CN110685868A - Wind turbine generator fault detection method and device based on improved gradient elevator - Google Patents
Wind turbine generator fault detection method and device based on improved gradient elevator Download PDFInfo
- Publication number
- CN110685868A CN110685868A CN201911025957.0A CN201911025957A CN110685868A CN 110685868 A CN110685868 A CN 110685868A CN 201911025957 A CN201911025957 A CN 201911025957A CN 110685868 A CN110685868 A CN 110685868A
- Authority
- CN
- China
- Prior art keywords
- parameter
- fault detection
- hyper
- wind turbine
- algorithm
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 claims abstract description 101
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 90
- 238000005457 optimization Methods 0.000 claims abstract description 69
- 238000010219 correlation analysis Methods 0.000 claims abstract description 26
- 238000011156 evaluation Methods 0.000 claims description 56
- 238000012549 training Methods 0.000 claims description 19
- 238000012795 verification Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 35
- 230000008569 process Effects 0.000 description 15
- 238000012423 maintenance Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 5
- 238000003066 decision tree Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 244000141353 Prunus domestica Species 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002015 leaf growth Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000002945 steepest descent method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
- Y02P70/50—Manufacturing or production processes characterised by the final manufactured product
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a wind turbine generator fault detection method and device based on an improved gradient elevator. The method comprises the following steps: acquiring a state feature set of the wind turbine generator, wherein the state feature set comprises at least one state feature; selecting target state characteristics from the state characteristic set according to a maximum information coefficient correlation analysis method; optimizing the hyperparameter of the gradient elevator algorithm according to a Bayesian hyperparameter optimization method to obtain a fault detection model, wherein the hyperparameter is an algorithm parameter of which the influence degree on the gradient elevator reaches a preset value; and predicting to obtain a fault detection result of the wind turbine generator according to the target state characteristics and the fault detection model.
Description
Technical Field
The invention relates to the field of wind power generation, in particular to a wind turbine generator fault detection method and device based on an improved gradient elevator.
Background
The wind power generation technology is an important direction in the field of new energy, and places with rich wind power resources are often located in remote areas, so that the wind turbine generator is prone to failure due to the fact that the external environment is severe. The failure of the gearbox of the wind turbine generator is the cause of longest downtime and greatest economic loss, and the failure of the gearbox directly influences the overall performance of equipment. Therefore, the method has important significance for carrying out fault detection and rapid fault identification on the gearbox component of the wind turbine generator, reducing the operation and maintenance cost of the wind turbine generator and improving the production efficiency of the whole wind field.
The machine learning method is widely applied to the field of wind turbine generator fault diagnosis, does not need to establish an accurate mathematical model and deep professional knowledge, only needs to analyze and process data, establishes a fault diagnosis model, and utilizes the data model to realize fault diagnosis. The gradient boosting algorithm is one of the classic machine learning algorithms. The gradient boosting algorithm is an algorithm integrating a weak learner into a strong learner, and training samples are adjusted according to the performance of a base learner, so that the strong learner is generated. The lifting algorithm is mainly used for classifying problems, the algorithm is adjusted by improving the weight occupied by the error sample, and the algorithm precision is improved. Because the lifting algorithm needs to know the lower limit of the weak classifier accuracy rate identification in advance, the application in the actual fault diagnosis is limited. With the continuous and deep research of experts on the lifting algorithm, the AdaBoost algorithm solves the practical application problem of the lifting algorithm; the GBDT algorithm effectively solves the problem of complexity of feature transformation; the XGboost algorithm adopts parallel processing, adds regular terms to the complexity of the tree model, and effectively avoids overfitting. These methods optimize the lifting algorithm model. However, since the traditional gradient boosting algorithm is very sensitive to abnormal values, when the data samples are abnormal points, the learning effect of the base classifier can be greatly interfered; the traditional lifting algorithm has low training efficiency and large memory occupation; in the actual process of diagnosing the fault of the wind turbine generator, due to the existence of more characteristic vectors, the traditional lifting algorithm has high complexity during calculation, and cannot process massive large data, so that the calculation efficiency and the real-time performance of fault detection are influenced.
Aiming at the problems of low computing efficiency, poor real-time performance and the like, the microsoft asia institute proposes a gradient hoist (LightGBM) algorithm. The algorithm generates a decision tree through a leaf node segmentation method, searches characteristic segmentation points based on a Histogram algorithm, supports parallel learning, can efficiently process big data, and effectively solves the problems of low calculation efficiency, poor real-time performance and the like.
However, the LightGBM algorithm has the disadvantage that the ideal fault detection performance can be obtained only by adjusting the parameters of the LightGBM model, and the conventional optimization algorithm is easily involved in the problems of local optimization, premature convergence and the like. Therefore, for fault detection under complex working conditions, the problem of real-time fault detection cannot be solved when the traditional optimization algorithm optimizes the LightGBM algorithm, and the fault detection rate is low, so that the operation and maintenance cost of the wind turbine generator and the production efficiency of a wind field are influenced.
Disclosure of Invention
The invention aims to provide a wind turbine generator fault detection method based on an improved gradient elevator, which selects target state characteristics through a maximum information coefficient correlation analysis method, performs hyperparametric optimization on a gradient elevator algorithm according to a Bayesian hyperparametric optimization method to obtain a fault detection model, and improves the efficiency and accuracy of wind turbine generator fault detection under complex working conditions, thereby reducing the operation and maintenance cost of the wind turbine generator and improving the production efficiency of a wind field.
The invention provides a wind turbine generator fault detection method based on an improved gradient elevator, which comprises the following steps:
acquiring a state feature set of the wind turbine generator, wherein the state feature set comprises at least one state feature;
selecting target state characteristics from the state characteristic set according to a maximum information coefficient correlation analysis method;
optimizing the hyperparameter of the gradient elevator algorithm according to a Bayesian hyperparameter optimization method to obtain a fault detection model, wherein the hyperparameter is an algorithm parameter of which the influence degree on the gradient elevator reaches a preset value;
and predicting to obtain a fault detection result of the wind turbine generator according to the target state characteristics and the fault detection model.
Further, selecting a target state feature from the state feature set according to a maximum information coefficient correlation analysis method, including:
calculating a correlation strength coefficient of the state characteristics and the faults of the wind turbine generator set by a maximum information coefficient correlation analysis method;
and selecting the state characteristics corresponding to the relevant intensity coefficients within the range of the preset coefficient interval as the target state characteristics according to the characteristic selection rule.
Further, the method for optimizing the hyperparameters of the gradient elevator algorithm according to the Bayesian hyperparameter optimization method to obtain a fault detection model comprises the following steps:
selecting an algorithm parameter with the influence degree reaching a preset value on the gradient elevator from the gradient elevator algorithm as a hyper-parameter;
optimizing the hyperparameters by adopting a Bayesian hyperparameter optimization method to obtain an optimal parameter combination;
and substituting the optimal parameter combination into a gradient elevator algorithm to obtain a fault detection model.
Further, a Bayesian super-parameter optimization method is adopted to optimize the super-parameters to obtain an optimal parameter combination, which comprises the following steps:
constructing an objective function according to a Bayesian optimization method;
obtaining a historical evaluation result of the target function, and constructing a probability model according to the historical evaluation result;
and mapping the hyper-parameters to the score probability of the target function in the probability model, and obtaining the optimal parameter combination by adopting a tree structure Parzen estimation method.
Further, when the combination of the optimal parameters is more than two, the method further comprises:
setting a parameter combination interval of the hyper-parameters;
acquiring a training data set and a verification data set of a probability model;
constructing an evaluation function according to the hyper-parameters, the training data set and the verification data set;
evaluating the classification results corresponding to all the optimal parameter combinations through an evaluation function to obtain evaluation results;
and selecting the optimal parameter combination from the optimal parameter combinations according to the evaluation result.
The invention provides a wind turbine generator fault detection device based on an improved gradient hoisting machine, which comprises:
the data acquisition module is used for acquiring a state characteristic set of the wind turbine generator, and the state characteristic set comprises at least one state characteristic;
the characteristic selection module is used for selecting target state characteristics from the state characteristic set according to a maximum information coefficient correlation analysis method;
the fault detection model parameter optimization module is used for optimizing the hyperparameters of the gradient elevator algorithm according to a Bayesian hyperparameter optimization method to obtain a fault detection model, and the hyperparameters are algorithm parameters which enable the influence degree of the gradient elevator to reach a preset value;
and the fault prediction module is used for predicting to obtain a fault detection result of the wind turbine generator according to the target state characteristics and the fault detection model.
Further, the feature selection module comprises:
the correlation strength calculation unit is used for calculating a correlation strength coefficient of the state characteristics and the faults of the wind turbine generator through a maximum information coefficient correlation analysis method;
and the fault detection model parameter selection unit is used for selecting the state characteristics corresponding to the relevant intensity coefficients within the range of the preset coefficient interval as the target state characteristics according to the characteristic selection rule.
Further, the fault detection model parameter optimization module comprises:
the super-parameter selecting unit is specifically used for selecting an algorithm parameter with the influence degree reaching a preset value on the gradient elevator from the gradient elevator algorithm as a super-parameter;
the super-parameter optimization unit is also used for optimizing the super-parameters by adopting a Bayesian super-parameter optimization method to obtain an optimal parameter combination;
and the model construction unit is also used for substituting the optimal parameter combination into a gradient elevator algorithm to obtain a fault detection model.
Further, in the above-mentioned case,
the hyper-parameter optimization unit is specifically used for constructing an objective function according to a Bayesian optimization method;
the hyper-parameter optimization unit is also used for acquiring the historical evaluation result of the objective function and constructing a probability model according to the historical evaluation result;
and the hyper-parameter optimization unit is also used for mapping the hyper-parameters to the score probability of the target function in the probability model, and obtaining the optimal parameter combination by adopting a tree structure Parzen estimation method.
Further, when the optimal parameters are two or more, the model building module further includes:
the parameter evaluation unit is used for setting a parameter combination interval of the hyper-parameters;
the parameter evaluation unit is also used for acquiring a training data set and a verification data set of the probability model;
the parameter evaluation unit is also used for constructing an evaluation function according to the hyper-parameters, the training data set and the verification data set;
the parameter evaluation unit is also used for evaluating the classification results corresponding to all the optimal parameter combinations through the evaluation function to obtain evaluation results;
and the parameter evaluation unit is also used for selecting the optimal parameter combination from the optimal parameter combinations according to the evaluation result.
According to the method and the device for detecting the fault of the wind turbine generator based on the improved gradient elevator, the state parameters of the wind turbine generator are obtained, the target state characteristics are selected from the state parameters according to the maximum information coefficient correlation analysis method, the hyperparameters of the gradient elevator algorithm are optimized according to the Bayesian hyperparameter optimization method, the fault detection model is obtained, the hyperparameters are algorithm parameters with the influence degree reaching the preset value on the gradient elevator, and the fault detection result of the wind turbine generator is obtained through prediction according to the target state characteristics and the fault detection model. In the invention, the target state characteristics are selected by a maximum information coefficient correlation analysis method, so that part of state characteristics in the state characteristic set are deleted and selected, and the time consumption in the fault detection process is reduced; and the gradient elevator algorithm is subjected to hyper-parameter optimization according to a Bayesian hyper-parameter optimization method to obtain a fault detection model, so that the accuracy of fault detection by using the fault detection model is improved. Therefore, the wind turbine generator fault detection method improves the efficiency and accuracy of wind turbine generator fault detection under complex working conditions, thereby reducing the operation and maintenance cost of the wind turbine generator and improving the production efficiency of a wind field.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed in the prior art and the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic flow chart of an embodiment of a wind turbine generator fault detection method based on an improved gradient hoist according to the present invention;
FIG. 2 is a comparison of the accuracy of fault detection provided by the present invention;
FIG. 3 is a schematic flow chart of another embodiment of the wind turbine generator fault detection method based on the improved gradient hoisting machine according to the present invention;
FIG. 4 is a schematic flow chart of a wind turbine generator fault detection method based on an improved gradient hoist according to another embodiment of the present invention;
FIG. 5 is a schematic structural diagram of an embodiment of a wind turbine generator fault detection device based on an improved gradient hoisting machine provided by the invention;
FIG. 6 is a schematic structural diagram of another embodiment of the wind turbine generator fault detection device based on the improved gradient hoisting machine provided by the invention;
FIG. 7 is a schematic structural diagram of a wind turbine generator fault detection device based on an improved gradient hoist according to another embodiment of the present invention;
fig. 8 is a schematic structural diagram of a wind turbine generator fault detection device based on an improved gradient hoist according to still another embodiment of the present invention.
Detailed Description
The core of the invention is to provide a wind turbine generator fault detection method and device based on an improved gradient elevator, target state characteristics are selected through a maximum information coefficient correlation analysis method, and a Bayesian super-parameter optimization method is used for carrying out super-parameter optimization on a gradient elevator algorithm to obtain a fault detection model, so that the efficiency and accuracy of wind turbine generator fault detection under complex working conditions are improved, the operation and maintenance cost of the wind turbine generator is reduced, and the production efficiency of a wind field is improved.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a wind turbine generator fault detection method based on an improved gradient elevator, including:
101. acquiring a state feature set of the wind turbine generator, wherein the state feature set comprises at least one state feature;
in this embodiment, a wind farm generally includes a large number of wind turbines, And in order to facilitate regulation And monitoring of the wind turbines, a SCADA (Supervisory Control And data acquisition) system is used to collect And monitor data of each wind turbine, the obtained SCADA data includes multiple types, And feature extraction including data normalization And missing value processing is performed on the SCADA data through expert experience, so that state features with high information abundance And interpretability are obtained, And the numerous state features are arranged into a state feature set, for example, the state features in the state feature set specifically include a nacelle vibration direction, a wind speed, a rotor rotation speed, an environment temperature, a nacelle temperature, a pitch angle, active power, And the like.
102. Selecting target state characteristics from the state characteristic set according to a maximum information coefficient correlation analysis method;
in this embodiment, for different fault types, parameters to be used are different, and therefore, a maximum information coefficient correlation analysis method needs to be used to select, from the state feature set, a state feature whose detected fault correlation degree meets a condition as a target state feature.
103. Optimizing the superparameter of the gradient elevator algorithm according to a Bayesian superparameter optimization method to obtain a fault detection model;
in this embodiment, the Gradient hoist (LightGBM) algorithm is a Decision Tree algorithm-based distributed Gradient hoist (GBDT) framework proposed in 2017. The GBDT algorithm can process discretization information data, but only utilizes first derivative information when optimizing a loss function, and residual errors of an n-1 tree are needed when an nth tree is trained, so that parallelization operation is difficult to realize. The XGboost algorithm is characterized in that second-order derivatives are introduced to perform Taylor expansion on a loss function, L2 regularization of parameters and the like to integrally evaluate the complexity of a model, parallel calculation is supported, and the accuracy of the algorithm is improved. Based on the former, the LightGBM provides a Hisgram-based decision tree algorithm, utilizes a leaf growth strategy with depth limitation, and adopts multiple linesAnd the lightGBM has low memory occupancy rate due to the optimization of the program, can process large-scale data, and is more efficient and higher in precision. Given a supervised learning data set
The purpose of LightGBM is to find a mapping relation
To approximate the function f (x) such that the desired value of the loss function Ψ (y, f (x)) is minimized, as follows:
LightGBM utilizing regression trees
To approximate the final model, the formula of the final model is as follows;
the regression tree may be represented in another form, namely wq(x)Q ∈ {1, 2.,. J }, J represents the number of leaf nodes, q represents the decision rule of the tree, w represents the sample weight, and the loss function LtCan be expressed as:
the conventional LightGBM employs a steepest descent method, which considers only the gradient of the penalty function. In LightGBM, Newton's method is used to quickly approximate the target function, simplifying the loss function LtAfter that, it is possible to obtain:
wherein, gi、hiRepresenting a first order loss function and a second order loss function, respectively.Namely, it is
By means of IjTo represent the sample set of leaf j, the loss function LtThe method can be as follows:
given the structure q (x) of the tree, the optimal weight sum L for each leaf nodeKThe limit values of (c) can be obtained by quadratic programming:
the gain calculation formula is:
the LightGBM algorithm prunes the tree using the maximum tree depth and avoids overfitting, and adopts multithread optimization to improve efficiency and save time.
The main parameters affecting the model performance in the LightGBM algorithm include the number of leaves, the learning rate, etc., and these parameters cannot be obtained through training and need to be manually adjusted, and these parameters are called hyper-parameters. The Bayesian optimization idea is that a probability model is formed by using the results according to the past evaluation results of the objective function, and the hyper-parameters are mapped to the score probability of the objective function to find the optimal parameters, so that the hyper-parameters of the gradient elevator algorithm can be optimized according to the Bayesian hyper-parameter optimization method, and the LightGBM algorithm obtained after the hyper-parameters are optimized is a fault detection model.
104. And predicting to obtain a fault detection result of the wind turbine generator according to the target state characteristics and the fault detection model.
In this embodiment, after the target state characteristics are calculated by the fault detection model, the fault detection result of the wind turbine generator can be predicted. According to the result of detecting the gearbox fault after the AdaBoost, the GBDT, the LightGBM algorithm and the LightGBM algorithm are optimized by the Bayesian hyper-parameter (namely a fault detection model), the AdaBoost, the GBDT and the LightGBM algorithm are found to have the precision mean values of 0.917, 0.922 and 0.926 respectively, and the correct recognition rate mean values of the AdaBoost, the GBDT and the LightGBM algorithm are 0.853, 0.861 and 0.902 respectively, the GBDT algorithm combines a decision tree with a lifting algorithm, the GBDT is improved in fault diagnosis precision compared with the AdaBoost, and the LightGBM algorithm adopts multi-thread optimization, high efficiency and best performance. As shown in fig. 2, it is a comparison graph of algorithm accuracy of the LightGBM algorithm and the LightGBM algorithm after being optimized by the bayesian hyperparameter (i.e., the LightGBM _ TPE), where the accuracy of the LightGBM algorithm is about 0.94, and the accuracy of the LightGBM _ TPE is about 0.97, and the accuracy of fault detection is significantly improved.
In the embodiment of the invention, the target state characteristics are selected through a maximum information coefficient correlation analysis method, so that part of state characteristics in the state characteristic set are deleted and selected, and the time consumption of the fault detection process is reduced; and the gradient elevator algorithm is subjected to hyper-parameter optimization according to a Bayesian hyper-parameter optimization method to obtain a fault detection model, so that the accuracy of fault detection by using the fault detection model is improved. Therefore, the wind turbine generator fault detection method improves the efficiency and accuracy of wind turbine generator fault detection under complex working conditions, thereby reducing the operation and maintenance cost of the wind turbine generator and improving the production efficiency of a wind field.
In the embodiment shown in fig. 1, how the maximum information coefficient correlation analysis method in step 102 specifically implements target state feature selection is described below by an embodiment, optionally, in some embodiments of the present invention, selecting a target state feature from a state feature set according to the maximum information coefficient correlation analysis method includes:
calculating a correlation strength coefficient of the state characteristics and the faults of the wind turbine generator set by a maximum information coefficient correlation analysis method;
and selecting the state characteristics corresponding to the relevant intensity coefficients within the range of the preset coefficient interval as the target state characteristics according to the characteristic selection rule.
In the embodiment of the invention, the maximum information coefficient theory is used for measuring the strength of numerical association between two characteristics. If X is a discrete variable, the information entropy of X is as follows:
conditional entropy refers to the conditional probability distribution of X occurrence when a random variable Y occurs:
H(X|Y)＝-∑y∈YP(y)∑x∈XP(x|y)log2P(x|y)
subtracting the conditional probability distribution of X from the information entropy of X to obtain mutual information as follows:
for a random variable X, the maximum information coefficient of Y is:
where | X |. | Y | represents the number of grids. The parameter B represents the total amount of data to the power of 0.6.
The maximum information coefficient ranges between 0 and 1, the closer the value is to 1, the stronger the correlation between the two variables and vice versa.
Therefore, based on the maximum information coefficient correlation analysis method, the correlation strength coefficient of the state characteristic and the fault of the wind turbine generator can be calculated, a characteristic selection rule is set, the characteristic selection rule can be a preset coefficient interval in which the correlation strength coefficient is preset, and the state characteristic is selected as the target state characteristic as long as the correlation strength coefficient corresponding to the state characteristic is within the range of the preset coefficient interval. Therefore, the state feature associated with fault detection can be selected from the plurality of state features as the target state feature, and time consumption caused by excessive state features in the fault detection process is reduced.
In the embodiment shown in fig. 1, only the theory of the bayesian hyperparameter optimization method is described in step 103, and the manner of obtaining the hyperparameter and how to obtain the fault detection model are not specifically described, and step 103 is specifically described below by using the embodiment.
As shown in fig. 3, an embodiment of the present invention provides a wind turbine generator fault detection method based on an improved gradient elevator, including:
301. acquiring a state feature set of the wind turbine generator, wherein the state feature set comprises at least one state feature;
see step 101 for details.
302. Selecting target state characteristics from the state characteristic set according to a maximum information coefficient correlation analysis method;
for details, refer to the description of step 102 in the above embodiment.
303. Selecting an algorithm parameter with the influence degree reaching a preset value on the gradient elevator from the gradient elevator algorithm as a hyper-parameter;
in this embodiment, the main parameters affecting the model performance in the LightGBM algorithm include the number of leaves, the learning rate, etc., and these parameters cannot be obtained through training and need to be manually adjusted, and these parameters are called hyper-parameters.
304. Optimizing the hyperparameters by adopting a Bayesian hyperparameter optimization method to obtain an optimal parameter combination;
in this embodiment, the optimizing the hyper-parameters by using the bayesian hyper-parameter optimization method specifically includes:
(1) constructing an objective function according to a Bayesian optimization method;
(2) acquiring a historical evaluation result of the target function, and constructing a probability model according to the historical evaluation result;
(3) and mapping the hyper-parameters to the score probability of the objective function in the probability model, and obtaining the optimal parameter combination expressed as P (Y | X) by adopting a Tree-structured Parzen Estimator (TPE).
The selection of the probability model can be divided into a Gaussian process, a random forest regression and a Tree-structured Parzen Estimator (TPE), and the TPE obtains a good result, so that the Bayes Tree-structured Parzen Estimator is adopted to perform the hyperparametric optimization on the LightGBM.
305. Substituting the optimal parameter combination into a gradient elevator algorithm to obtain a fault detection model;
in this embodiment, after the optimal parameter combination is obtained, the optimal parameter combination is substituted into the gradient elevator algorithm, so that the hyper-parameter optimization of the gradient elevator algorithm is realized, and the fault detection model is obtained.
306. And predicting to obtain a fault detection result of the wind turbine generator according to the target state characteristics and the fault detection model.
See step 104 for details.
In the above embodiment shown in fig. 3, there may be a plurality of optimal parameter combinations, and then different optimal parameter combinations need to be verified, so as to select an optimal solution, the specific method is as follows:
optionally, as shown in fig. 4, in some embodiments of the present invention, when the optimal parameters are combined into two or more parameters, the method further includes:
401. setting a parameter combination interval of the hyper-parameters;
402. acquiring a training data set and a verification data set of a probability model;
403. constructing an evaluation function according to the hyper-parameters, the training data set and the verification data set;
404. evaluating the classification results corresponding to all the optimal parameter combinations through an evaluation function to obtain evaluation results;
405. and selecting the optimal parameter combination from the optimal parameter combinations according to the evaluation result.
In the embodiment of the present invention, θ is assumed to be { θ ═ θ1、θ2…θnDenotes the hyper-parameter in the machine learning algorithm A (e.g. LightGBM), DtrainThe data set represents a training data set, DvalidThe dataset represents a validation dataset (i.e., hyper-parametric optimization), both of which are independently distributed. With L (A, theta, D)valid,Dtrain) To express the verification loss of the algorithm A, the optimization problem is generally solved by K-fold cross verification, and an evaluation function is constructed as follows:
the method comprises the steps of firstly setting a parameter combination interval for selecting hyper-parameters, continuously training a model through a training data set in the parameter optimization process, evaluating classification results obtained by all optimal parameter combinations through an evaluation function f (theta) to obtain evaluation results, and selecting the optimal parameter combination from the optimal parameter combinations according to the evaluation results.
In the above embodiment, a wind turbine generator fault detection method based on an improved gradient hoisting machine is described in detail, and a wind turbine generator fault detection device based on an improved gradient hoisting machine applying the method is described in detail by the following embodiment, specifically as follows:
as shown in fig. 5, an embodiment of the present invention provides a wind turbine generator fault detection apparatus based on an improved gradient elevator, including:
the data acquisition module 501 is configured to acquire a status feature set of the wind turbine generator, where the status feature set includes at least one status feature;
a feature selection module 502, configured to select a target state feature from the state feature set according to a maximum information coefficient correlation analysis method;
the fault detection model parameter optimization module 503 is configured to optimize a hyperparameter of the gradient elevator algorithm according to a bayesian hyperparameter optimization method to obtain a fault detection model, where the hyperparameter is an algorithm parameter whose influence degree on the gradient elevator reaches a preset value;
and the fault prediction module 504 is configured to predict a fault detection result of the wind turbine generator according to the target state characteristic and the fault detection model.
In the embodiment of the invention, the characteristic selection module 502 selects the target state characteristics from the state parameter set of the wind turbine generator acquired by the data acquisition module 501 through a maximum information coefficient correlation analysis method, so that part of the state characteristics are deleted and selected, and the time consumption in the fault detection process is reduced; and the fault detection model parameter optimization module 503 performs the hyperparametric optimization on the gradient elevator algorithm according to the Bayesian hyperparametric optimization method to obtain a fault detection model, and the fault prediction module 504 calculates the fault detection result of the wind turbine generator system according to the target state characteristics and the fault detection model, so that the accuracy of fault detection by using the fault detection model is improved. Therefore, the wind turbine generator fault detection method improves the efficiency and accuracy of wind turbine generator fault detection under complex working conditions, thereby reducing the operation and maintenance cost of the wind turbine generator and improving the production efficiency of a wind field.
Optionally, in combination with the embodiment shown in fig. 5, as shown in fig. 6, in some embodiments of the present invention, the feature extracting module 502 includes:
the correlation strength calculation unit 601 is configured to calculate a correlation strength coefficient between the state characteristic and the fault of the wind turbine generator by using a maximum information coefficient correlation analysis method;
the fault detection model parameter selecting unit 602 is configured to select, according to a feature selection rule, a state feature corresponding to a correlation strength coefficient within a preset coefficient interval as a target state feature.
Optionally, in combination with the embodiment shown in fig. 5 or fig. 6, as shown in fig. 7, the fault detection model parameter optimization module 503 includes:
a hyper-parameter selecting unit 701, configured to select, as a hyper-parameter, an algorithm parameter that has an influence degree on the gradient elevator reaching a preset value from the gradient elevator algorithms;
the hyper-parameter optimization unit 702 is further configured to optimize the hyper-parameters by using a bayesian hyper-parameter optimization method to obtain an optimal parameter combination;
the model building unit 703 is further configured to substitute the optimal parameter combination into a gradient elevator algorithm to obtain a fault detection model.
Alternatively, as shown in connection with figure 7,
the hyper-parameter optimization unit 702 is specifically configured to construct an objective function according to a bayesian optimization method;
the hyper-parameter optimization unit 702 is further configured to obtain a historical evaluation result of the objective function, and construct a probability model according to the historical evaluation result;
the hyper-parameter optimization unit 702 is further configured to map the hyper-parameters to the score probability of the target function in the probability model, and obtain an optimal parameter combination by using a tree structure Parzen estimation method.
Optionally, with reference to the embodiment shown in fig. 7, as shown in fig. 8, when the optimal parameters are combined into two or more parameters, the fault detection model parameter optimization module 503 further includes:
a parameter evaluation unit 801 configured to set a parameter combination section of the hyper-parameter;
the parameter evaluation unit 801 is further configured to obtain a training data set and a verification data set of the probabilistic model;
the parameter evaluation unit 801 is further configured to construct an evaluation function according to the hyper-parameters, the training data set and the verification data set;
the parameter evaluation unit 801 is further configured to evaluate the classification results corresponding to all the optimal parameter combinations through an evaluation function to obtain evaluation results;
the parameter evaluation unit 801 is further configured to select an optimal parameter combination from the optimal parameter combinations according to the evaluation result.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A wind turbine generator fault detection method based on an improved gradient elevator is characterized by comprising the following steps:
acquiring a state feature set of the wind turbine generator, wherein the state feature set comprises at least one state feature;
selecting target state features from the state feature set according to a maximum information coefficient correlation analysis method;
optimizing the hyperparameter of the gradient elevator algorithm according to a Bayesian hyperparameter optimization method to obtain a fault detection model, wherein the hyperparameter is an algorithm parameter of which the influence degree on the gradient elevator reaches a preset value;
and predicting to obtain a fault detection result of the wind turbine generator according to the target state characteristics and the fault detection model.
2. The method of claim 1, wherein selecting a target state feature from the state feature set according to a maximum information coefficient correlation analysis method comprises:
calculating a correlation strength coefficient of the state characteristics and the faults of the wind turbine generator set by a maximum information coefficient correlation analysis method;
and selecting the state characteristics corresponding to the relevant intensity coefficients within the range of the preset coefficient interval as the target state characteristics according to the characteristic selection rule.
3. The method according to claim 1 or 2, wherein the optimizing the hyper-parameters of the gradient elevator algorithm according to the bayesian hyper-parameter optimization method to obtain the fault detection model comprises:
selecting an algorithm parameter with the influence degree reaching a preset value on the gradient elevator from the gradient elevator algorithm as a hyper-parameter;
optimizing the hyper-parameters by adopting a Bayesian hyper-parameter optimization method to obtain an optimal parameter combination;
and substituting the optimal parameter combination into the gradient elevator algorithm to obtain a fault detection model.
4. The method of claim 3, wherein said optimizing said hyper-parameters using a Bayesian hyper-parameter optimization method to obtain an optimal parameter combination comprises:
constructing an objective function according to a Bayesian optimization method;
obtaining a historical evaluation result of the target function, and constructing a probability model according to the historical evaluation result;
and mapping the hyper-parameters to the score probability of the target function in the probability model, and obtaining the optimal parameter combination by adopting a tree structure Parzen estimation method.
5. The method of claim 4, wherein when the optimal parameter combination is two or more, the method further comprises:
setting a parameter combination interval of the hyper-parameters;
acquiring a training data set and a verification data set of the probability model;
constructing an evaluation function according to the hyper-parameters, the training data set and the verification data set;
evaluating the classification results corresponding to all the optimal parameter combinations through the evaluation function to obtain evaluation results;
and selecting the optimal parameter combination from the optimal parameter combinations according to the evaluation result.
6. The utility model provides a wind turbine generator system fault detection device based on improve gradient lifting machine which characterized in that includes:
the system comprises a data acquisition module, a state feature set generation module and a state feature set generation module, wherein the data acquisition module is used for acquiring the state feature set of the wind turbine generator, and the state feature set comprises at least one state feature;
the characteristic selection module is used for selecting target state characteristics from the state characteristic set according to a maximum information coefficient correlation analysis method;
the fault detection model parameter optimization module is used for optimizing the hyperparameters of the gradient elevator algorithm according to a Bayesian hyperparameter optimization method to obtain a fault detection model, and the hyperparameters are algorithm parameters with the influence degree reaching a preset value on the gradient elevator;
and the fault prediction module is used for predicting to obtain a fault detection result of the wind turbine generator according to the target state characteristics and the fault detection model.
7. The apparatus of claim 6, wherein the feature extraction module comprises:
the correlation strength calculation unit is used for calculating the correlation strength coefficient of the state characteristic and the fault of the wind turbine generator through a maximum information coefficient correlation analysis method;
and the fault detection model characteristic selection unit is used for selecting the state characteristic corresponding to the relevant strength coefficient within the range of the preset coefficient interval as the target state characteristic according to the characteristic selection rule.
8. The apparatus of claim 6 or 7, wherein the fault detection model parameter optimization module comprises:
the super-parameter selecting unit is specifically used for selecting an algorithm parameter with the influence degree reaching a preset value on the gradient elevator from the gradient elevator algorithm as a super-parameter;
the super-parameter optimization unit is also used for optimizing the super-parameters by adopting a Bayesian super-parameter optimization method to obtain an optimal parameter combination;
and the model construction unit is also used for substituting the optimal parameter combination into the gradient elevator algorithm to obtain a fault detection model.
9. The apparatus of claim 8,
the hyper-parameter optimization unit is specifically used for constructing an objective function according to a Bayesian optimization method;
the hyper-parameter optimization unit is further used for obtaining a historical evaluation result of the objective function and constructing a probability model according to the historical evaluation result;
the hyper-parameter optimization unit is further configured to map the hyper-parameters to the score probability of the objective function in the probability model, and obtain an optimal parameter combination by using a tree structure Parzen estimation method.
10. The apparatus of claim 9, wherein when the optimal parameters are two or more in combination, the model construction module further comprises:
the parameter evaluation unit is used for setting a parameter combination interval of the hyper-parameter;
the parameter evaluation unit is further used for acquiring a training data set and a verification data set of the probability model;
the parameter evaluation unit is further used for constructing an evaluation function according to the hyper-parameters, the training data set and the verification data set;
the parameter evaluation unit is further configured to evaluate the classification results corresponding to all the optimal parameter combinations through the evaluation function to obtain evaluation results;
and the parameter evaluation unit is also used for selecting the optimal parameter combination from the optimal parameter combinations according to the evaluation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911025957.0A CN110685868A (en) | 2019-10-25 | 2019-10-25 | Wind turbine generator fault detection method and device based on improved gradient elevator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911025957.0A CN110685868A (en) | 2019-10-25 | 2019-10-25 | Wind turbine generator fault detection method and device based on improved gradient elevator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110685868A true CN110685868A (en) | 2020-01-14 |
Family
ID=69114788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911025957.0A Pending CN110685868A (en) | 2019-10-25 | 2019-10-25 | Wind turbine generator fault detection method and device based on improved gradient elevator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110685868A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488946A (en) * | 2020-04-28 | 2020-08-04 | 东南大学 | Radar servo system fault diagnosis method based on information fusion |
| CN112100575A (en) * | 2020-09-11 | 2020-12-18 | 石化盈科信息技术有限责任公司 | Equipment state trend prediction method and device, computer equipment and storage medium |
| CN112598148A (en) * | 2020-09-30 | 2021-04-02 | 新天绿色能源股份有限公司 | Fan variable pitch motor temperature fault early warning method based on collaborative expression and LightGBM algorithm |
| CN112682273A (en) * | 2020-12-31 | 2021-04-20 | 长沙理工大学 | Wind turbine generator fault detection method based on cost-sensitive lightweight gradient elevator |
| CN112734130A (en) * | 2021-01-21 | 2021-04-30 | 河北工业大学 | Fault early warning method for double-fed fan main shaft |
| CN112990255A (en) * | 2020-12-23 | 2021-06-18 | 中移（杭州）信息技术有限公司 | Method and device for predicting equipment failure, electronic equipment and storage medium |
| CN113095390A (en) * | 2021-04-02 | 2021-07-09 | 东北大学 | Walking stick motion analysis system and method based on cloud database and improved ensemble learning |
| CN113326883A (en) * | 2021-06-03 | 2021-08-31 | 中创三优（北京）科技有限公司 | Training method, device and medium for power utilization rate prediction model of charging station |
| CN113339208A (en) * | 2021-07-21 | 2021-09-03 | 申能新能源(青海)有限公司 | Method for selecting abnormal vibration fragments of wind turbine generator |
| CN113361186A (en) * | 2021-04-28 | 2021-09-07 | 山东大学 | Complete data-based wind turbine generator fault diagnosis method |
| CN113378908A (en) * | 2021-06-04 | 2021-09-10 | 浙江大学 | Heating ventilation air conditioning system fault diagnosis method based on LightGBM algorithm and grid search algorithm |
| CN113505639A (en) * | 2021-05-28 | 2021-10-15 | 北京化工大学 | TPE-XGboost-based rotating machine multi-parameter health state evaluation method |
| CN114330934A (en) * | 2022-03-09 | 2022-04-12 | 南方电网数字电网研究院有限公司 | Model parameter self-adaptive GRU new energy short-term power generation power prediction method |
| CN116861218A (en) * | 2023-07-25 | 2023-10-10 | 上海华菱电站成套设备股份有限公司 | Mine winder key equipment state monitoring early warning system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8386401B2 (en) * | 2008-09-10 | 2013-02-26 | Digital Infuzion, Inc. | Machine learning methods and systems for identifying patterns in data using a plurality of learning machines wherein the learning machine that optimizes a performance function is selected |
| CN108932580A (en) * | 2018-06-05 | 2018-12-04 | 浙江运达风电股份有限公司 | Wind turbines pitch variable bearings wear monitoring and method for early warning based on data modeling |
| CN109858631A (en) * | 2019-02-02 | 2019-06-07 | 清华大学 | The automaton learning system and method for stream data analysis for concept migration |
| CN110032944A (en) * | 2019-03-20 | 2019-07-19 | 国网电力科学研究院(武汉)能效测评有限公司 | A kind of electric load feature extracting method and system |
| CN110135064A (en) * | 2019-05-15 | 2019-08-16 | 上海交通大学 | A kind of generator rear bearing temperature fault prediction technique, system and controller |
-
2019
- 2019-10-25 CN CN201911025957.0A patent/CN110685868A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8386401B2 (en) * | 2008-09-10 | 2013-02-26 | Digital Infuzion, Inc. | Machine learning methods and systems for identifying patterns in data using a plurality of learning machines wherein the learning machine that optimizes a performance function is selected |
| CN108932580A (en) * | 2018-06-05 | 2018-12-04 | 浙江运达风电股份有限公司 | Wind turbines pitch variable bearings wear monitoring and method for early warning based on data modeling |
| CN109858631A (en) * | 2019-02-02 | 2019-06-07 | 清华大学 | The automaton learning system and method for stream data analysis for concept migration |
| CN110032944A (en) * | 2019-03-20 | 2019-07-19 | 国网电力科学研究院(武汉)能效测评有限公司 | A kind of electric load feature extracting method and system |
| CN110135064A (en) * | 2019-05-15 | 2019-08-16 | 上海交通大学 | A kind of generator rear bearing temperature fault prediction technique, system and controller |
Non-Patent Citations (1)
| Title |
|---|
| FLYINGWARRIOR: "自动机器学习超参数调整（贝叶斯优化）", 《HTTPS://WWW.CNBLOGS.COM/WMX24/P/10025600.HTML》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488946A (en) * | 2020-04-28 | 2020-08-04 | 东南大学 | Radar servo system fault diagnosis method based on information fusion |
| CN112100575A (en) * | 2020-09-11 | 2020-12-18 | 石化盈科信息技术有限责任公司 | Equipment state trend prediction method and device, computer equipment and storage medium |
| CN112598148A (en) * | 2020-09-30 | 2021-04-02 | 新天绿色能源股份有限公司 | Fan variable pitch motor temperature fault early warning method based on collaborative expression and LightGBM algorithm |
| CN112990255A (en) * | 2020-12-23 | 2021-06-18 | 中移（杭州）信息技术有限公司 | Method and device for predicting equipment failure, electronic equipment and storage medium |
| CN112990255B (en) * | 2020-12-23 | 2024-05-28 | 中移（杭州）信息技术有限公司 | Device failure prediction method, device, electronic device and storage medium |
| CN112682273A (en) * | 2020-12-31 | 2021-04-20 | 长沙理工大学 | Wind turbine generator fault detection method based on cost-sensitive lightweight gradient elevator |
| CN112734130A (en) * | 2021-01-21 | 2021-04-30 | 河北工业大学 | Fault early warning method for double-fed fan main shaft |
| CN112734130B (en) * | 2021-01-21 | 2022-06-10 | 河北工业大学 | Fault early warning method for double-fed fan main shaft |
| CN113095390A (en) * | 2021-04-02 | 2021-07-09 | 东北大学 | Walking stick motion analysis system and method based on cloud database and improved ensemble learning |
| CN113095390B (en) * | 2021-04-02 | 2024-06-04 | 东北大学 | Walking stick movement analysis method based on cloud database and improved ensemble learning |
| CN113361186A (en) * | 2021-04-28 | 2021-09-07 | 山东大学 | Complete data-based wind turbine generator fault diagnosis method |
| CN113505639A (en) * | 2021-05-28 | 2021-10-15 | 北京化工大学 | TPE-XGboost-based rotating machine multi-parameter health state evaluation method |
| CN113505639B (en) * | 2021-05-28 | 2024-03-22 | 北京化工大学 | Rotary machine multi-parameter health state assessment method based on TPE-XGBoost |
| CN113326883A (en) * | 2021-06-03 | 2021-08-31 | 中创三优（北京）科技有限公司 | Training method, device and medium for power utilization rate prediction model of charging station |
| CN113326883B (en) * | 2021-06-03 | 2022-08-30 | 中创三优（北京）科技有限公司 | Training method, device and medium for power utilization rate prediction model of charging station |
| CN113378908A (en) * | 2021-06-04 | 2021-09-10 | 浙江大学 | Heating ventilation air conditioning system fault diagnosis method based on LightGBM algorithm and grid search algorithm |
| CN113339208B (en) * | 2021-07-21 | 2023-08-22 | 申能新能源(青海)有限公司 | Method for selecting abnormal vibration segments of wind turbine generator |
| CN113339208A (en) * | 2021-07-21 | 2021-09-03 | 申能新能源(青海)有限公司 | Method for selecting abnormal vibration fragments of wind turbine generator |
| CN114330934A (en) * | 2022-03-09 | 2022-04-12 | 南方电网数字电网研究院有限公司 | Model parameter self-adaptive GRU new energy short-term power generation power prediction method |
| CN116861218A (en) * | 2023-07-25 | 2023-10-10 | 上海华菱电站成套设备股份有限公司 | Mine winder key equipment state monitoring early warning system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110685868A (en) | Wind turbine generator fault detection method and device based on improved gradient elevator | |
| CN110594107B (en) | Wind turbine generator fault detection method and device based on rapid gradient elevator | |
| CN108022001B (en) | Short-term load probability density prediction method based on PCA (principal component analysis) and quantile regression forest | |
| CN111275288B (en) | XGBoost-based multidimensional data anomaly detection method and device | |
| US11840998B2 (en) | Hydraulic turbine cavitation acoustic signal identification method based on big data machine learning | |
| CN108073158A (en) | Based on PCA and KNN density algorithm Wind turbines Method for Bearing Fault Diagnosis | |
| CN110717610B (en) | Wind power prediction method based on data mining | |
| CN111079343B (en) | Wind turbine generator effective wind speed estimation method based on width learning | |
| CN110365053B (en) | Short-term wind power prediction method based on delay optimization strategy | |
| CN114363195B (en) | Network flow prediction and early warning method for time and frequency spectrum residual convolution network | |
| CN111340282A (en) | DA-TCN-based method and system for estimating residual service life of equipment | |
| CN117290800B (en) | Timing sequence anomaly detection method and system based on hypergraph attention network | |
| CN110874665B (en) | Control device and method for wind generating set | |
| CN114297907A (en) | Greenhouse environment spatial distribution prediction method and device | |
| CN114021483A (en) | Ultra-short-term wind power prediction method based on time domain characteristics and XGboost | |
| CN115434875A (en) | Wind turbine generator fault state detection method based on space-time neural network | |
| CN114429238A (en) | Wind turbine generator fault early warning method based on space-time feature extraction | |
| Dong et al. | Real-time detection of wind power abnormal data based on semi-supervised learning Robust Random Cut Forest | |
| CN107844872B (en) | Short-term wind speed forecasting method for wind power generation | |
| CN114139638A (en) | Fan blade icing fault diagnosis method considering multivariable correlation | |
| CN113642238A (en) | Micrometeorological factor-based radial basis function neural network power transmission line icing prediction method | |
| CN117458955A (en) | Operation control method and system of motor | |
| CN117096860A (en) | Overhead transmission line current-carrying capacity interval prediction method and equipment based on LSSVM model | |
| CN112183814A (en) | Short-term wind speed prediction method | |
| CN111915070B (en) | Prediction method for k-nearest neighbor day-ahead wind speed by adopting atmospheric pressure spatial correlation |
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: 20200114 |
|
| RJ01 | Rejection of invention patent application after publication |