selection step, a proper machine learning model is selected according to the type and the distribution of data and predicted tasks and indexes;
in the model training step, a training set, a verification set, a corresponding loss function and an optimization algorithm are used for carrying out parameter initialization and iterative updating on the model, and a regularization and early stopping method is used for preventing the model from being over-fitted or under-fitted;
in the model fusion step, a proper model fusion method is selected according to the type and output of the submodels, and the complementarity and diversity among the submodels are utilized to improve the stability and reliability of life prediction;
in the model evaluation step, a prediction result of the model is evaluated by using a test set or new data and corresponding evaluation indexes and methods, and the performance and accuracy of the model are checked;
in the model updating step, the model is adjusted and updated according to the actual running condition and feedback information of the wind turbine generator.
After the technical scheme is adopted, the method can comprehensively utilize multi-source data of the wind turbine generator, such as running state data, environment parameter data and fault record data, extract effective information and characteristics of the data, and increase the utilization rate and value of the data;
the method can comprehensively utilize various machine learning models, such as linear regression, support vector machines, neural networks and random forests, construct a plurality of sub-models, and adopt a model fusion method, and utilize complementarity and diversity among the sub-models to improve the stability and reliability of life prediction;
according to the method, the service life of the wind turbine generator can be predicted periodically or in real time according to the running requirement and planning of the wind power plant, and a prediction result is displayed on a monitoring interface or sent to related personnel or departments so as to carry out subsequent analysis and processing;
according to the method, the model can be adjusted and updated according to the actual running condition and feedback information of the wind turbine generator, so that the model can keep the latest and optimal state, and the accuracy and the robustness of prediction are improved.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic illustration of data collection and preprocessing of the present invention;
FIG. 3 is a schematic diagram of the model construction and model training of the present invention;
FIG. 4 is a schematic diagram of the model fusion and model evaluation of the present invention;
FIG. 5 is a schematic diagram of a model application and model update of the present invention.
Detailed Description
The multi-model fusion method for predicting the service life of the wind turbine generator, as shown in fig. 1, comprises the following steps:
s101: data collection and preprocessing;
s102: model construction and model training;
s103: model fusion and model evaluation;
s104: model application and model update.
The specific implementation mode is as follows:
s101: data collection and preprocessing, as shown in fig. 2, this step includes the sub-steps of:
s1011: data collection
And various data are acquired from the wind turbine generator in real time or periodically by using a sensor, a monitoring system, a log file and the like, and are stored in a database or a cloud platform. For example, running state data such as rotation speed, power, temperature, vibration, noise and the like, environmental parameter data such as wind speed, wind direction, humidity, air pressure and the like, fault record data such as fault type, fault time and the like can be obtained from the wind turbine generator. The data can reflect the running condition and service life characteristics of the wind turbine generator and can also be used as input for model training and prediction;
s1012: data cleansing
And performing quality inspection and correction on the data by using methods such as anomaly detection, missing value filling, noise filtering and the like, and removing or correcting incomplete, inaccurate or irrelevant data. For example, outliers or outliers may be detected and deleted using a box plot or 3-sigma rule or the like; the method such as mean interpolation or K neighbor interpolation can be used for filling the missing value; noise may be filtered using a method such as a sliding average or kalman filter. The methods can improve the quality and usability of data and avoid errors of model training and prediction;
s1013: data normalization
And carrying out scale adjustment and distribution transformation on the data by using methods such as maximum and minimum value normalization, standardization, logarithmic transformation and the like, and eliminating the dimensional and bias effects of the data. For example, the data may be converted to values within the [0,1] interval using a maximum minimum normalization method; a normalization method can be used to convert the data into a normal distribution with a mean value of 0 and a standard deviation of 1; a logarithmic transformation method can be used to convert the data to logarithmic form, reducing the degree of skewness. The method can enable the data to meet the input requirement of the model, and can also improve the efficiency of model training and prediction;
s1014: feature extraction
The data is subjected to dimension reduction and transformation by using methods such as principal component analysis, factor analysis, wavelet transformation and the like, and main characteristics and information of the data are extracted. For example, a principal component analysis method may be used to convert high-dimensional features into low-dimensional features and retain a maximum amount of information; a factor analysis method can be used to convert multiple correlation features into a few uncorrelated factors and reveal potential causal relationships; the wavelet transform method may be used to transform the time domain features into frequency domain features and highlight local variations. These methods can reduce redundancy and complexity of data and can also extract effective information of data.
S102: model construction and training, as shown in fig. 3, this step includes the sub-steps of:
s1021: model selection
Based on different data characteristics and predicted targets, a suitable machine learning model is selected, such as Linear Regression (LR), support Vector Machines (SVM), neural Networks (NN), random Forests (RF), and the like. For example, an appropriate machine learning model may be selected according to the type and distribution of the data, and the task and index of the prediction, such as linear regression for fitting continuous value predictions of linear relationships, support vector machines for processing classification or regression predictions of nonlinear relationships, neural networks for fitting nonlinear predictions of complex relationships, random forests for processing ensemble learning predictions of high-dimensional features, and the like. The models can be correspondingly constructed and set according to the characteristics and the requirements of the data;
s1022: model training
And initializing parameters and updating iteration of the model by using a training set, a verification set, a corresponding loss function and an optimization algorithm, so that the model can fit data and achieve optimal performance. Meanwhile, the methods of regularization, early stopping and the like are used for preventing the model from being over fitted or under fitted. For example, the following parameters and methods may be used:
linear regression model: using mean square error as the loss function, gradient descent as the optimization algorithm, and L2 regularization to prevent overfitting. Parameters of the model comprise intercept items and slope items, and the parameters can be solved through a least square method;
support vector machine model: using a 0-1 loss function as the loss function, using a sequence minimum optimization method as the optimization algorithm, and using a cross-validation selection kernel function and penalty parameters. The parameters of the model comprise normal vectors and intercept terms of the classification hyperplane, and the types and parameters of the kernel function, and can be solved by maximizing interval;
neural network model: the cross entropy loss function is used as a loss function, a random gradient descent method is used as an optimization algorithm, and early stop is used to prevent overfitting. The parameters of the model comprise the weight and bias of each layer, and the type and parameters of the activation function can be updated by a back propagation algorithm;
random forest model: the number and depth of trees are selected using the genie opacity as a loss function, the adaptive enhancement method as an optimization algorithm, and cross-validation. The parameters of the model comprise the structure and splitting rule of each decision tree, and the proportion of the training set and the feature set generated by a self-service method and a random subspace method, and can be generated by an adaptive enhancement method.
S103: model fusion and evaluation as shown in fig. 4, this step includes the sub-steps of:
s1031: model fusion
One or more model fusion methods, such as weighted average, voting method, stacking method and the like, are adopted to synthesize the outputs of a plurality of sub-models, and the complementarity and diversity among the sub-models are utilized to improve the stability and reliability of life prediction; for example, the following methods may be used:
model fusion: and using a stacking method, taking the output of the four sub-models as new characteristics, and inputting the new characteristics into a logistic regression model to obtain a final life prediction result. The method can learn the sub-model output again by utilizing the logistic regression model, so that the accuracy and the robustness of prediction are improved;
s1032: model evaluation
Evaluating the prediction result of the model by using a test set or new data and corresponding evaluation indexes and methods, and checking the performance and accuracy of the model; for example, the following indices and methods may be used:
model evaluation: measuring the error and the correlation between the predicted value and the true value by using indexes such as mean square error, average absolute error, correlation coefficient and the like; and measuring the correctness, the completeness and the like of the classification prediction by using indexes such as confusion matrix, accuracy, recall rate and the like. These metrics and methods can reflect the merits and improvements of the model.
S104: model application and update, as shown in fig. 5, this step includes the sub-steps of:
s1041: model deployment
Converting the model into a format and an interface suitable for a wind power plant monitoring system, and embedding the model into the wind power plant monitoring system so that the model can receive data and output a prediction result; for example, the following frames and tools may be used:
model deployment: the models are converted into lightweight executable files or services by using frameworks such as TensorFlow Lite or ONNX and the like, and are embedded into a wind farm monitoring system. These frames and tools can make the model more compatible and portable;
s1042: model prediction
According to the running requirements and planning of the wind power plant, predicting the service life of the wind turbine generator set regularly or in real time, and displaying the prediction result on a monitoring interface or sending the prediction result to related personnel or departments so as to carry out subsequent analysis and processing; for example, the following methods may be used:
model prediction: according to the running targets and constraints of the wind power plant, such as generating capacity, cost, safety and the like, the service life of the wind turbine is predicted, and the prediction result is displayed on a monitoring interface in a chart or report form or is sent to related personnel or departments, such as operation and maintenance personnel, management personnel and the like. The method can enable the wind power plant to timely know the service life condition of the wind turbine generator and make corresponding decisions and operations;
s1043: model update
According to the actual running condition and feedback information of the wind turbine generator, the model is adjusted and updated; for example, the following methods may be used:
model updating: and adjusting and updating the model according to the actual running condition and feedback information of the wind turbine generator. For example, the model may be retrained or trimmed using the new data; or using methods such as transfer learning or incremental learning to enable the model to adapt to new data distributions or changes. These methods may enable the model to remain up-to-date and optimal, and improve accuracy and robustness of predictions.
By the method, the service life of the wind turbine generator can be predicted and optimized, and the performance degradation and life-prolonging dynamic adjustment of the wind turbine generator are realized, so that the running efficiency and economy of the wind power plant are improved.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (10)
1. The multi-model fusion method for predicting the service life of the wind turbine generator is characterized by comprising the following steps of:
s101, data collection and preprocessing
Collecting data from various data sources of the running state, the environmental parameters and the fault records of the wind turbine generator, and performing pretreatment operations of data cleaning, data normalization and feature extraction to obtain a data set suitable for model input;
s102, model construction and model training
Selecting a proper machine learning model, namely model selection, according to different data characteristics and prediction targets, and respectively carrying out model training on a data set to obtain a plurality of sub-models;
s103, model fusion and model evaluation
Adopting one or more model fusion methods to synthesize the outputs of a plurality of sub-models to obtain a final life prediction result, and evaluating the performance and accuracy of the models by the methods of cross verification and error analysis;
s104, model application and model update
And deploying the model into a monitoring system of the wind farm, predicting the service life of the wind turbine at regular intervals, and adjusting and updating the model according to actual running conditions and feedback information.
2. The multi-model fusion method for predicting service life of wind turbine generator set according to claim 1, wherein the method comprises the following steps: in the data collection step, various data are acquired from the wind turbine generator in real time or periodically by using a mode of a sensor, a monitoring system and a log file, and are stored in a database or a cloud platform.
3. The multi-model fusion method for predicting service life of wind turbine generator set according to claim 1, wherein the method comprises the following steps: in the data cleaning step, the quality inspection and correction are carried out on the data by using an anomaly detection method, a missing value filling method and a noise filtering method, and incomplete, inaccurate or irrelevant data are removed or corrected.
4. The multi-model fusion method for predicting service life of wind turbine generator set according to claim 1, wherein the method comprises the following steps: in the data normalization step, the data are subjected to scale adjustment and distribution transformation by using maximum and minimum value normalization, standardization and logarithmic transformation methods, and the dimensional and deviation effects of the data are eliminated.
5. The multi-model fusion method for predicting service life of wind turbine generator set according to claim 1, wherein the method comprises the following steps: in the feature extraction step, the data is subjected to dimension reduction and transformation by using principal component analysis, factor analysis and wavelet transformation methods, and main features and information of the data are extracted.
6. The multi-model fusion method for predicting service life of wind turbine generator set according to claim 1, wherein the method comprises the following steps: in the model selection step, an appropriate machine learning model is selected based on the type and distribution of data, and predicted tasks and metrics.
7. The multi-model fusion method for predicting service life of wind turbine generator set according to claim 1, wherein the method comprises the following steps: in the model training step, a training set, a verification set, a corresponding loss function and an optimization algorithm are used for carrying out parameter initialization and iterative updating on the model, and a regularization and early stop method is used for preventing the model from being over-fitted or under-fitted.
8. The multi-model fusion method for predicting service life of wind turbine generator set according to claim 1, wherein the method comprises the following steps: in the model fusion step, a proper model fusion method is selected according to the type and output of the submodels, and the complementarity and diversity among the submodels are utilized to improve the stability and reliability of life prediction.
9. The multi-model fusion method for predicting service life of wind turbine generator set according to claim 1, wherein the method comprises the following steps: in the model evaluation step, the prediction result of the model is evaluated using the test set or new data and the corresponding evaluation index and method, and the performance and accuracy of the model are checked.
10. The multi-model fusion method for predicting service life of wind turbine generator set according to claim 1, wherein the method comprises the following steps: in the model updating step, the model is adjusted and updated according to the actual running condition and feedback information of the wind turbine generator.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311075725.2A CN117077532A (en) | 2023-08-24 | 2023-08-24 | Multi-model fusion method for life prediction of wind turbine generator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311075725.2A CN117077532A (en) | 2023-08-24 | 2023-08-24 | Multi-model fusion method for life prediction of wind turbine generator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117077532A true CN117077532A (en) | 2023-11-17 |
Family
ID=88705723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311075725.2A Pending CN117077532A (en) | 2023-08-24 | 2023-08-24 | Multi-model fusion method for life prediction of wind turbine generator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117077532A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220178353A1 (en) * | 2019-04-01 | 2022-06-09 | Acciona Generación Renovable, S.A. | A method for estimating remaining useful life of components of an operational wind turbine |
-
2023
- 2023-08-24 CN CN202311075725.2A patent/CN117077532A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220178353A1 (en) * | 2019-04-01 | 2022-06-09 | Acciona Generación Renovable, S.A. | A method for estimating remaining useful life of components of an operational wind turbine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Marugán et al. | Reliability analysis of detecting false alarms that employ neural networks: A real case study on wind turbines | |
| Li et al. | Short-term wind power prediction based on data mining technology and improved support vector machine method: A case study in Northwest China | |
| De Benedetti et al. | Anomaly detection and predictive maintenance for photovoltaic systems | |
| CN111539550B (en) | Method, device, equipment and storage medium for determining working state of photovoltaic array | |
| Udo et al. | Data-driven predictive maintenance of wind turbine based on SCADA data | |
| Lindemann et al. | Anomaly detection and prediction in discrete manufacturing based on cooperative LSTM networks | |
| CN116032557B (en) | Method and device for updating deep learning model in network security anomaly detection | |
| CN117013527A (en) | Distributed photovoltaic power generation power prediction method | |
| CN117077532A (en) | Multi-model fusion method for life prediction of wind turbine generator | |
| Yang et al. | Fault early warning of wind turbine gearbox based on multi‐input support vector regression and improved ant lion optimization | |
| CN110709789A (en) | Method and apparatus for monitoring the condition of a subsystem within a renewable power generation device or microgrid | |
| CN117874467A (en) | Power equipment state monitoring method and system based on multi-source data fusion | |
| CN117728587B (en) | Real-time monitoring system and method for operation data of new energy power generation equipment | |
| CN118313812A (en) | Electric power big data acquisition and processing method based on machine learning | |
| CN117989074A (en) | Intelligent monitoring method for offshore wind turbine based on sensing calculation coordination | |
| Sanz-Bobi et al. | Intelligent system for a remote diagnosis of a photovoltaic solar power plant | |
| CN116384048A (en) | Method for predicting bearing life of wind generating set | |
| Pérez‐Campuzano et al. | Modelling damage equivalent loads in wind turbines from general operational signals: Exploration of relevant input selection methods using aeroelastic simulations | |
| CN118536082A (en) | Inverter fault prediction method and device based on artificial intelligence, terminal equipment and storage medium | |
| CN118017502A (en) | Digital twinning-based power distribution calculation power prediction method, system and medium | |
| CN117578440A (en) | Power grid load prediction method based on neural network | |
| CN117494009A (en) | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform | |
| CN116821610A (en) | Method for optimizing wind power generation efficiency by utilizing big data | |
| CN116826733A (en) | Photovoltaic power prediction method and system | |
| CN115598459A (en) | Power failure prediction method for 10kV feeder line fault of power distribution network |
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 |