Method, system and equipment for detecting working state of wind driven generator and storage medium

Abstract

The invention discloses a method, a system and equipment for detecting the working state of a wind driven generator and a storage medium. The method comprises the following steps: acquiring a vibration signal of the wind driven generator in a preset time period; inputting the vibration signal into a pre-trained feature extraction model to obtain a mutual information topology global vibration waveform feature matrix; based on the mutual information topology global vibration waveform feature matrix, obtaining an optimized mutual information topology global vibration waveform feature matrix; inputting the optimized mutual information topology global vibration waveform feature matrix into a pre-trained classifier to obtain a classification result; and detecting the working state of the wind driven generator based on the classification result. According to the technical scheme, whether the working state of the wind driven generator is normal or not is detected, so that normal operation of the wind driven generator is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of wind power generation, and in particular to a method, system, device and storage medium for detecting the working status of a wind turbine. Background Art

[0002] Because wind farms are often located in remote areas, routine inspection and maintenance of wind turbines in these farms is often difficult and requires high labor costs. Therefore, SCADA (Supervisory Control And Data Acquisition) systems have been introduced to monitor the condition of wind turbines. The data collected by SCADA systems is diverse (e.g., vibration, speed, temperature, electrical energy, and angle, etc.) and large in quantity. Therefore, analyzing key data can enable condition monitoring of wind turbines. However, analyzing and interpreting the massive SCADA data of wind turbines is extremely difficult, and the reliability of the data analysis results is insufficient due to the influence of the wind turbine's environment and other operating factors. Summary of the Invention

[0003] The present application provides a method, system, device and storage medium for detecting the working status of a wind turbine, which can detect whether the working status of the wind turbine is normal, thereby ensuring the normal operation of the wind turbine.

[0004] In a first aspect, an embodiment of the present application provides a method for detecting the working status of a wind turbine, comprising: obtaining a vibration signal of the wind turbine within a predetermined time period; inputting the vibration signal into a pre-trained feature extraction model to obtain a mutual information topology global vibration waveform feature matrix; wherein the feature extraction model has pre-learned the ability to obtain a feature matrix based on feature information in the signal; based on the mutual information topology global vibration waveform feature matrix, obtaining an optimized mutual information topology global vibration waveform feature matrix; inputting the optimized mutual information topology global vibration waveform feature matrix into a pre-trained classifier to obtain a classification result; wherein the classification result is used to indicate whether the working status of the wind turbine is normal; based on the classification result, detecting the working status of the wind turbine.

[0005] In this technical solution, the working state of the wind turbine can be detected based on the acquired vibration signal of the wind turbine to determine whether the working state of the wind turbine is normal, thereby ensuring the normal operation of the wind turbine.

[0006] In one implementation, the feature extraction model includes a first convolutional neural network, a second convolutional neural network and a graph neural network, wherein the inputting the vibration signal into a pre-trained feature extraction model to obtain a mutual information topology global vibration waveform feature matrix includes: inputting the vibration signal into the first convolutional neural network to obtain a plurality of vibration waveform feature vectors; generating a mutual information input matrix based on the mutual information between the plurality of vibration waveform feature vectors; inputting the mutual information input matrix into the second convolutional neural network to obtain a mutual information feature matrix; arranging the plurality of vibration waveform feature vectors in two dimensions to obtain a global vibration waveform feature matrix; and inputting the mutual information feature matrix and the global vibration waveform feature matrix into the graph neural network to obtain the mutual information topology global vibration waveform feature matrix.

[0007] In an optional implementation, the inputting the vibration signal into the first convolutional neural network to obtain multiple vibration waveform feature vectors includes: performing convolution processing on the vibration signal to obtain a convolution feature map; performing mean pooling processing based on a feature matrix on the convolution feature map to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activation feature map; and obtaining the multiple vibration waveform feature vectors based on the activation feature map.

[0008] In an optional implementation, the mutual information is obtained as follows:

[0009]

[0010] Among them, v x and v y Respectively represent any two different ones of the plurality of vibration waveform feature vectors, I(V x ; V y ) represents the mutual information, v x Indicates the V x The first eigenvalue at each position in, v y Indicates the v y The second eigenvalue at each position in the x ,v y ) is the v x and the v y The joint probability density function, p(v x ) and p(v x ) is the marginal density function.

[0011] In one implementation, obtaining an optimized mutual information topology global vibration waveform feature matrix based on the mutual information topology global vibration waveform feature matrix includes: obtaining multiple third eigenvalues ​​of each position of the mutual information topology global vibration waveform feature matrix; performing characteristic manifold optimization on the mutual information topology global vibration waveform feature matrix based on the multiple third eigenvalues ​​to obtain the optimized mutual information topology global vibration waveform feature matrix.

[0012] In an optional implementation, the formula for obtaining the third eigenvalue is:

[0013]

[0014] Among them, m i,j is the third eigenvalue, W is the width of the mutual information topology global vibration waveform feature matrix, and H is the height of the mutual information topology global vibration waveform feature matrix.

[0015] In one implementation, the classifier includes multiple fully connected layers and a normalized exponential Softmax classification function, wherein the optimized mutual information topology global vibration waveform feature matrix is ​​input into a pre-trained classifier to obtain a classification result, including: expanding the optimized mutual information topology global vibration waveform feature matrix to obtain a classification feature vector; inputting the classification feature vector into the multiple fully connected layers to obtain an encoded classification feature vector; and inputting the encoded classification feature vector into the Softmax classification function to obtain the classification result.

[0016] In a second aspect, an embodiment of the present application provides a system for detecting the working status of a wind turbine, comprising: an acquisition module for acquiring a vibration signal of the wind turbine within a predetermined time period; a first processing module for inputting the vibration signal into a pre-trained feature extraction model to obtain a mutual information topology global vibration waveform feature matrix; wherein the feature extraction model has pre-learned the ability to obtain a feature matrix based on feature information in the signal; a second processing module for acquiring an optimized mutual information topology global vibration waveform feature matrix based on the mutual information topology global vibration waveform feature matrix; a third processing module for inputting the optimized mutual information topology global vibration waveform feature matrix into a pre-trained classifier to obtain a classification result; wherein the classification result is used to indicate whether the working status of the wind turbine is normal; and a detection module for detecting the working status of the wind turbine based on the classification result.

[0017] In one implementation, the feature extraction model includes a first convolutional neural network, a second convolutional neural network and a graph neural network, wherein the first processing module is specifically used to: input the vibration signal into the first convolutional neural network to obtain multiple vibration waveform feature vectors; generate a mutual information input matrix based on the mutual information between the multiple vibration waveform feature vectors; input the mutual information input matrix into the second convolutional neural network to obtain a mutual information feature matrix; arrange the multiple vibration waveform feature vectors in two dimensions to obtain a global vibration waveform feature matrix; input the mutual information feature matrix and the global vibration waveform feature matrix into the graph neural network to obtain the mutual information topology global vibration waveform feature matrix.

[0018] In an optional implementation, the first processing module is specifically used to: perform convolution processing on the vibration signal to obtain a convolution feature map; perform mean pooling processing based on a feature matrix on the convolution feature map to obtain a pooled feature map; perform nonlinear activation on the pooled feature map to obtain an activation feature map; and obtain the multiple vibration waveform feature vectors based on the activation feature map.

[0019] In an optional implementation, the mutual information is obtained as follows:

[0020]

[0021] Among them, V x and V y Respectively represent any two different ones of the plurality of vibration waveform feature vectors, I(V x ; V y ) represents the mutual information, v x Indicates the V x The first eigenvalue at each position in, v y Indicates the V y The second eigenvalue at each position in the x ,v y ) is the v x and the v y The joint probability density function, p(v x ) and p(v x ) is the marginal density function.

[0022] In one implementation, the second processing module is specifically used to: obtain multiple third eigenvalues ​​of each position of the mutual information topology global vibration waveform feature matrix; perform characteristic manifold optimization on the mutual information topology global vibration waveform feature matrix based on the multiple third eigenvalues ​​to obtain the optimized mutual information topology global vibration waveform feature matrix.

[0023] In an optional implementation, the formula for obtaining the third eigenvalue is:

[0024]

[0025] Among them, m i,j is the third eigenvalue, W is the width of the mutual information topology global vibration waveform feature matrix, and H is the height of the mutual information topology global vibration waveform feature matrix.

[0026] In one implementation, the classifier includes multiple fully connected layers and a Softmax classification function, wherein the third processing module is specifically used to: expand the optimized mutual information topology global vibration waveform feature matrix to obtain a classification feature vector; input the classification feature vector into the multiple fully connected layers to obtain an encoded classification feature vector; input the encoded classification feature vector into the Softmax classification function to obtain the classification result.

[0027] In a third aspect, an embodiment of the present application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for detecting the working status of a wind turbine as described in the first aspect.

[0028] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium for storing instructions, which, when executed, enables the method described in the first aspect to be implemented.

[0029] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for detecting the working status of a wind turbine as described in the first aspect.

[0030] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present application.

[0032] Figure 1 Schematic diagram of a method for detecting the working status of a wind turbine provided in an embodiment of the present application;

[0033] Figure 2 is a schematic diagram of another method for detecting the working status of a wind turbine provided in an embodiment of the present application;

[0034] Figure 3 Schematic diagram of another method for detecting the working status of a wind turbine provided in an embodiment of the present application;

[0035] Figure 4 Schematic diagram of another method for detecting the working status of a wind turbine provided in an embodiment of the present application;

[0036] Figure 5 This is an application scenario diagram of a wind turbine operating status detection system provided by an embodiment of the present application;

[0037] Figure 6 Schematic diagram of the architecture of a method for detecting the working status of a wind turbine provided in an embodiment of the present application;

[0038] Figure 7 1 is a schematic diagram of a wind turbine operating status detection system provided in an embodiment of the present application;

[0039] Figure 8 is a schematic block diagram of an example electronic device that can be used to implement embodiments of the present application. DETAILED DESCRIPTION

[0040] The following description of exemplary embodiments of the present application is made in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0041] In the description of this application, unless otherwise specified, " / " represents or. For example, A / B can represent A or B. "And / or" in this application is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The various numbers such as first and second mentioned in this application are only for convenience of description and are not intended to limit the scope of the embodiments of this application, nor do they indicate a sequential order.

[0042] See Figure 1 , Figure 1 Schematic diagram of a method for detecting the working status of a wind turbine provided in an embodiment of the present application. Figure 1 As shown, the method may include but is not limited to the following steps:

[0043] Step S101: Acquire a vibration signal of a wind turbine within a predetermined time period.

[0044] In an embodiment of the present application, the wind turbine may be an offshore wind turbine; the predetermined time period is a time period before the current time point (for example, one hour before the current time point).

[0045] In an embodiment of the present application, there is at least one vibration signal.

[0046] For example, multiple vibration sensors are pre-deployed at multiple different locations of a wind turbine to collect vibration signals at each of multiple time points in a predetermined time period, thereby obtaining multiple vibration signals of the wind turbine in the predetermined time period.

[0047] Step S102: Input the vibration signal into a pre-trained feature extraction model to obtain a mutual information topology global vibration waveform feature matrix.

[0048] In the embodiment of the present application, the feature extraction model has pre-learned the ability to obtain a mutual information topology global vibration waveform feature matrix based on the feature information in the vibration signal.

[0049] It is understandable that, because the vibration signals generated by a wind turbine during normal operation have implicit regular characteristics, when the wind turbine's operating state is abnormal, the vibration pattern characteristics will also change accordingly, and the vibration pattern characteristics will have mutual correlation and influence at different locations of the wind turbine. Based on the above characteristics, this application extracts the implicit temporal characteristics of the vibration signals at multiple locations of the wind turbine from the vibration signals based on a pre-trained feature extraction model.

[0050] Step S103: Based on the mutual information topology global vibration waveform feature matrix, an optimized mutual information topology global vibration waveform feature matrix is ​​obtained.

[0051] For example, a distribution transfer optimization oriented to a quasi-bounded closed domain is performed on the mutual information topology global vibration waveform feature matrix to obtain an optimized mutual information topology global vibration waveform feature matrix.

[0052] Step S104: inputting the optimized mutual information topology global vibration waveform feature matrix into a pre-trained classifier to obtain a classification result.

[0053] In the embodiment of the present application, the above classification result is used to indicate whether the working state of the wind turbine is normal.

[0054] As an example, the optimized mutual information topology global vibration waveform feature matrix is ​​input into a pre-trained classifier to obtain a first classification result indicating that the working state of the wind turbine is normal.

[0055] As another example, the optimized mutual information topology global vibration waveform feature matrix is ​​input into a pre-trained classifier to obtain a second classification result indicating that the working state of the wind turbine is abnormal.

[0056] Step S105: Based on the classification result, the working status of the wind turbine is detected.

[0057] As an example, in response to the classification result being the first classification result, it is determined that the working state of the wind turbine is normal.

[0058] As another example, in response to the classification result being the second classification result, it is determined that the operating state of the wind turbine is abnormal.

[0059] By implementing the embodiments of the present application, the working state of the wind turbine can be detected based on the acquired vibration signal of the wind turbine to determine whether the working state of the wind turbine is normal, thereby ensuring the normal operation of the wind turbine.

[0060] In one implementation, the feature extraction model includes a first convolutional neural network, a second convolutional neural network, and a graph neural network. Thus, the vibration signal can be processed sequentially through the above multiple models to obtain a mutual information topology global vibration waveform feature matrix. As an example, see Figure 2 , Figure 2 Schematic diagram of another method for detecting the working status of a wind turbine provided in an embodiment of the present application. Figure 2 As shown, the method may include but is not limited to the following steps:

[0061] Step S201: Acquire a vibration signal of a wind turbine within a predetermined time period.

[0062] In the embodiment of the present application, step S201 can be implemented in any of the ways in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described in detail.

[0063] Step S202: Input the vibration signal into the first convolutional neural network to obtain multiple vibration waveform feature vectors.

[0064] In an embodiment of the present application, the vibration signal includes a waveform diagram of each vibration signal.

[0065] For example, the vibration signal is input into the first convolutional neural network to perform feature mining on the waveform graph of each vibration signal in the vibration signal, extract the implicit feature distribution information of the waveform graph of each vibration signal in the vibration signal, and thus obtain multiple vibration waveform feature vectors.

[0066] In an optional implementation, the vibration signal is input into a first convolutional neural network to obtain multiple vibration waveform feature vectors, including: convolution processing of the vibration signal to obtain a convolution feature map; mean pooling processing of the convolution feature map based on a feature matrix to obtain a pooled feature map; nonlinear activation of the pooled feature map to obtain an activation feature map; and obtaining multiple vibration waveform feature vectors based on the activation feature map.

[0067] Step S203: Generate a mutual information input matrix based on the mutual information between multiple vibration waveform feature vectors.

[0068] For example, the mutual information between every two vibration waveform feature vectors in the plurality of vibration waveform feature vectors is calculated to obtain a plurality of mutual information, and each mutual information is used as an element in a matrix, thereby obtaining a mutual information input matrix.

[0069] In the embodiment of the present application, the mutual information is used to measure the influence of the mutuality between the vibration characteristics at two positions of the wind turbine corresponding to the two vibration waveform feature vectors on the final working state classification judgment.

[0070] In an optional implementation, the formula for obtaining the mutual information is:

[0071]

[0072] Among them, I(V x ; V y ) represents mutual information, V x and V y Respectively represent any two different vibration waveform feature vectors, v x Indicates V x The first eigenvalue at each position in, v y Indicates V y The second eigenvalue at each position in the x ,v y ) is v x and v y The joint probability density function, p(v x ) and p(v x ) is the marginal density function.

[0073] It is understandable that mutual information can measure the mutuality between two objects. Therefore, in classification problems, mutual information can be used to measure the influence of the mutuality between two features on the final classification judgment, that is, to measure the influence of the mutuality between the vibration features at various positions of the wind turbine on the classification judgment of the final abnormality of the working state. If the contribution values ​​of two features to the confidence of the final class probability are similar, the mutual information between the two features is larger. Therefore, the present application further strengthens the expression of implicit features in the vibration signal by the contribution of each vibration waveform feature to the confidence of the final class probability, so as to improve the accuracy of the abnormality judgment of the working state of the wind turbine.

[0074] Step S204: Input the mutual information input matrix into the second convolutional neural network to obtain a mutual information feature matrix.

[0075] For example, the mutual information input matrix is ​​input into the second convolutional neural network to extract the implicit correlation features of each position in the mutual information input matrix, that is, the mutual correlation features between the hidden vibration features at various positions of the wind turbine, and the above mutual correlation features are used as elements in the matrix to obtain the mutual information topological feature matrix.

[0076] Step S205: Arrange the multiple vibration waveform feature vectors in two dimensions to obtain a global vibration waveform feature matrix.

[0077] Step S206: Input the mutual information feature matrix and the global vibration waveform feature matrix into the graph neural network to obtain the mutual information topology global vibration waveform feature matrix.

[0078] For example, multiple vibration waveform feature vectors are used as feature representations of nodes, and the mutual information feature matrix is ​​used as feature representations of edges between nodes. The global vibration waveform feature matrix and the mutual information feature matrix obtained by two-dimensional arrangement of multiple vibration waveform feature vectors are input into the graph neural network to obtain the mutual information topology global vibration waveform feature matrix.

[0079] Step S207: Based on the mutual information topology global vibration waveform feature matrix, an optimized mutual information topology global vibration waveform feature matrix is ​​obtained.

[0080] In the embodiment of the present application, step S207 can be implemented in any of the ways in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described in detail.

[0081] Step S208: inputting the optimized mutual information topology global vibration waveform feature matrix into a pre-trained classifier to obtain a classification result.

[0082] In the embodiment of the present application, step S208 can be implemented in any of the ways in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described in detail.

[0083] Step S209: Based on the classification result, the working status of the wind turbine is detected.

[0084] In the embodiment of the present application, step S209 can be implemented in any of the ways in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described in detail.

[0085] By implementing the embodiments of the present application, the vibration signal of the acquired wind turbine can be input into the first convolutional neural network, the second convolutional neural network and the graph neural network in sequence to obtain the mutual information topology global vibration waveform feature matrix, and then perform subsequent processing to detect the working status of the wind turbine to determine whether the working status of the wind turbine is normal and ensure the normal operation of the wind turbine.

[0086] In one implementation of the present application, an optimized mutual information topology global vibration waveform feature matrix can be obtained based on the eigenvalues ​​of the mutual information topology global vibration waveform feature matrix. As an example, see Figure 3 , Figure 3 This is a schematic diagram of another method for detecting the working status of a wind turbine provided in an embodiment of the present application. Figure 3 As shown, the method may include but is not limited to the following steps:

[0087] Step S301: Acquire a vibration signal of a wind turbine within a predetermined time period.

[0088] In the embodiment of the present application, step S301 can be implemented in any of the ways in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described in detail.

[0089] Step S302: Input the vibration signal into a pre-trained feature extraction model to obtain a mutual information topology global vibration waveform feature matrix.

[0090] In the embodiment of the present application, step S302 can be implemented in any of the ways in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described in detail.

[0091] Step S303: obtaining multiple third eigenvalues ​​of each position of the mutual information topology global vibration waveform feature matrix.

[0092] In an optional implementation, the formula for obtaining the third eigenvalue is:

[0093]

[0094] Among them, m i,j is the third eigenvalue, W is the width of the mutual information topology global vibration waveform feature matrix, and H is the height of the mutual information topology global vibration waveform feature matrix.

[0095] Step S304: performing characteristic manifold optimization on the mutual information topology global vibration waveform characteristic matrix based on multiple third eigenvalues ​​to obtain an optimized mutual information topology global vibration waveform characteristic matrix.

[0096] It is understandable that, since each vector in the mutual information topology global vibration waveform feature matrix represents the mutual information topology expression of the waveform graphic semantics of a single vibration sensor, and each vibration sensor has a certain degree of independence, this leads to the inconsistency of feature distribution between the mutual information topology global vibration waveform feature vectors of the mutual information topology global vibration waveform feature matrix obtained by the graph neural network, so that the obtained mutual information topology global vibration waveform feature matrix may have a distribution convergence anomaly relative to the overall distribution. Therefore, the high-dimensional feature distribution represented by the mutual information topology global vibration waveform feature matrix may have inductive divergence when transferred to the target domain of the classification problem, affecting the training speed and the accuracy of the classification results. Therefore, the present application adopts the calculated third eigenvalue to perform feature manifold optimization on the mutual information topology global vibration waveform feature matrix to obtain the optimized mutual information topology global vibration waveform feature matrix. Thus, based on the structured information constraint of the conditional classification, the feature distribution converges towards the bounded closed domain of the feature set, so that the feature distribution is transferred to the range with a stable structured boundary under the target domain. Thereby improving the accuracy of the classification results obtained subsequently.

[0097] Step S305: inputting the optimized mutual information topology global vibration waveform feature matrix into a pre-trained classifier to obtain a classification result.

[0098] In the embodiment of the present application, step S305 can be implemented in any of the ways in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described in detail.

[0099] Step S306: Based on the classification result, the working status of the wind turbine is detected.

[0100] In the embodiment of the present application, step S306 can be implemented in any of the ways in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described in detail.

[0101] By implementing the embodiments of the present application, the mutual information topology global vibration waveform feature matrix can be obtained based on the vibration signal of the wind turbine within a predetermined time period, and the optimized mutual information topology global vibration waveform feature matrix can be obtained based on the eigenvalues ​​of the mutual information topology global vibration waveform feature matrix, so as to detect the working state of the wind turbine based on the optimized mutual information topology global vibration waveform feature matrix to determine whether the working state of the wind turbine is normal and ensure the normal operation of the wind turbine.

[0102] In one implementation of the present application, the classifier includes multiple fully connected layers and a normalized exponential Softmax classification function, so that the optimized mutual information topology global vibration waveform feature matrix can be sequentially input into the multiple fully connected layers and the Softmax classification function to obtain the classification result. As an example, see Figure 4 , Figure 4 This is a schematic diagram of another method for detecting the working status of a wind turbine provided in an embodiment of the present application. Figure 4 As shown, the method may include but is not limited to the following steps:

[0103] Step S401: Acquire a vibration signal of a wind turbine within a predetermined time period.

[0104] In the embodiment of the present application, step S401 can be implemented in any of the ways in the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and will not be described in detail.

[0105] Step S402: Input the vibration signal into a pre-trained feature extraction model to obtain a mutual information topology global vibration waveform feature matrix.

[0106] In the embodiment of the present application, step S402 can be implemented in any of the ways in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described in detail.

[0107] Step S403: Based on the mutual information topology global vibration waveform feature matrix, an optimized mutual information topology global vibration waveform feature matrix is ​​obtained.

[0108] In the embodiment of the present application, step S403 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiments of the present disclosure and will not be described in detail.

[0109] Step S404: Expand the optimized mutual information topology global vibration waveform feature matrix to obtain a classification feature vector.

[0110] As an example, the optimized mutual information topology global vibration waveform feature matrix is ​​expanded according to row vectors to obtain a classification feature vector.

[0111] As another example, the optimized mutual information topology global vibration waveform feature matrix is ​​expanded according to column vectors to obtain a classification feature vector.

[0112] Step S405: Input the classification feature vector into multiple fully connected layers to obtain an encoded classification feature vector.

[0113] For example, the classification feature vector is input into multiple fully connected layers for fully connected encoding to obtain the encoded classification feature vector.

[0114] Step S406: Input the encoded classification feature vector into the Softmax classification function to obtain a classification result.

[0115] In the embodiment of the present application, the generation formula of the classification result can be expressed as:

[0116] O=sogtmax{(M2,B2):…:(M1,B1)|Project(F)}

[0117] Among them, Project(F) represents the projection of the optimized mutual information topology global vibration waveform feature matrix into a vector, M1 and M2 are the weight matrices of each fully connected layer in the classifier, and B1 and B2 represent the bias matrices of each fully connected layer.

[0118] Step S407: Based on the classification result, the working status of the wind turbine is detected.

[0119] In the embodiment of the present application, step S407 can be implemented in any of the ways in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described in detail.

[0120] By implementing the embodiments of the present application, the obtained optimized mutual information topology global vibration waveform feature matrix can be input into a classifier including multiple fully connected layers and a Softmax classification function to obtain a classification result to detect whether the working status of the wind turbine is normal and ensure the normal operation of the wind turbine.

[0121] In some embodiments of the present application, the method for detecting the operating status of a wind turbine generator may further include: issuing a fault warning message in response to the abnormal operating status of the wind turbine generator. This allows maintenance personnel of the wind turbine generator to promptly repair the faulty wind turbine generator based on the warning message, thereby ensuring the normal operation of the wind turbine generator.

[0122] See Figure 5 , Figure 5 This is an application scenario diagram of a wind turbine working status detection system provided by an embodiment of the present application. Figure 5 As shown, in this application scenario, first obtain the data from the wind turbines deployed on the wind turbines (for example, Figure 5The vibration signals of a predetermined time period collected by multiple vibration sensors (eg, as shown in FIG. Figure 5 Then, the obtained vibration signal is input into a server equipped with a method for detecting the working status of a wind turbine (e.g., Figure 5 S) as shown in , wherein the server can process the vibration signal using the wind turbine working status detection method provided in any embodiment of the present application to generate a classification result indicating whether the working status of the wind turbine is normal.

[0123] See Figure 6 , Figure 6 Schematic diagram of the architecture of a method for detecting the working status of a wind turbine provided in an embodiment of the present application, such as Figure 6 As shown, in the architecture of the method for detecting the working status of a wind turbine provided in an embodiment of the present application, first, a vibration signal of a predetermined time period collected by multiple vibration sensors deployed on the wind turbine is obtained; then, the waveform graphs of each vibration signal in the vibration signal are respectively passed through a first convolutional neural network model as a filter to obtain multiple vibration waveform feature vectors; then, the mutual information between every two vibration waveform feature vectors in the multiple vibration waveform feature vectors is calculated to obtain a mutual information input matrix; then, the mutual information input matrix is ​​passed through a second convolutional neural network model as a feature extractor to obtain a mutual information feature matrix; then, the multiple vibration waveform feature vectors are two-dimensionally arranged to obtain a global vibration waveform feature matrix; then, the global vibration waveform feature matrix and the mutual information feature matrix are passed through a graph neural network model to obtain a mutual information topology global vibration waveform feature matrix; then, the mutual information topology global vibration waveform feature matrix is ​​feature manifold optimized to obtain an optimized mutual information topology global vibration waveform feature matrix; finally, the optimized mutual information topology global vibration waveform feature matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the working status of the wind turbine is normal.

[0124] See Figure 7 , Figure 7 Schematic diagram of a wind turbine operating status detection system provided in an embodiment of the present application, such as Figure 7As shown, the system 700 includes: an acquisition module 701, which is used to obtain the vibration signal of the wind turbine within a predetermined time period; a first processing module 702, which is used to input the vibration signal into a pre-trained feature extraction model to obtain a mutual information topology global vibration waveform feature matrix; wherein, the feature extraction model has pre-learned to obtain the ability to obtain the mutual information topology global vibration waveform feature matrix based on the feature information in the vibration signal; a second processing module 703, which is used to obtain an optimized mutual information topology global vibration waveform feature matrix based on the mutual information topology global vibration waveform feature matrix; a third processing module 704, which is used to input the optimized mutual information topology global vibration waveform feature matrix into a pre-trained classifier to obtain a classification result; wherein, the classification result is used to indicate whether the working state of the wind turbine is normal; a detection module 705, which is used to detect the working state of the wind turbine based on the classification result.

[0125] In one implementation, the feature extraction model includes a first convolutional neural network, a second convolutional neural network and a graph neural network, wherein the first processing module 702 is specifically used to: input the vibration signal into the first convolutional neural network to obtain multiple vibration waveform feature vectors; generate a mutual information input matrix based on the mutual information between the multiple vibration waveform feature vectors; input the mutual information input matrix into the second convolutional neural network to obtain a mutual information feature matrix; arrange the multiple vibration waveform feature vectors in two dimensions to obtain a global vibration waveform feature matrix; input the mutual information feature matrix and the global vibration waveform feature matrix into the graph neural network to obtain a mutual information topology global vibration waveform feature matrix.

[0126] In an optional implementation, the first processing module 702 is specifically used to: perform convolution processing on the vibration signal to obtain a convolution feature map; perform mean pooling processing based on the feature matrix on the convolution feature map to obtain a pooled feature map; perform nonlinear activation on the pooled feature map to obtain an activation feature map; and obtain multiple vibration waveform feature vectors based on the activation feature map.

[0127] In an optional implementation, the formula for obtaining mutual information is:

[0128]

[0129] Among them, V x and V y Respectively represent any two different vibration waveform feature vectors, I(V x ; V y ) represents mutual information, v x Indicates V x The first eigenvalue at each position in, v y Indicates V u The second eigenvalue at each position in the x,v y ) is v x and v y The joint probability density function, p(v x ) and p(v x ) is the marginal density function.

[0130] In one implementation, the second processing module 703 is specifically used to: obtain multiple third eigenvalues ​​of each position of the mutual information topology global vibration waveform feature matrix; perform characteristic manifold optimization on the mutual information topology global vibration waveform feature matrix based on the multiple third eigenvalues ​​to obtain an optimized mutual information topology global vibration waveform feature matrix.

[0131] In an optional implementation, the formula for obtaining the third eigenvalue is:

[0132]

[0133] Among them, m i,j is the third eigenvalue, W is the width of the mutual information topology global vibration waveform feature matrix, and H is the height of the mutual information topology global vibration waveform feature matrix.

[0134] In one implementation, the classifier includes multiple fully connected layers and a Softmax classification function, wherein the third processing module 704 is specifically used to: expand the optimized mutual information topology global vibration waveform feature matrix to obtain a classification feature vector; input the classification feature vector into multiple fully connected layers to obtain an encoded classification feature vector; input the encoded classification feature vector into the Softmax classification function to obtain a classification result.

[0135] Through the device of the embodiment of the present application, the working status of the wind turbine can be detected based on the acquired vibration signal of the wind turbine to determine whether the working status of the wind turbine is normal, thereby ensuring the normal operation of the wind turbine.

[0136] Based on the embodiments of the present application, the present application further provides a computer-readable storage medium, wherein computer instructions are used to enable a computer to execute the method for detecting the working status of a wind turbine according to any of the aforementioned embodiments provided in the embodiments of the present application.

[0137] See Figure 8 ,like Figure 8, which is a schematic block diagram of an example electronic device that can be used to implement embodiments of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are provided for example only and are not intended to limit the implementation of the present application as described and / or claimed herein.

[0138] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0139] Various components in device 800 are connected to I / O interface 805, including an input unit 806, such as a keyboard, mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0140] The computing unit 801 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the method for detecting the operating status of a wind turbine. For example, in some embodiments, the method for detecting the operating status of a wind turbine can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method for detecting the operating status of a wind turbine described above can be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the method for detecting the working status of the wind turbine generator in any other appropriate manner (for example, by means of firmware).

[0141] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard parts (ASSPs), system on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow charts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0143] In the context of the present application, a machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM) or a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0144] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a cathode ray tube (CRT) or an LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0145] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, 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: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0146] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, establishing a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS (Virtual Private Server) services. The server may also be a server in a distributed system or a server integrated with blockchain.

[0147] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of this application can be achieved. This is not limited herein.

[0148] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A method for detecting the working status of a wind turbine, characterized in that: include: Acquiring a vibration signal of the wind turbine within a predetermined time period; Inputting the vibration signal into a pre-trained feature extraction model to obtain a mutual information topology global vibration waveform feature matrix; wherein the feature extraction model has been pre-learned to obtain a feature matrix based on feature information in the signal; Based on the mutual information topology global vibration waveform feature matrix, obtaining an optimized mutual information topology global vibration waveform feature matrix; Inputting the optimized mutual information topology global vibration waveform feature matrix into a pre-trained classifier to obtain a classification result; wherein the classification result is used to indicate whether the working state of the wind turbine is normal; Based on the classification result, the working status of the wind turbine is detected.

2. The method according to claim 1, wherein The feature extraction model includes a first convolutional neural network, a second convolutional neural network, and a graph neural network, wherein the vibration signal is input into a pre-trained feature extraction model to obtain a mutual information topology global vibration waveform feature matrix, including: Inputting the vibration signal into the first convolutional neural network to obtain a plurality of vibration waveform feature vectors; generating a mutual information input matrix based on the mutual information between the plurality of vibration waveform feature vectors; Inputting the mutual information input matrix into the second convolutional neural network to obtain a mutual information feature matrix; Arranging the plurality of vibration waveform feature vectors in two dimensions to obtain a global vibration waveform feature matrix; The mutual information feature matrix and the global vibration waveform feature matrix are input into the graph neural network to obtain the mutual information topology global vibration waveform feature matrix.

3. The method according to claim 2, wherein Inputting the vibration signal into the first convolutional neural network to obtain a plurality of vibration waveform feature vectors includes: Performing convolution processing on the vibration signal to obtain a convolution feature map; Performing mean pooling processing based on a feature matrix on the convolution feature map to obtain a pooled feature map; Performing nonlinear activation on the pooled feature map to obtain an activated feature map; Based on the activation feature map, the plurality of vibration waveform feature vectors are obtained.

4. The method according to claim 2, wherein The formula for obtaining the mutual information is: Among them, I(V x ; V y ) represents the mutual information, V x and V y Respectively represent any two different ones of the multiple vibration waveform feature vectors, v x Indicates the V x The first eigenvalue at each position in, v y Indicates the V y The second eigenvalue at each position in the x , v y ) is the v x and the v y The joint probability density function, p(v x ) and p(v x ) is the marginal density function.

5. The method according to claim 1, wherein The step of obtaining an optimized mutual information topology global vibration waveform feature matrix based on the mutual information topology global vibration waveform feature matrix includes: Obtaining multiple third eigenvalues ​​at each position of the mutual information topology global vibration waveform feature matrix; The mutual information topology global vibration waveform feature matrix is ​​optimized on a characteristic manifold basis based on the multiple third eigenvalues ​​to obtain the optimized mutual information topology global vibration waveform feature matrix.

6. The method according to claim 5, wherein The formula for obtaining the third eigenvalue is: Among them, m i，j is the third eigenvalue, W is the width of the mutual information topology global vibration waveform feature matrix, and H is the height of the mutual information topology global vibration waveform feature matrix.

7. The method according to claim 1, wherein The classifier includes multiple fully connected layers and a normalized exponential Softmax classification function, wherein the optimized mutual information topology global vibration waveform feature matrix is ​​input into a pre-trained classifier to obtain a classification result, including: Expanding the optimized mutual information topology global vibration waveform feature matrix to obtain a classification feature vector; Inputting the classification feature vector into the multiple fully connected layers to obtain an encoded classification feature vector; The encoded classification feature vector is input into the Softmax classification function to obtain the classification result.

8. A wind turbine operating status detection system, characterized in that: include: An acquisition module, configured to acquire a vibration signal of the wind turbine within a predetermined time period; A first processing module is configured to input the vibration signal into a pre-trained feature extraction model to obtain a mutual information topology global vibration waveform feature matrix; wherein the feature extraction model has been pre-learned to obtain a feature matrix based on feature information in the signal; A second processing module is configured to obtain an optimized mutual information topology global vibration waveform feature matrix based on the mutual information topology global vibration waveform feature matrix; A third processing module is configured to input the optimized mutual information topology global vibration waveform feature matrix into a pre-trained classifier to obtain a classification result; wherein the classification result is used to indicate whether the working state of the wind turbine is normal; A detection module is used to detect the working status of the wind turbine based on the classification result.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for detecting the working status of a wind turbine according to any one of claims 1 to 7.

10. A computer-readable storage medium for storing instructions, characterized in that: When the instructions are executed, the method according to any one of claims 1 to 7 is implemented.

Images