A method for classification and identification of partial discharge

Abstract

The present application relates to the field of electrical equipment detection technology, and in particular to a method for partial discharge classification and identification, comprising obtaining a partial discharge signal and extracting graph structural features from the partial discharge signal to obtain node features of the partial discharge signal; determining a temporal dynamic threshold interval based on the KL divergence between a positive sample and each candidate negative sample for negative sample sampling; constructing and training a graph encoder based on the positive and negative samples to obtain a high-dimensional feature vector corresponding to the partial discharge signal; the loss function of the graph encoder includes a bidirectional weighted likelihood loss function and a feature contrast loss function; and classifying the partial discharge signal into partial discharge types based on the high-dimensional feature vector using BK-Means. By extracting graph structural features and constructing high-dimensional feature vectors, combined with dynamic threshold negative sample sampling and a graph encoder based on ResGCN, the classification accuracy and computational efficiency of the partial discharge signal are improved.

Description

Technical Field

[0001] The present application relates to the technical field of electrical equipment detection, and more specifically, to a method for classifying and identifying partial discharges. Background Art

[0002] Accurate identification of partial discharge (PD) is crucial for the safe operation of high-voltage equipment and is extremely important for the stability and reliability of power systems. In recent years, significant progress has been made in PD identification using supervised learning. By building a model and training it with sample data with known labels, this approach enables the model to learn and identify the characteristics of different PD types. However, the amount of data generated during modern electrical equipment monitoring is enormous. Determining the label for each set of data requires detailed analysis, a process that is both time-consuming and incurs high labor costs. Given these limitations, the unsupervised learning paradigm offers a viable alternative, offering the potential to bypass the laborious data labeling process.

[0003] In the study of partial discharge, pulse signals have significant time series characteristics, and the temporal relationship between pulses is the key to studying discharge characteristics. Traditional clustering algorithms, such as k-means and DBSCAN, usually rely only on the feature information of data points and ignore the structural relationship between samples. Therefore, the clustering effect is poor when processing complex data. In recent years, deep graph clustering (Graph Neural Networks, GNNs) has made significant progress in many fields. GNNs are able to process graph-structured data, where nodes represent data points and edges represent the relationship between data points. Thanks to their powerful graph information processing capabilities, graph convolutional networks perform well in graph clustering tasks such as social networks and recommendation systems. By combining node features and graph structural information, GNNs can achieve more accurate node representation learning and clustering.

[0004] Recently, deep graph node clustering has been primarily categorized into generative and contrastive methods. Generative methods typically utilize autoencoders to reconstruct graph structure or node features, but this method constrains the latent representation by using a reconstruction loss, which can lead to fluctuations and instabilities during training. Contrastive methods, in contrast, aim to learn representations that can distinguish between positive and negative samples, where positive samples are pairs of nodes belonging to the same cluster, and negative samples are pairs from different clusters. By bringing positive samples closer together and negative samples further apart, they improve the model's representational power.

[0005] In contrastive learning, data augmentation techniques (such as masked features, node deactivation, edge perturbations, and subgraph partitioning) have been shown to significantly improve representation learning. However, for time-series spike data, the construction of negative samples is particularly important. These methods typically focus only on static features of the data and fail to effectively capture temporal relationships. Therefore, in time-series spike data classification, the sampling and construction of negative samples requires more targeted strategies to improve the model's sensitivity to temporal dependencies and classification accuracy. Summary of the Invention

[0006] In view of this, the present application provides a partial discharge classification and recognition method to solve the problem that when the existing technology classifies time series pulse data based on contrastive learning, the sampling and construction of negative samples only focus on the static characteristics of the data and cannot effectively capture the time series relationship, resulting in the model's sensitivity to time series dependence and low classification accuracy.

[0007] The technical solutions provided in this application are as follows:

[0008] A partial discharge classification and identification method, comprising:

[0009] Acquire a partial discharge signal, and perform graph structure feature extraction on the partial discharge signal to obtain node features of the partial discharge signal;

[0010] Taking the node features as positive samples, and extracting a negative sample candidate set from the partial discharge signal;

[0011] Determining a temporal dynamic threshold interval based on the KL divergence between the positive sample and each candidate negative sample in the negative sample candidate set for negative sample sampling; the KL divergence between the sampled negative sample and the positive sample is within the temporal dynamic threshold interval;

[0012] Based on the positive samples and negative samples, two ResGCN-based graph encoders are constructed and trained to obtain high-dimensional feature vectors corresponding to partial discharge signals; the loss function of the graph encoder includes a bidirectional weighted likelihood loss function and a feature contrast loss function;

[0013] According to the high-dimensional feature vector, the partial discharge signal is classified into partial discharge types based on BK-Means.

[0014] In one possible implementation, performing graph structure feature extraction on the partial discharge signal to obtain node features corresponding to the partial discharge signal includes:

[0015] Constructing an adjacency matrix for representing a graph structure according to the partial discharge signal, and determining a degree matrix D of the adjacency matrix A;

[0016] Based on the degree matrix D, the adjacency matrix A is standardized to obtain a standardized adjacency matrix Expressed as: Where I is the identity matrix;

[0017] Based on the standardized adjacency matrix Enhanced graph structure representation to obtain improved adjacency matrix Expressed as: Among them, α is used to represent the transition probability from one node to another.

[0018] In one possible implementation, the KL divergence between the positive sample and each candidate negative sample in the negative sample candidate set is expressed as:

[0019]

[0020] Among them, x represents the positive sample, represents the candidate negative samples in the negative sample candidate set.

[0021] In one possible implementation, determining a temporal dynamic threshold interval based on the KL divergence between the positive sample and each candidate negative sample in the negative sample candidate set and performing negative sample sampling includes:

[0022] Determine the minimum KL divergence value KL between the positive sample and each of the candidate negative samples min and the maximum KL divergence value KL max ;

[0023] According to the KL min and the KL max , determine the dynamic threshold increment θ, expressed as:

[0024] θ=φ(KL max -KL min ); where φ is the adjustment factor;

[0025] According to the KL min 、KL max and the dynamic threshold increment θ, determine the time dynamic threshold interval for negative sample sampling, and the negative sample obtained by sampling The KL divergence between the positive sample and the time dynamic threshold is within the time dynamic threshold interval, which is expressed as:

[0026]

[0027] in, is the candidate negative sample in the negative sample candidate set, w t is the time window, t is the time corresponding to the collection of the positive sample, t iis the time corresponding to the collection of the negative sample.

[0028] In one possible implementation, two ResGCN-based graph encoders are constructed and trained based on the positive and negative samples, including:

[0029] The positive samples and the negative samples are encoded based on two independent graph convolutional networks GCNs, which are expressed as:

[0030] Where, is the graph convolution operation of the i-th encoder, is the normalized adjacency matrix, X is the node feature matrix composed of positive samples ×, is the parameter of the i-th GCN, δ is the PRelu activation function;

[0031] According to the graph convolution operation, the output z of the positive sample is obtained 1 、z 2 And the output of the negative sample

[0032] The output of the positive sample is expressed as:

[0033]

[0034] The output of the negative sample is expressed as:

[0035] Where, Negative samples The negative sample matrix is formed, represents residual connection;

[0036] According to the output of the positive sample and the negative sample, the feature mean of all samples is calculated to obtain the global feature vector h i , expressed as:

[0037]

[0038] In the formula, j represents a single sample, σ is the activation function, n is the number of samples, is the output of the graph-based encoder;

[0039] The similarity between features is calculated based on a bilinear interaction network, expressed as:

[0040]

[0041] Among them, F k represents the output of the bilinear interaction network, W k are the parameters of the bilinear interaction network, is the transposed matrix of the output of the graph encoder.

[0042] In one possible implementation, the bidirectional weighted likelihood loss function L c , expressed as:

[0043]

[0044] Where, N is the number of positive samples, M is the number of negative samples; is the feature of the positive sample, is the feature of the negative sample, y is the positive sample label, h 2 is the global vector obtained by the second graph encoder.

[0045] In one possible implementation, the feature contrast loss function is expressed as:

[0046]

[0047] Where index(j) is the negative example index sampled from a uniform distribution from 0 to μ, e is the current training round, E is the total training round, is a predetermined constant, R is the index range; N is the number of positive samples, M is the number of negative samples; S ii is the feature-level similarity matrix S i，j The diagonal elements of the feature-level similarity matrix S i，j Used to quantify the cosine similarity between feature i and feature j, S index(j) are the off-diagonal elements corresponding to negative samples; γ is used to control the sensitivity of similarity.

[0048] Compared with the existing technology, the technical solution of this application has the following beneficial effects:

[0049] Based on the technical solution of this application, by extracting graph structure features and constructing high-dimensional feature vectors, the complex characteristics of partial discharge signals can be effectively captured, improving classification accuracy. By adopting a negative sample sampling strategy within a dynamic threshold range, the blindness of negative sample selection is avoided, allowing the model to better learn the characteristic differences of partial discharge signals during training. At the same time, the use of a ResGCN-based graph encoder and a BK-Means clustering algorithm not only enables the processing of large-scale data sets, but also achieves accurate classification of partial discharge types while maintaining computational efficiency, with high practicality and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flow chart of a partial discharge classification and identification method provided in Example 1 of the present application.

[0051] Figure 2 A framework diagram of graph comparison unsupervised clustering provided in Example 1 of the present application. DETAILED DESCRIPTION

[0052] The following will combine the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0053] Example 1

[0054] See also Figure 1 , is a flow chart of a partial discharge classification and identification method provided in Example 1 of the present application. Figure 1 As shown in , the specific implementation steps of the above method include:

[0055] Step 101: Collect partial discharge signals at preset time intervals.

[0056] Optionally, the above-mentioned preset time interval can be set according to actual conditions, and is not specifically limited in the embodiment of the present application.

[0057] Step 102: extract graph structure features from the partial discharge signal to obtain node features corresponding to the partial discharge signal.

[0058] The graph structure is used to describe the complex relationship between data elements. It is a nonlinear structure composed of a vertex set and an edge set. Each signal point in the partial discharge signal is regarded as a node in the graph. A graph structure is represented as: G = {V, E, X}, where V and E are the vertex set and edge set, that is, V = {v1, v2, v3...}, E = {v1v2, v2v3...}, v i represents a node. X is the corresponding node feature matrix.

[0059] Based on the collected partial discharge signals, the adjacency matrix A is constructed to represent the topological structure of the graph G. The adjacency matrix A is expressed as That is, if two sets of partial discharge signals are adjacent, the edge between them is a i，j =1, otherwise a ij is 0.

[0060] Based on the above adjacency matrix A, determine the degree matrix D of the adjacency matrix A. The degree matrix D is a diagonal matrix, and the elements on the diagonal are the degrees of each node. i The degree represents the number of edges associated with the node.

[0061] Normalize A where I is the identity matrix.

[0062] Specifically, the input of each layer of GCN is the node feature matrix X and the adjacency matrix A. The two are directly inner-producted, multiplied by a parameter matrix W, and activated with an activation function to form a neural network layer.

[0063] However, because the diagonal elements of the adjacency matrix are all zero, the inner product with the node feature matrix is equivalent to a weighted sum of the adjacency matrix. The node feature values become the weights of the adjacency matrix, and the node's own features are ignored. To avoid this, we add an identity matrix I to the adjacency matrix A, so that the diagonal elements of the adjacency matrix are all 1.

[0064] Furthermore, since the adjacency matrix A has not been normalized, it is difficult to limit the data to the required range. Through normalization, the data can be made comparable while relatively maintaining the relationship between the data. Therefore, in order to avoid the inner product multiplication of the adjacency matrix and the feature matrix changing the original distribution of the features, this embodiment performs a normalization process on the adjacency matrix A, which is expressed as:

[0065] Based on the above normalized adjacency matrix, the above graph structure representation is enhanced to obtain an improved adjacency matrix, which is expressed as

[0066] Specifically, enhancing the graph structure is a method to improve the original graph structure by adding additional information or connections. This enhancement can be reflected in many aspects. Figure 2 As shown, this embodiment enhances the structure of the graph by adding new nodes or edges. Wherein α is the transition probability, which is used to describe the probability of going from one node to another. In the field of deep learning, graph convolutional networks (GCN) can be used to learn node representations on the graph and calculate transition probabilities based on this. GCN updates the representation of nodes by aggregating information from neighboring nodes, thereby capturing the structural characteristics of the graph. Optionally, different methods of enhancing the graph structure can be set according to actual conditions, and this embodiment of the application does not make specific limitations.

[0067] Step 103: Take the node features as positive samples (x), and extract a negative sample candidate set (x1, x2, ..., x n ). Wherein, n is a positive integer.

[0068] In this embodiment, the positive samples and negative samples are derived from the same data set, namely, a data set consisting of collected partial discharge signals. For example, assuming that there are 100 sets of data in the data set, a corresponding negative sample is found for each set of data in order. Specifically, the method for screening negative samples provided in this application is as follows:

[0069] Step 104: quantify the probability distribution between positive samples and each candidate negative sample in the negative sample candidate set using KL divergence.

[0070] In this embodiment, by minimizing the similarity between positive and negative samples and maximizing the similarity between similar samples, a more effective data representation is learned. Specifically, for each candidate negative sample Calculate the KL divergence between it and the positive sample ×, expressed as:

[0071]

[0072] Step 105: According to each candidate negative sample The KL divergence between the positive sample x and the negative sample x determines the time dynamic threshold interval and selects more suitable negative samples. Expressed as:

[0073]

[0074] Specifically, the embodiment of the present application is based on all candidate negative samples The KL divergence between the positive sample x and the positive sample x determines the range of a time dynamic threshold, which is determined by the minimum KL divergence KL min , maximum KL divergence KL max and the dynamic threshold increment θ. Where θ=φ(KL max -KL min ). φ is the adjustment factor, which is used to adjust the threshold range so that the selected negative samples More suitable. t is the time window, t is the time corresponding to the collection of positive samples, t i The time corresponding to the collection of negative samples. Set the time window w t It is used to ensure that there is a certain time interval between the selected negative samples and the positive samples, and to avoid selecting samples that are too close in time to the positive samples, thereby improving the negative samples. diversity.

[0075] Through the above method, this embodiment can more effectively select negative samples that have a moderate difference in probability distribution from the positive samples and a certain time interval. This approach not only takes into account temporal independence but also ensures the diversity of negative samples. The negative samples obtained through screening are used to train the model, thereby improving the model's ability to identify the differences between positive and negative samples.

[0076] Step 106: Based on the positive samples and the corresponding negative samples, two ResGCN-based graph encoders are constructed and trained.

[0077] In this embodiment, a graph convolutional network with residual connections (ResGCN) is used as a graph encoder, and the positive samples and the corresponding negative samples obtained in steps 102 to 105 are used together in the training process of the graph encoder, so that the signal features of each node can be mapped to a high-dimensional space for encoding. Specifically, Figure 2 As shown in , two independent graph convolutional networks (GCNs) are used to encode positive and negative samples. Each GCN encodes the adjacency matrix And node feature x as input, perform the following transformation to extract features:

[0078]

[0079] in, is the graph convolution operation of the i-th encoder, is the normalized adjacency matrix, X is the node feature matrix composed of positive samples x, is the parameter of the i-th GCN, and δ is the PRelu activation function.

[0080] After being processed by the graph encoder, the output z of the positive sample i The feature representation is enhanced by adding the node feature matrix X, which is expressed as:

[0081]

[0082] Where +X represents the residual connection. Based on the above residual connection, the original feature information can be retained while allowing the model to learn more complex feature interactions.

[0083] The negative sample output is and Expressed as:

[0084] Where, Negative samples The negative sample matrix is formed, represents a residual connection.

[0085] Calculate the feature mean of all samples to obtain the global feature vector hi, which is calculated as follows:

[0086]

[0087] Among them, j represents a single sample, σ is the activation function, and n is the number of samples. is the output of the graph-based encoder.

[0088] A bilinear interaction network is used to calculate the similarity between features, expressed as:

[0089]

[0090] Among them, F k represents the output of the bilinear interaction network, W k are the parameters of the bilinear interaction network, is the transposed matrix of the output of the graph encoder.

[0091] The method provided in this application embodiment learns feature representations using graph structure information and node features, allowing the model to discover the inherent structure and patterns of data without labels. Through these steps, the model is able to map the original features into a high-dimensional space, where the similarity of features is determined by both the graph structure and node features, which facilitates subsequent tasks such as clustering, classification, or dimensionality reduction.

[0092] Step 107: Set a loss function to optimize the two graph encoders and complete the training of the two graph encoders. The loss function includes a bidirectional weighted likelihood loss function L c And the feature contrast loss function L f .

[0093] Specifically, define the loss function To optimize the classification performance of the model, the loss function is trained by maximizing the likelihood of positive examples and minimizing the likelihood of negative samples, which is expressed as:

[0094]

[0095] Among them, N and M are the number of positive samples and negative samples respectively. The loss functions in the two directions are weighted averaged to obtain the final bidirectional weighted likelihood loss function L c , expressed as:

[0096]

[0097] This embodiment uses the joint loss function in the model training process, comprehensively considering the losses in two directions, and optimizing the performance of the model in the classification task by balancing the maximization likelihood of positive samples and the minimization likelihood of negative samples, thereby improving its ability to distinguish between positive and negative samples.

[0098] Furthermore, in order to enhance the independence of features in the latent space, this embodiment provides a feature contrast loss function L f Specifically, define the feature matrix Where D is the feature dimension and N is the number of positive samples. Its transposed matrix

[0099] By calculating the transpose of the feature matrix Z The dot product with itself is then normalized to obtain the feature-level similarity matrix S i，j, used to quantify the similarity between each feature, expressed as:

[0100]

[0101] Among them, S i，j Represents the cosine similarity between feature i and feature j, matrix S i，j The value range is [-1, 1].

[0102] Feature contrast loss function L f , by transforming the matrix S i，j The diagonal elements of are treated as positive samples, and the off-diagonal elements are treated as negative samples. Feature contrast loss function L f The expression is as follows:

[0103]

[0104] Among them, index(j) is the negative example index sampled from a uniform distribution from 0 to μ, e is the current training round, E is the total training round, is a predetermined constant (set to 0.5), R is the index range. N is the number of positive samples, and M is the number of negative samples. ii is the diagonal element of the feature-level similarity matrix S, S index(j) are the off-diagonal elements corresponding to negative examples. γ controls the sensitivity of the similarity.

[0105] The final loss function is:

[0106] Loss = L c +L f

[0107] Step 108: Based on the two trained graph encoders, output a high-dimensional feature vector corresponding to the partial discharge signal.

[0108] Step 109: Input the high-dimensional feature vector corresponding to the partial discharge signal into the skeleton initialization K-means clustering (Baackbone initialization K-means; hereinafter referred to as BK-means) to perform partial discharge (PD) type classification.

[0109] This example applies BK-means clustering to PD signals based on the obtained high-dimensional feature vectors. BK-means clustering uses the K-means algorithm to obtain a set of local optimal solutions (clustering results). Skeletal clusters are then obtained by intersecting these local optimal solutions. Skeletal clusters are then used to construct an initial skeleton solution and a new search space. Finally, the initial skeleton solution guides the K-means algorithm to search for clustering results in the new search space.

[0110] Compared with the prior art, the technical solution provided in Example 1 of the present application has the following beneficial effects:

[0111] The technical solutions provided by the embodiments of this application effectively capture the complex features of partial discharge signals through graph structure feature extraction and the construction of high-dimensional feature vectors, thereby improving classification accuracy. By adopting a negative sample sampling strategy within a dynamic threshold range, the blindness of negative sample selection is avoided, enabling the model to better learn the characteristic differences of partial discharge signals during training. Furthermore, the use of a ResGCN-based graph encoder and a BK-Means clustering algorithm not only enables the processing of large-scale data sets but also enables accurate classification of partial discharge types while maintaining computational efficiency, demonstrating high practicality and reliability.

[0112] Example 2

[0113] In Example 2 of this application, 11 representative clustering techniques were compared and validated. The experimental results, as shown in Table 1, demonstrate that BK-means is capable of achieving highly cohesive and highly separated clustering results. The novel graph data clustering method provided in this example significantly improves clustering accuracy and surpasses existing traditional and deep learning methods in multiple performance metrics.

[0114] See Table 1 for a comparison of the performance of different models.

[0115] Method ACC NMI ARI F1 K-Means 63.89 63.17 56.71 55.94 Spectral Clustering 54.83 39.6 34.38 50.82 Ward Hierarchical 62.81 62.69 55.36 54.74 BK-Means 77.28 66.23 69.93 66.08 GAE 68.74 63.06 61.08 65.95 DFCN 74.65 69.61 66.35 63.18 GCSEE 76.27 53.49 54.62 60.85 DCRN 83.16 79.50 73.76 68.49 DCLN 88.34 81.51 84.35 81.27 EGAE 92.36 85.75 87.62 89.16 SGCC 95.54 85.92 89.81 94.61

[0116] As shown in Table 1, the method provided in the embodiment of the present application shows a significant improvement in the four indicators of accuracy (ACC), normalized mutual information (NMI), adjusted Rand index (ARI) and F1 value. Compared with the closest existing method EGAE, this method improves ACC by 3.18%, NMI by 0.17%, ARI by 2.19%, and F1 value by 5.45%. This improvement is attributed to the innovative introduction of the positive and negative sample contrast learning mechanism in this application, which effectively emphasizes the differences between classes, thereby enhancing the clustering ability during the encoding process.

[0117] In comparison with deep graph clustering methods (such as GAE, DFCN, GCSEE, etc.), the SGCC method provided in the embodiment of the present application also showed obvious performance improvement, especially under the guidance of contrastive learning, achieving a higher clustering effect.

[0118] The technical effects of the embodiments of the present application have been verified in the clustering task of partial discharge signals, proving that this method can effectively improve the clustering ability of graph data, especially in the processing of unlabeled signal data, and can significantly improve the accuracy and robustness of clustering.

[0119] Although the embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for classifying and identifying partial discharge, characterized in that: include: Acquire a partial discharge signal, and perform graph structure feature extraction on the partial discharge signal to obtain node features of the partial discharge signal; Taking the node features as positive samples, and extracting a negative sample candidate set from the partial discharge signal; Determining a temporal dynamic threshold interval based on the KL divergence between the positive sample and each candidate negative sample in the negative sample candidate set, for performing negative sample sampling; The KL divergence between the sampled negative sample and the positive sample is within the time dynamic threshold interval; Based on the positive samples and negative samples, two ResGCN-based graph encoders are constructed and trained to obtain high-dimensional feature vectors corresponding to partial discharge signals; the loss function of the graph encoder includes a bidirectional weighted likelihood loss function and a feature contrast loss function; According to the high-dimensional feature vector, the partial discharge signal is classified into partial discharge types based on BK-Means.

2. A partial discharge classification and identification method according to claim 1, characterized in that: Extracting graph structure features of the partial discharge signal to obtain node features corresponding to the partial discharge signal includes: Constructing an adjacency matrix for representing a graph structure according to the partial discharge signal, and determining a degree matrix D of the adjacency matrix A; Based on the degree matrix D, the adjacency matrix A is standardized to obtain a standardized adjacency matrix Expressed as: Where I is the identity matrix; Based on the standardized adjacency matrix Enhanced graph structure representation to obtain improved adjacency matrix Expressed as: Among them, α is the transition probability.

3. A partial discharge classification and identification method according to claim 1, characterized in that: The KL divergence between the positive sample and each candidate negative sample in the negative sample candidate set is expressed as: Among them, x represents the positive sample, represents the candidate negative samples in the negative sample candidate set.

4. A partial discharge classification and identification method according to claim 1, characterized in that: Determining a temporal dynamic threshold interval based on the KL divergence between the positive sample and each candidate negative sample in the negative sample candidate set, and performing negative sample sampling, including: Determine the minimum KL divergence value KL between the positive sample and each of the candidate negative samples min and the maximum KL divergence value KL max ; According to the KL min and the KL max , determine the dynamic threshold increment θ, expressed as: θ=φ(KL max -KL min ); where φ is the adjustment factor; According to the KL min 、KL max and the dynamic threshold increment θ, determine the time dynamic threshold interval for negative sample sampling, and the negative sample obtained by sampling The KL divergence between the positive sample and the time dynamic threshold is within the time dynamic threshold interval, which is expressed as: in, is the candidate negative sample in the negative sample candidate set, w t is the time window, t is the time corresponding to the collection of the positive sample, t i is the time corresponding to the collection of the negative sample.

5. The method for classification and identification of partial discharge according to claim 1, characterized in that: Based on the positive and negative samples, two ResGCN-based graph encoders are constructed and trained, including: The positive samples and the negative samples are encoded based on two independent graph convolutional networks GCNs, which are expressed as: Where, is the graph convolution operation of the i-th encoder, is the adjacency matrix, X is the node feature matrix composed of positive samples x, is the parameter of the i-th GCN, δ is the PRelu activation function; According to the graph convolution operation, the output z of the positive sample is obtained 1 、z 2 And the output of the negative sample The output of the positive sample is expressed as: The output of the negative sample is expressed as: Where, Negative samples The negative sample matrix is formed, represents residual connection; According to the output of the positive sample and the negative sample, the feature mean of all samples is calculated to obtain the global feature vector h i , expressed as: In the formula, j represents a single sample, σ is the activation function, n is the number of samples, is the output of the graph-based encoder; The similarity between features is calculated based on a bilinear interaction network, expressed as: Among them, F k represents the output of the bilinear interaction network, W k are the parameters of the bilinear interaction network, is the transposed matrix of the output of the graph encoder.

6. A partial discharge classification and identification method according to claim 1, characterized in that: The bidirectional weighted likelihood loss function L c , expressed as: Where, N is the number of positive samples, M is the number of negative samples; is the feature of the positive sample, is the feature of the negative sample, y is the positive sample label, h 2 is the global vector obtained by the second graph encoder.

7. The method for classifying and identifying partial discharge according to claim 1, characterized in that: The feature contrast loss function is expressed as: Where index(j) is the negative example index sampled from a uniform distribution from 0 to μ, e is the current training round, E is the total training round, is a predetermined constant, R is the index range; N is the number of positive samples, M is the number of negative samples; S ii is the feature-level similarity matrix S i，j The diagonal elements of the feature-level similarity matrix S i，j Used to quantify the cosine similarity between feature i and feature j, S index(j) are the off-diagonal elements corresponding to negative samples; γ is used to control the sensitivity of similarity.

Images