CN117972467A - Intelligent wind power plant fault diagnosis method, device and storage medium - Google Patents
Intelligent wind power plant fault diagnosis method, device and storage medium Download PDFInfo
- Publication number
- CN117972467A CN117972467A CN202211297412.7A CN202211297412A CN117972467A CN 117972467 A CN117972467 A CN 117972467A CN 202211297412 A CN202211297412 A CN 202211297412A CN 117972467 A CN117972467 A CN 117972467A
- Authority
- CN
- China
- Prior art keywords
- temperature
- winding
- vector
- characteristic
- classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000003745 diagnosis Methods 0.000 title claims abstract description 49
- 238000004804 winding Methods 0.000 claims abstract description 226
- 239000013598 vector Substances 0.000 claims abstract description 181
- 239000011159 matrix material Substances 0.000 claims abstract description 99
- 230000005540 biological transmission Effects 0.000 claims abstract description 80
- 238000010248 power generation Methods 0.000 claims abstract description 51
- 238000000605 extraction Methods 0.000 claims abstract description 42
- 238000012546 transfer Methods 0.000 claims abstract description 39
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 29
- 230000015654 memory Effects 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 230000004927 fusion Effects 0.000 claims description 9
- 238000002405 diagnostic procedure Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000006698 induction Effects 0.000 description 6
- 230000004913 activation Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Wind Motors (AREA)
Abstract
The application provides an intelligent diagnosis method and device for wind farm faults and a storage medium. The method comprises the following steps: acquiring real-time temperature values and power generation power values of three-phase windings of a fan engine and real-time temperature values of a transmission shaft at a plurality of preset time points in a preset time period; extracting a winding temperature characteristic matrix and a winding power characteristic matrix through a convolutional neural network; obtaining a temperature characteristic vector of the transmission bearing through a multi-scale neighborhood characteristic extraction module; fusing the temperature characteristic vector of the transmission bearing and the winding temperature characteristic matrix to obtain a temperature characteristic vector; and taking the transfer vector of the temperature characteristic vector relative to the winding power characteristic matrix as a classification characteristic vector, and identifying whether the fan generator has faults or not according to the classification characteristic vector. The transfer vector of the temperature characteristic vector relative to the winding power characteristic is used for representing the correlation characteristic information between the power generation performance and the temperature during power generation, so that the relative index of the temperature is utilized for carrying out fault diagnosis on the wind power plant fan generator, and the accuracy of fault diagnosis is improved.
Description
Technical Field
The application relates to the technical field of fan generators, in particular to an intelligent diagnosis method, device and storage medium for wind power plant faults.
Background
The fan generator is one of the most important parts of the fan, and the identification of whether the fan generator is in fault operation is important content for maintaining the fan. In general, each phase winding of the fan generator is provided with a temperature sensor, the driving end and the non-driving end of the transmission bearing are also provided with temperature sensors, the temperature can be acquired through the temperature sensors, and protective measures are taken for high temperature so as to protect the winding to the greatest extent and ensure the operation safety of the fan generator.
When the winding of the fan generator is at high temperature, the fan generator is likely to have faults, and in order to avoid the fan generator to operate with faults, the fan generator is often required to be stopped for fault detection. However, there are many factors that cause the winding of the fan generator to generate high temperature, for example, under the condition of full load power generation, the passing current heats the winding to generate high temperature, and meanwhile, the winding temperature is influenced by the environmental temperature, so that the winding temperature has large changes in different seasons and different time periods. The mode of high-temperature alarm and shutdown inspection is not beneficial to the full utilization of wind energy, reduces the power generation efficiency and wastes wind power resources.
Patent publication number CN105527573a provides a method for identifying a failure of a wind power plant fan generator, which comprises the steps of calculating a three-phase failure calculation value of the fan generator according to the three-phase winding real-time temperature, the three-phase real-time power generation power, the real-time temperature of a transmission bearing and the rated power of the fan generator, selecting a maximum value from the three-phase failure calculation values of the fan generator as a failure judgment value of the fan generator, and then carrying out failure identification on the fan generator according to the failure judgment value of the fan generator.
Although the technical scheme can be used for carrying out fault identification on the fan generator, in the actual operation test process, the identification accuracy is lower. Therefore, an optimized intelligent diagnosis scheme for wind farm faults is expected.
Disclosure of Invention
The application provides an intelligent diagnosis method, device and system for faults of a wind farm, which are used for improving the identification accuracy of the faults. The technical scheme of the application is as follows:
in a first aspect, an embodiment of the present application provides a method for intelligently diagnosing a wind farm fault, including:
Acquiring real-time temperature values and power generation power values of three-phase windings of a fan engine and real-time temperature values of a transmission shaft at a plurality of preset time points in a preset time period;
Extracting temperature correlation characteristics of real-time temperature values of three-phase windings at a plurality of preset time points in the preset time period in a time dimension through a first convolutional neural network to obtain a winding temperature characteristic matrix;
Extracting implicit association features of the power generation power values of the three-phase windings at a plurality of preset time points in the preset time period in the time dimension through a second convolution neural network to obtain a winding power feature matrix;
Obtaining a transmission bearing temperature feature vector through dynamic multi-scale neighborhood associated features of the transmission shaft at the time dimension of real-time temperature values of a plurality of preset time points in the preset time period by a multi-scale neighborhood feature extraction module;
fusing the temperature characteristic vector of the transmission bearing and the temperature characteristic matrix of the winding to obtain a temperature characteristic vector; obtaining a transfer vector of the temperature characteristic vector relative to the winding power characteristic matrix;
and taking the transfer vector as a classification characteristic vector, and identifying whether the fan generator has faults or not according to the classification characteristic vector.
In some implementations, the extracting, by the first convolutional neural network, temperature-related features of real-time temperature values of the three-phase windings at a plurality of predetermined time points in the predetermined time period in a time dimension to obtain a winding temperature feature matrix includes:
according to the dimension of the winding sample and the dimension of time, arranging real-time temperature values of the three-phase winding at a plurality of preset time points in the preset time period into a winding temperature input matrix;
and inputting the winding temperature input matrix into the first convolutional neural network to obtain the winding temperature characteristic matrix.
In some implementations, the extracting, by the second convolutional neural network, implicit correlation features of the generated power values of the three-phase windings at a plurality of predetermined time points in the predetermined time period in a time dimension to obtain a winding power feature matrix includes:
According to the dimension of the winding sample and the dimension of time, arranging the power generation values of the three-phase windings at a plurality of preset time points in the preset time period into a winding power input matrix;
and inputting the winding power input matrix into the second convolutional neural network to obtain the winding power characteristic matrix.
In some implementations, the extracting, by the multi-scale neighborhood feature extraction module, a dynamic multi-scale neighborhood associated feature of real-time temperature values of the transmission shaft at a plurality of predetermined time points in the predetermined time period in a time dimension to obtain a transmission bearing temperature feature vector includes:
according to the time dimension, real-time temperature values of the transmission shafts at a plurality of preset time points in the preset time period are arranged as temperature input vectors;
And inputting the temperature input vector into the multi-scale neighborhood feature extraction module to obtain the temperature feature vector of the transmission bearing.
In some implementations, before the identifying whether the fan generator has a fault according to the classification feature vector, the method further includes:
performing micro operator conversion optimization of classification deviation on the classification feature vector;
And identifying whether the fan generator has faults or not according to the optimized classification feature vector.
In some implementations, the micromanipulation conversion optimization of the classification feature vector for classification bias includes:
performing micro operator conversion optimization of classification deviation on the classification feature vector through a first formula, wherein the first formula is expressed as follows:
Where v i is the eigenvalue of each position of the classification feature vector, v i' is the eigenvalue of each position of the optimized classification feature vector, and log is the logarithm of the base 2.
In some implementations, the identifying whether the fan generator has a fault based on the classification feature vector includes:
and inputting the classification feature vector into a classifier, and identifying whether the fan generator has faults or not.
In a second aspect, an embodiment of the present application provides an intelligent wind farm fault diagnosis apparatus, including:
the wind power data acquisition module is used for acquiring real-time temperature values and power generation power values of three-phase windings of the fan engine and real-time temperature values of the transmission shaft at a plurality of preset time points in a preset time period;
The winding temperature characteristic extraction module is used for extracting temperature correlation characteristics of real-time temperature values of the three-phase windings at a plurality of preset time points in the preset time period in a time dimension through a first convolutional neural network to obtain a winding temperature characteristic matrix;
The winding power feature extraction module is used for extracting implicit association features of the power generation power values of the three-phase windings at a plurality of preset time points in the preset time period in the time dimension through a second convolution neural network to obtain a winding power feature matrix;
The transmission shaft temperature characteristic extraction module is used for obtaining a transmission bearing temperature characteristic vector through dynamic multi-scale neighborhood associated characteristics of the transmission shaft real-time temperature values of a plurality of preset time points in the preset time period in the time dimension by the multi-scale neighborhood characteristic extraction module;
the characteristic fusion transfer module is used for fusing the temperature characteristic vector of the transmission bearing and the winding temperature characteristic matrix to obtain a temperature characteristic vector; obtaining a transfer vector of the temperature characteristic vector relative to the winding power characteristic matrix;
And the fault classification and identification module is used for taking the transfer vector as a classification characteristic vector and identifying whether the fan generator has faults or not according to the classification characteristic vector.
In some implementations, the winding temperature feature extraction module is specifically configured to:
according to the dimension of the winding sample and the dimension of time, arranging real-time temperature values of the three-phase winding at a plurality of preset time points in the preset time period into a winding temperature input matrix;
and inputting the winding temperature input matrix into the first convolutional neural network to obtain the winding temperature characteristic matrix.
In some implementations, the winding power feature extraction module is specifically configured to:
According to the dimension of the winding sample and the dimension of time, arranging the power generation values of the three-phase windings at a plurality of preset time points in the preset time period into a winding power input matrix;
and inputting the winding power input matrix into the second convolutional neural network to obtain the winding power characteristic matrix.
In some implementations, the transmission shaft temperature feature extraction module is specifically configured to:
according to the time dimension, real-time temperature values of the transmission shafts at a plurality of preset time points in the preset time period are arranged as temperature input vectors;
And inputting the temperature input vector into the multi-scale neighborhood feature extraction module to obtain the temperature feature vector of the transmission bearing.
In some implementations, the apparatus further includes an optimization module to:
performing micro operator conversion optimization of classification deviation on the classification feature vector;
And identifying whether the fan generator has faults or not according to the optimized classification feature vector.
In some implementations, the optimization module is specifically configured to:
performing micro operator conversion optimization of classification deviation on the classification feature vector through a first formula, wherein the first formula is expressed as follows:
Where v i is the eigenvalue of each position of the classification feature vector, v i' is the eigenvalue of each position of the optimized classification feature vector, and log is the logarithm of the base 2.
In some implementations, the fault classification module is specifically configured to:
and inputting the classification feature vector into a classifier, and identifying whether the fan generator has faults or not.
In a third aspect, an embodiment of the present application provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; the storage stores instructions executable by the at least one processor, so that the at least one processor can execute the intelligent diagnosis method for wind farm faults according to the embodiment of the first aspect of the present application.
In a fourth aspect, an embodiment of the present application provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to execute the wind farm fault intelligent diagnosis method according to the embodiment of the first aspect of the present application.
In a fifth aspect, embodiments of the present application provide a computer program product comprising computer instructions which, when executed by a processor, implement the steps of the wind farm fault intelligent diagnosis method according to the embodiments of the first aspect of the present application.
The technical scheme provided by the embodiment of the application at least has the following beneficial effects:
And (3) using the neural network as a feature extractor to respectively extract the temperature features of the winding nozzle and the power features of the winding, and simultaneously extracting the temperature features of the transmission bearing. And then, the temperature integral characteristic of the fan generator is represented based on the fusion of the temperature characteristic of the transmission bearing and the winding temperature characteristic, and a transfer vector of the temperature integral characteristic relative to the winding power characteristic is used as a classification characteristic vector of fault classification. The method has the advantages that the temperature integral characteristic is used for representing the correlation characteristic information between the power generation performance and the temperature during power generation relative to the transfer vector of the winding power characteristic, so that the relative index of the temperature is used for carrying out fault diagnosis on the wind power plant fan generator, the accuracy of fault diagnosis is improved, protection measures can be taken for high temperature, the winding is protected to the greatest extent, the operation safety of the fan generator is guaranteed, and the power generation efficiency of the fan is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application and do not constitute a undue limitation on the application.
FIG. 1 is a flowchart illustrating a method for intelligent diagnosis of wind farm faults, according to an exemplary embodiment.
FIG. 2 is a flowchart illustrating a method for intelligent diagnosis of wind farm faults, according to another exemplary embodiment.
FIG. 3 is an application scenario diagram illustrating a wind farm fault intelligent diagnostic method according to an exemplary embodiment.
FIG. 4 is a block diagram illustrating a wind farm fault intelligent diagnostic device, according to an exemplary embodiment.
Fig. 5 is a block diagram of an electronic device, according to an example embodiment.
Detailed Description
In order to enable a person skilled in the art to better understand the technical solutions of the present application, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like herein are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
In the related art, according to the real-time temperature of a three-phase winding of a fan generator, the real-time power generation power of the three-phase, the real-time temperature of a transmission bearing and the rated power of the fan generator, a three-phase fault calculated value of the fan generator is calculated, then a maximum value is selected from the three-phase fault calculated values of the fan generator to be used as a fault judgment value of the fan generator, and then the fan generator is subjected to fault identification according to the fault judgment value of the fan generator. Analysis of the related technology finds that the reason for low identification accuracy mainly comprises the following two points:
1. A linear model is used for mining the association relation among the winding temperature, the power generation power and the transmission shaft temperature, but the three are nonlinear in reality.
2. And judging whether a fault exists or not based on the comparison between the maximum of the three-phase fault calculated values and a preset threshold value, wherein the preset threshold value does not accord with the actual scene condition.
In order to solve the problems, the application provides an intelligent diagnosis method, an intelligent diagnosis device and a storage medium for wind farm faults, so as to improve the accuracy of fault identification.
FIG. 1 is a flow chart of a method for intelligent diagnosis of wind farm faults according to one embodiment of the present application. It should be noted that, the wind farm fault intelligent diagnosis method of the embodiment of the application can be applied to the wind farm fault intelligent diagnosis device of the embodiment of the application. The wind farm fault intelligent diagnosis device can be configured on electronic equipment. As shown in fig. 1, the wind farm fault intelligent diagnosis method may include the following steps.
In step S101, real-time temperature values and power generation values of three-phase windings of the fan motor and real-time temperature values of the propeller shaft at a plurality of predetermined time points within a predetermined period of time are acquired.
In the present embodiment, the real-time temperature values of the three-phase windings (U-phase winding, V-phase winding, and W-phase winding) and the generated power values of the three-phase windings at a plurality of predetermined time points within a predetermined period of time, and the real-time temperature values of the propeller shaft at a plurality of predetermined time points within the corresponding predetermined period of time are acquired.
In step S102, temperature correlation characteristics of real-time temperature values of the three-phase windings at a plurality of preset time points in the preset time period in a time dimension are extracted through a first convolutional neural network, and a winding temperature characteristic matrix is obtained.
As one possible implementation manner, the method for obtaining the winding temperature characteristic matrix includes:
According to the dimension of the winding sample and the dimension of time, arranging real-time temperature values of the three-phase winding at a plurality of preset time points in the preset time period into a winding temperature input matrix; and inputting the winding temperature input matrix into the first convolutional neural network to obtain the winding temperature characteristic matrix.
It will be appreciated that for real-time temperature values of the three-phase windings at a plurality of predetermined points in time over a predetermined period of time, rather than treating the three-phase windings as separate individuals, in order to be able to extract the temperature timing related characteristics of each of the three-phase windings over the predetermined period of time. Therefore, after real-time temperature values of the three-phase windings at a plurality of preset time points in the preset time period are arranged into a winding temperature input matrix according to a winding sample dimension (U-phase winding, V-phase winding and W-phase winding) and a time dimension, the winding temperature input matrix is processed by using a first convolution neural network which is used as a feature extractor and has excellent performance in local implicit association feature extraction so as to extract temperature association features of the three-phase windings in the time dimension respectively, and then the winding temperature feature matrix is obtained according to the winding sample dimension.
In step S103, implicit correlation features of the power generation values of the three-phase windings at a plurality of predetermined time points in the predetermined time period in the time dimension are extracted through a second convolutional neural network, so as to obtain a winding power feature matrix.
As one possible implementation manner, the method for obtaining the winding power characteristic matrix includes:
According to the dimension of the winding sample and the dimension of time, arranging the power generation values of the three-phase windings at a plurality of preset time points in the preset time period into a winding power input matrix; and inputting the winding power input matrix into the second convolutional neural network to obtain the winding power characteristic matrix.
It is understood that for the power generation values of the three-phase windings at a plurality of predetermined time points within the predetermined period of time, it is considered that the respective power generation values of the three-phase windings have implicit correlation characteristics in the time dimension. Therefore, in order to fully mine the characteristic information, the power generation values of the three-phase windings at a plurality of preset time points in the preset time period are arranged into a winding power input matrix according to the winding sample dimension and the time dimension, the winding power input matrix is processed in a second convolution neural network serving as a characteristic extractor, so that implicit associated characteristic information of the power generation values of the three-phase windings in the time dimension is extracted, and then the winding power characteristic matrix corresponding to the three-phase windings is obtained according to the winding sample dimension.
In step S104, a transmission bearing temperature feature vector is obtained through dynamic multi-scale neighborhood associated features of real-time temperature values of the transmission shaft at a plurality of preset time points in the preset time period in the time dimension by the multi-scale neighborhood feature extraction module.
As one possible implementation manner, the method for obtaining the temperature characteristic vector of the transmission bearing comprises the following steps:
According to the time dimension, real-time temperature values of the transmission shafts at a plurality of preset time points in the preset time period are arranged as temperature input vectors; and inputting the temperature input vector into the multi-scale neighborhood feature extraction module to obtain the temperature feature vector of the transmission bearing.
It is understood that the real-time temperature values of the drive shaft for a plurality of predetermined points in time within said predetermined period of time have different pattern states at different time spans within said predetermined period of time due to their regular character of dynamics in the time dimension. Therefore, in order to accurately diagnose the faults of the fan generator, real-time temperature values of the transmission shaft at a plurality of preset time points in the preset time period are arranged into temperature input vectors according to time dimensions, and then feature extraction is carried out through a multi-scale neighborhood feature extraction module so as to extract dynamic multi-scale neighborhood associated features of the real-time temperature of the transmission shaft in different time spans, so that a transmission bearing temperature feature vector is obtained.
In step S105, the temperature feature vector of the transmission bearing and the winding temperature feature matrix are fused, so as to obtain a temperature feature vector; and obtaining a transfer vector of the temperature characteristic vector relative to the winding power characteristic matrix.
As one possible implementation manner, the temperature characteristic vector of the transmission bearing and the temperature characteristic matrix of the winding are fused by the following formula to obtain the temperature characteristic vector;
Wherein V t represents the temperature characteristic vector of the transmission bearing, M t represents the temperature characteristic matrix of the winding, V 1 represents the temperature characteristic vector, Representing matrix multiplication.
It can be understood that the temperature characteristic vector is obtained by fusing the temperature characteristic vector of the transmission bearing and the temperature characteristic matrix of the winding, and the temperature characteristic vector is used for representing the integral characteristic of the temperature.
It should be understood that, when the winding of the fan generator is at high temperature, there may be a fault in the fan generator, however, there are many factors that cause the winding of the fan generator to be at high temperature, for example, in the case of full-load power generation, the passing current heats the winding to be at high temperature, and is influenced by the environmental temperature, so that the temperature of the winding varies greatly in different seasons and different periods. Therefore, in order to avoid using absolute quantity of temperature to perform fault analysis and diagnosis, the transfer vector of the temperature characteristic vector relative to the winding power characteristic matrix is used for representing the correlation between the power generation performance and the temperature during power generation, and further, the relative index of the temperature is used for performing classification judgment on whether the wind power plant fan generator has faults or not, so that the accuracy of fault diagnosis is improved, and the operation safety of the fan generator is further ensured.
As one possible implementation, the transfer vector of the temperature eigenvector with respect to the winding power eigenvector is calculated with the following formula:
Wherein V 1 represents a temperature characteristic vector, M 1 represents a winding power characteristic matrix, V represents a transfer vector, Representing matrix multiplication.
In step S106, the transfer vector is used as a classification feature vector, and whether the fan generator has a fault is identified according to the classification feature vector.
As a possible implementation manner, the optimized classification feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether a wind farm fan generator has a fault or not. If the classification result shows faults, protection measures can be timely taken for high temperature so as to protect windings to the greatest extent, ensure the operation safety of the fan generator and further improve the power generation efficiency of the fan.
According to the intelligent diagnosis method for the wind power plant faults, provided by the embodiment of the application, the neural network is used as a feature extractor to respectively extract the temperature features of the winding nozzle and the power features of the winding in time sequence distribution, and simultaneously extract the temperature features of the transmission bearing. And then, the temperature integral characteristic of the fan generator is represented based on the fusion of the temperature characteristic of the transmission bearing and the winding temperature characteristic, and a transfer vector of the temperature integral characteristic relative to the winding power characteristic is used as a classification characteristic vector of fault classification. The method has the advantages that the temperature integral characteristic is used for representing the correlation characteristic information between the power generation performance and the temperature during power generation relative to the transfer vector of the winding power characteristic, so that the relative index of the temperature is used for carrying out fault diagnosis on the wind power plant fan generator, the accuracy of fault diagnosis is improved, protection measures can be taken for high temperature, the winding is protected to the greatest extent, the operation safety of the fan generator is guaranteed, and the power generation efficiency of the fan is improved.
Based on the above embodiment, the transfer vector may be further optimized to provide distribution convergence of the transfer vector, thereby providing accuracy of fault mode intelligent diagnosis. FIG. 2 is a flow chart of a method for intelligent diagnosis of wind farm faults according to another embodiment of the present application. As shown in fig. 2, the wind farm fault intelligent diagnosis method may include the following steps.
In step S201, real-time temperature values and power generation values of three-phase windings of the fan motor and real-time temperature values of the propeller shaft at a plurality of predetermined time points within a predetermined period of time are acquired.
As an example, the real-time temperature value of the three-phase winding and the real-time temperature value of the transmission shaft may be acquired by a plurality of temperature sensors, respectively, and the generated power value of the three-phase winding may be acquired by a power meter. For example, as shown in fig. 3, the real-time temperature value of the three-phase winding and the real-time temperature value of the transmission shaft are obtained by three first temperature sensors (T1-T3), the real-time temperature value of the transmission shaft is obtained by a second temperature sensor (T4), and then the real-time power generation power value of the three-phase winding is obtained by a power meter (P). The data can be transmitted to a server (S), and the server can process the input data so as to realize the intelligent diagnosis method for the wind farm faults.
In step S202, temperature correlation characteristics of real-time temperature values of three-phase windings at a plurality of predetermined time points in the predetermined time period in a time dimension are extracted through a first convolutional neural network, so as to obtain a winding temperature characteristic matrix.
As an example, real-time temperature values of three-phase windings at a plurality of preset time points in the preset time period are respectively arranged into row vectors according to a time dimension, so as to obtain three temperature row vectors; and arranging the three temperature row vectors into a winding temperature input matrix according to the dimension of the winding sample. And inputting the winding temperature input matrix into the first convolutional neural network to obtain the winding temperature characteristic matrix.
As one example, a process of extracting a winding temperature feature matrix through a first convolutional neural network, comprising: carrying out convolution processing on an input winding temperature input matrix to obtain a convolution characteristic diagram; carrying out mean pooling based on a local feature matrix on the convolution feature map to obtain a pooled feature map; then, carrying out nonlinear activation on the pooled feature map to obtain an activated feature map; and converting the obtained activation characteristic diagram into a winding temperature characteristic matrix of the output layer.
In step S203, implicit correlation features of the power generation values of the three-phase windings at a plurality of predetermined time points in the predetermined time period in the time dimension are extracted through a second convolutional neural network, so as to obtain a winding power feature matrix.
As an example, the respective power generation values of the three-phase windings at a plurality of predetermined time points within the predetermined time period are arranged as row vectors according to a time dimension, respectively, so as to obtain three power generation row vectors; and arranging the three power generation power row vectors into a winding power input matrix according to the winding sample dimension. And inputting the winding power input matrix into the second convolutional neural network to obtain the winding power characteristic matrix.
As one example, a process of extracting a winding power feature matrix through a second convolutional neural network, comprising:
Carrying out convolution processing on a winding power input matrix input by a first layer of a second convolution neural network to obtain a convolution characteristic diagram; carrying out mean pooling based on a local feature matrix on the convolution feature map to obtain a pooled feature map; non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map; and converting the obtained activation characteristic diagram into a winding power characteristic matrix of the output layer.
In step S204, a transmission bearing temperature feature vector is obtained through a dynamic multi-scale neighborhood associated feature of the real-time temperature values of the transmission shaft at a plurality of preset time points in the preset time period in the time dimension by a multi-scale neighborhood feature extraction module.
As one example, the process of extracting the drive bearing temperature feature vector by the multi-scale neighborhood feature extraction module includes:
Inputting a temperature input vector into a first convolution layer of a multi-scale neighborhood feature extraction module to obtain a first neighborhood scale transmission bearing temperature feature vector, wherein the first convolution layer is provided with a first one-dimensional convolution kernel with a first length;
Inputting a temperature input vector into a second convolution layer of a multi-scale neighborhood feature extraction module to obtain a temperature feature vector of a second neighborhood scale transmission bearing, wherein the second convolution layer is provided with a second one-dimensional convolution kernel with a second length, and the second length is different from the first length; and cascading the first neighborhood scale transmission bearing temperature characteristic vector and the second neighborhood scale transmission bearing temperature characteristic vector to obtain a transmission bearing temperature characteristic vector.
In step S205, the temperature feature vector of the transmission bearing and the winding temperature feature matrix are fused to obtain a temperature feature vector; and obtaining a transfer vector of the temperature characteristic vector relative to the winding power characteristic matrix.
It should be noted that, in the embodiment of the present application, the implementation process of the above step S205 may be referred to the description of the implementation process of the above step S105, which is not repeated herein.
In step S206, the transfer vector is used as a classification feature vector, and the classification feature vector is optimized by performing micro operator conversion of classification deviation, so as to obtain an optimized classification feature vector.
It should be noted that, when the transmission bearing temperature feature vector and the winding temperature feature matrix are fused to obtain a temperature feature vector, since the transmission bearing temperature feature vector has a time-series correlation and the winding temperature feature matrix has a two-dimensional correlation of time series and samples, misalignment of distribution between the transmission bearing temperature feature vector and the winding temperature feature matrix may affect the distribution convergence of the temperature feature vector, which further emphasizes the distribution divergence of the classification feature vector when calculating a transfer vector of the temperature feature vector with respect to the winding power feature matrix as the classification feature vector. Therefore, before classification is carried out through the classification feature vector, the classification deviation can be optimized through micro operator conversion, and whether the fan generator has faults or not is identified according to the optimized classification feature vector, so that the classification accuracy is improved.
As a possible implementation manner, the classification feature vector is optimized by micro operator conversion of classification bias according to the following formula:
Where v i is the eigenvalue of each position of the classification feature vector, v i' is the eigenvalue of each position of the optimized classification feature vector, and log is the logarithm of the base 2.
It can be understood that the micro operator conversion of the classification deviation optimizes the problem of the induction deviation under the classification problem caused by the possible distribution divergence of the classification feature vector, converts the induction deviation into the information expression combination of the micro operator based on the induction constraint form of the induction convergence rate, so as to converge the decision domain under the class probability limit based on the induction constraint of the classification problem, thereby improving the certainty of the induction result of the target problem under the condition that the distribution divergence possibly exists and improving the accuracy of the classification result of the classification feature vector.
In step S207, the classification feature vector is input to a classifier, and whether the fan generator has a fault is identified.
As one example, the classification feature vectors are fully-connected encoded using multiple fully-connected layers of a classifier to obtain encoded classification feature vectors; and obtaining the classification result by the coding classification feature vector through a Softmax classification function of the classifier.
According to the intelligent diagnosis method for the wind power plant faults, provided by the embodiment of the application, the neural network is used as a feature extractor to respectively extract the temperature features of the winding nozzle and the power features of the winding in time sequence distribution, and simultaneously extract the temperature features of the transmission bearing. And then, based on the fusion of the temperature characteristic of the transmission bearing and the temperature characteristic of the winding, the temperature integral characteristic of the fan generator is represented, a transfer vector of the temperature integral characteristic relative to the winding power characteristic is obtained, the transfer vector is subjected to convergence optimization, and the optimized transfer vector is used as a classification characteristic vector of fault classification. The temperature integral characteristic is used for representing the correlation characteristic information between the power generation performance and the temperature during power generation relative to the transfer vector of the winding power characteristic, so that the relative index of the temperature is used for carrying out fault diagnosis on the wind power plant fan generator, the accuracy of fault diagnosis is further improved, and therefore protection measures can be taken for high temperature to furthest protect the winding, the operation safety of the fan generator is ensured, and the power generation efficiency of the fan is improved.
FIG. 4 is a block diagram illustrating a wind farm fault intelligent diagnostic device, according to an exemplary embodiment. Referring to fig. 4, the wind farm fault intelligent diagnosis apparatus may include: the device comprises a wind power data acquisition module 401, a winding temperature characteristic extraction module 402, a winding power characteristic extraction module 403, a transmission shaft temperature characteristic extraction module 404, a characteristic fusion transfer module 405 and a fault classification identification module 406.
The wind power data acquisition module 401 is configured to acquire real-time temperature values and power generation power values of three-phase windings of the fan engine and real-time temperature values of the transmission shaft at a plurality of predetermined time points within a predetermined time period;
the winding temperature characteristic extraction module 402 is configured to extract temperature correlation characteristics of real-time temperature values of three-phase windings at a plurality of predetermined time points in the predetermined time period in a time dimension through a first convolutional neural network, so as to obtain a winding temperature characteristic matrix;
the winding power feature extraction module 403 is configured to extract implicit correlation features of the power generation values of the three-phase winding at a plurality of predetermined time points in the predetermined time period in a time dimension through a second convolutional neural network, so as to obtain a winding power feature matrix;
The transmission shaft temperature feature extraction module 404 is configured to obtain a transmission bearing temperature feature vector through dynamic multi-scale neighborhood associated features of real-time temperature values of the transmission shaft at a plurality of predetermined time points in the predetermined time period in the multi-scale neighborhood feature extraction module in a time dimension;
The feature fusion transfer module 405 is configured to fuse the temperature feature vector of the transmission bearing and the winding temperature feature matrix to obtain a temperature feature vector; obtaining a transfer vector of the temperature characteristic vector relative to the winding power characteristic matrix;
The fault classification recognition module 406 is configured to take the transfer vector as a classification feature vector, and recognize whether the fan generator has a fault according to the classification feature vector.
In some embodiments of the present application, the winding temperature feature extraction module is specifically configured to:
according to the dimension of the winding sample and the dimension of time, arranging real-time temperature values of the three-phase winding at a plurality of preset time points in the preset time period into a winding temperature input matrix;
and inputting the winding temperature input matrix into the first convolutional neural network to obtain the winding temperature characteristic matrix.
In some embodiments of the application, the winding power feature extraction module is specifically configured to:
According to the dimension of the winding sample and the dimension of time, arranging the power generation values of the three-phase windings at a plurality of preset time points in the preset time period into a winding power input matrix;
and inputting the winding power input matrix into the second convolutional neural network to obtain the winding power characteristic matrix.
In some embodiments of the present application, the transmission shaft temperature feature extraction module is specifically configured to:
according to the time dimension, real-time temperature values of the transmission shafts at a plurality of preset time points in the preset time period are arranged as temperature input vectors;
And inputting the temperature input vector into the multi-scale neighborhood feature extraction module to obtain the temperature feature vector of the transmission bearing.
In some embodiments of the application, the apparatus further comprises an optimization module for:
performing micro operator conversion optimization of classification deviation on the classification feature vector;
And identifying whether the fan generator has faults or not according to the optimized classification feature vector.
In some embodiments of the present application, the optimization module is specifically configured to:
performing micro operator conversion optimization of classification deviation on the classification feature vector through a first formula, wherein the first formula is expressed as follows:
Where v i is the eigenvalue of each position of the classification feature vector, v i' is the eigenvalue of each position of the optimized classification feature vector, and log is the logarithm of the base 2.
In some embodiments of the present application, the fault classification module is specifically configured to:
and inputting the classification feature vector into a classifier, and identifying whether the fan generator has faults or not.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
According to the wind power plant fault intelligent diagnosis device, the neural network is used as the feature extractor to respectively extract the temperature features of the winding nozzle and the power features of the winding in time sequence distribution, and meanwhile, the temperature features of the transmission bearing are extracted. And then, based on the fusion of the temperature characteristic of the transmission bearing and the temperature characteristic of the winding, the temperature integral characteristic of the fan generator is represented, a transfer vector of the temperature integral characteristic relative to the winding power characteristic is obtained, the transfer vector is subjected to convergence optimization, and the optimized transfer vector is used as a classification characteristic vector of fault classification. The temperature integral characteristic is used for representing the correlation characteristic information between the power generation performance and the temperature during power generation relative to the transfer vector of the winding power characteristic, so that the relative index of the temperature is used for carrying out fault diagnosis on the wind power plant fan generator, the accuracy of fault diagnosis is further improved, and therefore protection measures can be taken for high temperature to furthest protect the winding, the operation safety of the fan generator is ensured, and the power generation efficiency of the fan is improved.
According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.
As shown in fig. 5, a block diagram of an electronic device for implementing a method for intelligent diagnosis of wind farm faults according to an embodiment of the present application is provided. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the applications described and/or claimed herein.
As shown in fig. 5, the electronic device includes: one or more processors 501, memory 502, and interfaces for connecting components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple electronic devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 501 is illustrated in fig. 5.
Memory 502 is a non-transitory computer readable storage medium provided by the present application. The storage stores instructions executable by at least one processor to enable the at least one processor to execute the method for intelligently diagnosing the wind farm faults. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the method for intelligent diagnosis of wind farm faults provided by the present application.
The memory 502 is used as a non-transitory computer readable storage medium, and may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the method for intelligently diagnosing faults in a wind farm in an embodiment of the present application (e.g., the wind power data acquisition module 401, the winding temperature feature extraction module 402, the winding power feature extraction module 403, the transmission shaft temperature feature extraction module 404, the feature fusion transfer module 405, and the fault classification recognition module 406 shown in fig. 4). The processor 501 executes various functional applications of the server and data processing, that is, a method for implementing intelligent diagnosis of wind farm faults in the above-described method embodiments, by running non-transitory software programs, instructions, and modules stored in the memory 502.
Memory 502 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created from the use of electronic devices for intelligent diagnosis of wind farm faults, and the like. In addition, memory 502 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 502 may optionally include memory remotely located with respect to processor 501, which may be connected to the wind farm fault intelligent diagnosis electronics via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the wind farm fault intelligent diagnosis method can further comprise: an input device 503 and an output device 504. The processor 501, memory 502, input devices 503 and output devices 504 may be connected by a bus or otherwise, for example in fig. 5.
The input device 503 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic device for intelligent diagnosis of wind farm faults, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointer stick, one or more mouse buttons, a track ball, a joystick, etc. The output devices 504 may include a display device, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASIC (application specific integrated circuit), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
These computing programs (also referred to as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
In an exemplary embodiment, a computer program product is also provided, which, when instructions in the computer program product are executed by a processor of an electronic device, enables the electronic device to perform the above-described method.
It should also be noted that the exemplary embodiments mentioned in this disclosure describe some methods or systems based on a series of steps or devices. The present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, or may be performed in a different order from the order in the embodiments, or several steps may be performed simultaneously.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. The specification and examples are to be regarded in an illustrative manner only.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. The intelligent diagnosis method for the wind power plant faults is characterized by comprising the following steps of:
Acquiring real-time temperature values and power generation power values of three-phase windings of a fan engine and real-time temperature values of a transmission shaft at a plurality of preset time points in a preset time period;
Extracting temperature correlation characteristics of real-time temperature values of three-phase windings at a plurality of preset time points in the preset time period in a time dimension through a first convolutional neural network to obtain a winding temperature characteristic matrix;
Extracting implicit association features of the power generation power values of the three-phase windings at a plurality of preset time points in the preset time period in the time dimension through a second convolution neural network to obtain a winding power feature matrix;
Obtaining a transmission bearing temperature feature vector through dynamic multi-scale neighborhood associated features of the transmission shaft at the time dimension of real-time temperature values of a plurality of preset time points in the preset time period by a multi-scale neighborhood feature extraction module;
fusing the temperature characteristic vector of the transmission bearing and the temperature characteristic matrix of the winding to obtain a temperature characteristic vector; obtaining a transfer vector of the temperature characteristic vector relative to the winding power characteristic matrix;
and taking the transfer vector as a classification characteristic vector, and identifying whether the fan generator has faults or not according to the classification characteristic vector.
2. The method according to claim 1, wherein the extracting, by the first convolutional neural network, temperature-related features of real-time temperature values of the three-phase windings at a plurality of predetermined time points in the predetermined time period in a time dimension to obtain a winding temperature feature matrix includes:
according to the dimension of the winding sample and the dimension of time, arranging real-time temperature values of the three-phase winding at a plurality of preset time points in the preset time period into a winding temperature input matrix;
and inputting the winding temperature input matrix into the first convolutional neural network to obtain the winding temperature characteristic matrix.
3. The method according to claim 1, wherein extracting, by the second convolutional neural network, implicit correlation features of the generated power values of the three-phase windings at a plurality of predetermined time points in the predetermined time period in a time dimension, to obtain a winding power feature matrix, includes:
According to the dimension of the winding sample and the dimension of time, arranging the power generation values of the three-phase windings at a plurality of preset time points in the preset time period into a winding power input matrix;
and inputting the winding power input matrix into the second convolutional neural network to obtain the winding power characteristic matrix.
4. The method according to claim 1, wherein the extracting, by the multi-scale neighborhood feature extraction module, the dynamic multi-scale neighborhood correlation feature of the real-time temperature values of the transmission shaft at a plurality of predetermined time points in the predetermined time period in the time dimension to obtain the transmission bearing temperature feature vector includes:
according to the time dimension, real-time temperature values of the transmission shafts at a plurality of preset time points in the preset time period are arranged as temperature input vectors;
And inputting the temperature input vector into the multi-scale neighborhood feature extraction module to obtain the temperature feature vector of the transmission bearing.
5. The method of claim 1, wherein the identifying whether the fan generator has a fault based on the classification feature vector further comprises:
performing micro operator conversion optimization of classification deviation on the classification feature vector;
And identifying whether the fan generator has faults or not according to the optimized classification feature vector.
6. The method of claim 5, wherein said micromanipulation transform optimization of said classification feature vectors for classification bias comprises:
performing micro operator conversion optimization of classification deviation on the classification feature vector through a first formula, wherein the first formula is expressed as follows:
Where v i is the eigenvalue of each position of the classification feature vector, v i' is the eigenvalue of each position of the optimized classification feature vector, and log is the logarithm of the base 2.
7. The method of claim 1 or 5, wherein said identifying whether the fan generator is faulty based on the classification feature vector comprises:
and inputting the classification feature vector into a classifier, and identifying whether the fan generator has faults or not.
8. An intelligent wind farm fault diagnosis device, which is characterized by comprising:
the wind power data acquisition module is used for acquiring real-time temperature values and power generation power values of three-phase windings of the fan engine and real-time temperature values of the transmission shaft at a plurality of preset time points in a preset time period;
The winding temperature characteristic extraction module is used for extracting temperature correlation characteristics of real-time temperature values of the three-phase windings at a plurality of preset time points in the preset time period in a time dimension through a first convolutional neural network to obtain a winding temperature characteristic matrix;
The winding power feature extraction module is used for extracting implicit association features of the power generation power values of the three-phase windings at a plurality of preset time points in the preset time period in the time dimension through a second convolution neural network to obtain a winding power feature matrix;
The transmission shaft temperature characteristic extraction module is used for obtaining a transmission bearing temperature characteristic vector through dynamic multi-scale neighborhood associated characteristics of the transmission shaft real-time temperature values of a plurality of preset time points in the preset time period in the time dimension by the multi-scale neighborhood characteristic extraction module;
the characteristic fusion transfer module is used for fusing the temperature characteristic vector of the transmission bearing and the winding temperature characteristic matrix to obtain a temperature characteristic vector; obtaining a transfer vector of the temperature characteristic vector relative to the winding power characteristic matrix;
And the fault classification and identification module is used for taking the transfer vector as a classification characteristic vector and identifying whether the fan generator has faults or not according to the classification characteristic vector.
9. An electronic device, comprising:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the wind farm fault intelligent diagnostic method of any of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the wind farm fault intelligent diagnosis method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211297412.7A CN117972467A (en) | 2022-10-21 | 2022-10-21 | Intelligent wind power plant fault diagnosis method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211297412.7A CN117972467A (en) | 2022-10-21 | 2022-10-21 | Intelligent wind power plant fault diagnosis method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117972467A true CN117972467A (en) | 2024-05-03 |
Family
ID=90858349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211297412.7A Pending CN117972467A (en) | 2022-10-21 | 2022-10-21 | Intelligent wind power plant fault diagnosis method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117972467A (en) |
-
2022
- 2022-10-21 CN CN202211297412.7A patent/CN117972467A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Multilevel information fusion for induction motor fault diagnosis | |
| EP3515041A1 (en) | System and method for abstracting characteristics of cyber-physical systems | |
| Haroun et al. | Multiple features extraction and selection for detection and classification of stator winding faults | |
| CN109657982A (en) | A kind of fault early warning method and device | |
| CN111830409A (en) | Motor thermal fault diagnosis method and device based on deep neural network | |
| CN111709190A (en) | Wind turbine generator operation data image identification method and device | |
| CN112855460B (en) | Method, system, medium and equipment for predicting real-time fatigue life of shafting of wind turbine generator | |
| Zhao et al. | Signal-to-signal translation for fault diagnosis of bearings and gears with few fault samples | |
| Chen et al. | Adaptation regularization based on transfer learning for fault diagnosis of rotating machinery under multiple operating conditions | |
| Xu et al. | Fault diagnosis of gas turbine generator bearings using enhanced valuable sample strategy and convolutional neural network | |
| CN117972467A (en) | Intelligent wind power plant fault diagnosis method, device and storage medium | |
| Dabetwar et al. | Mass imbalance diagnostics in wind turbines using deep learning with data augmentation | |
| Gao et al. | Semi-supervised small sample fault diagnosis under a wide range of speed variation conditions based on uncertainty analysis | |
| He et al. | A Real-Time Adaptive Fault Diagnosis Scheme for Dynamic Systems With Performance Degradation | |
| CN115099264A (en) | Ship part fault diagnosis method and device, computer and computer storage medium | |
| Zhang et al. | Multi‐attribute quantitative bearing fault diagnosis based on convolutional neural network | |
| CN112699598A (en) | Intelligent diagnosis method and device for abnormal oil temperature of gear box | |
| CN117972498A (en) | Gear box state monitoring system and method for offshore wind turbine | |
| CN114877925B (en) | Comprehensive energy system sensor fault diagnosis method based on extreme learning machine | |
| Lyu et al. | A Novel Fault Diagnosis Method Based on Feature Fusion and Model Agnostic Meta-Learning | |
| CN117967506A (en) | Early warning control method and device for offshore wind turbine and storage medium | |
| Dinh et al. | Implementation of Digital Twin-Assisted Condition Monitoring and Fault Diagnosis for Wind Turbines | |
| CN110596586B (en) | Motor current waveform analysis method based on Alexnet algorithm | |
| Chang et al. | Centrifugal pump fault diagnosis method based on EAS and stacked capsule autoencoder | |
| Giri et al. | Optimized Fault Detection and Classification for 3-Phase Electric Drives–An AI/ML Approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication |