Abnormality identification method of mixed gas insulation equipment based on multivariate information processing

Abstract

The embodiment of the invention discloses a mixed gas insulation equipment abnormity identification method based on multivariate information processing, and the method comprises the steps: obtaining original data, the original data comprises a multi-band signal in the sulfur hexafluoride and nitrogen mixed gas insulation equipment; performing dimension reduction processing on the original data to obtain dimension-reduced data; and on the basis of the dimension reduction data, a discharge clustering algorithm is used for calculation to obtain an anomaly identification result, and fault identification of the SF6 / N2 mixed gas insulation equipment can be efficiently realized.

Description

Technical Field

[0001] This invention relates to the field of discharge detection technology, and in particular to an anomaly identification method for mixed gas insulation equipment based on multi-source information processing. Background Technology

[0002] Low-carbon and environmentally friendly combined electrical equipment using SF6 mixed gas has been gradually promoted and applied in recent years. However, the insulation medium characteristics and failure modes of mixed gas are significantly different from those of pure SF6 gas, making it difficult for existing insulation condition sensing technologies and insulation evaluation indicators to fully meet the operation, maintenance, and condition-based maintenance requirements of low-carbon combined electrical equipment.

[0003] Therefore, there is an urgent need for an efficient method for identifying anomalies or faults in mixed gas insulation equipment. Summary of the Invention

[0004] The main objective of this invention is to provide an anomaly identification method for mixed gas insulation equipment based on multi-source information processing, which can efficiently achieve fault identification of SF6 / N2 mixed gas insulation equipment.

[0005] To achieve the above objectives, this application provides an anomaly identification method for mixed gas insulation equipment based on multi-source information processing, the method comprising:

[0006] Obtain raw data, which includes the principal components of the statistical characteristic parameters of multi-band ultra-high frequency signals in the sulfur hexafluoride-nitrogen mixed gas insulation equipment;

[0007] The original data is subjected to dimensionality reduction processing to obtain dimensionality-reduced data;

[0008] Based on the reduced-dimensional data, a discharge clustering algorithm is used to calculate and obtain anomaly identification results.

[0009] Optionally, the step of performing dimensionality reduction processing on the original data to obtain dimensionality-reduced data includes:

[0010] Generate an original dataset matrix based on the original data;

[0011] Calculate the covariance matrix of the original dataset matrix;

[0012] The eigenvalues ​​and corresponding eigenvectors of the covariance matrix are calculated, and the corresponding eigenvectors are rearranged in descending order of the eigenvalues ​​to obtain the target matrix.

[0013] Multiply the original dataset matrix by the target matrix to obtain the parameter matrix;

[0014] The first k row vectors in the parameter matrix are obtained as the data after the original data is reduced to k dimensions, where k is a positive integer.

[0015] Optionally, the original dataset matrix is:

[0016]

[0017] Wherein, n is the number of UHF signal bands, m is the number of statistical feature parameters, and x is the element in the matrix. nm This represents the m-th statistical characteristic parameter in the n-th frequency band.

[0018] Optionally, k = 2; the dimensionality-reduced data are the first and second principal components of the original data after dimensionality reduction;

[0019] The anomaly identification results include a clustering result scatter plot, where the horizontal axis of the clustering result scatter plot is the first principal component, and the vertical axis of the clustering result scatter plot is the second principal component.

[0020] Optionally, the step of using a discharge clustering algorithm based on the dimensionality-reduced data to obtain anomaly identification results includes:

[0021] Obtain the number of clusters and select the initial cluster;

[0022] Calculate the Euclidean distance from each data point in the dimensionality-reduced data to the cluster center, assign each data point to the nearest cluster, and update the cluster center of each cluster; repeat this step until the cluster center no longer changes, the clustering is completed, and the anomaly identification result is obtained.

[0023] Optionally, the number of clusters is equal to the number of discharge types, p;

[0024] The selection of initial clusters includes randomly selecting p initial clusters.

[0025] Optionally, the discharge type includes one or more of the following:

[0026] Surface discharge, floating discharge, and tip discharge.

[0027] This application also provides an anomaly detection device, including:

[0028] The acquisition module acquires raw data, which includes multi-band signals in the sulfur hexafluoride-nitrogen mixed gas insulation equipment.

[0029] The dimensionality reduction module is used to perform dimensionality reduction processing on the original data to obtain dimensionality-reduced data;

[0030] The clustering module is used to perform calculations based on the dimensionality-reduced data using a discharge clustering algorithm to obtain anomaly identification results.

[0031] Optionally, the dimensionality reduction module is specifically used for:

[0032] Generate an original dataset matrix based on the original data;

[0033] Calculate the covariance matrix of the original dataset matrix;

[0034] The eigenvalues ​​and corresponding eigenvectors of the covariance matrix are calculated, and the corresponding eigenvectors are rearranged in descending order of the eigenvalues ​​to obtain the target matrix.

[0035] Multiply the original dataset matrix by the target matrix to obtain the parameter matrix;

[0036] The first k row vectors in the parameter matrix are obtained as the data after the original data is reduced to k dimensions, where k is a positive integer.

[0037] Optionally, the original dataset matrix is:

[0038]

[0039] Wherein, n is the number of UHF signal bands, m is the number of statistical feature parameters, and x is the element in the matrix. nm This represents the m-th statistical characteristic parameter in the n-th frequency band.

[0040] Optionally, k = 2; the dimensionality-reduced data are the first and second principal components of the original data after dimensionality reduction;

[0041] The anomaly identification results include a clustering result scatter plot, where the horizontal axis of the clustering result scatter plot is the first principal component, and the vertical axis of the clustering result scatter plot is the second principal component.

[0042] Optionally, the clustering module is specifically used for:

[0043] Obtain the number of clusters and select the initial cluster;

[0044] Calculate the Euclidean distance from each data point in the dimensionality-reduced data to the cluster center, assign each data point to the nearest cluster, and update the cluster center of each cluster; repeat this step until the cluster center no longer changes, the clustering is completed, and the anomaly identification result is obtained.

[0045] Optionally, the number of clusters is equal to the number of discharge types, p;

[0046] The selection of initial clusters includes randomly selecting p initial clusters.

[0047] Optionally, the discharge type includes one or more of the following:

[0048] Surface discharge, floating discharge, and tip discharge.

[0049] In another aspect, this application provides an electronic device including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform steps as described in the first aspect and any possible implementation thereof.

[0050] In another aspect, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the method described in the first aspect.

[0051] This application provides an anomaly identification method for mixed gas insulation equipment based on multi-dimensional information processing. The method involves acquiring raw data, including multi-frequency signals from the sulfur hexafluoride-nitrogen mixed gas insulation equipment; performing dimensionality reduction processing on the raw data to obtain dimensionality-reduced data; and using a discharge clustering algorithm based on the dimensionality-reduced data to calculate anomaly identification results. This method utilizes multi-frequency signals from the SF6 / N2 mixed gas insulation system for efficient discharge type identification, significantly enhancing the partial discharge monitoring capability of the SF6 / N2 mixed gas insulation equipment and enabling efficient fault identification of the SF6 / N2 mixed gas insulation equipment. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] in:

[0054] Figure 1 A flowchart illustrating an anomaly identification method for a mixed gas insulation device based on multi-source information processing, provided in an embodiment of this application;

[0055] Figure 2 This is a schematic diagram of a clustering result scatter plot provided in an embodiment of this application;

[0056] Figure 3 This is a schematic diagram of the structure of an anomaly identification device provided in an embodiment of this application;

[0057] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0058] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0059] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0060] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0061] SF6, mentioned in the embodiments of this application, is the known best electrical insulating medium; however, it is also the industrial gas with the strongest greenhouse effect. Under the overarching goal of "dual carbon" (carbon reduction and emission reduction), developing environmentally friendly alternatives to SF6 and reducing its greenhouse gas consumption is an inevitable choice. Currently, SF6 replacement technologies include using sulfur hexafluoride and nitrogen mixtures, such as SF6 / N2 mixtures, which involve adding 30% N2 to SF6 gas, significantly reducing greenhouse gas consumption while maintaining insulation performance comparable to SF6. At present, SF6 / N2 mixtures are beginning to be widely used in GIS busbars across China.

[0062] The anomaly identification method for mixed gas insulation equipment based on multivariate information processing in this application mainly includes a proposed intelligent clustering identification algorithm for SF6 / N2 mixed gas insulation anomalies based on multivariate information processing. Its components include a dimensionality reduction method for the original dataset and a discharge clustering algorithm based on the dimensionality reduction data.

[0063] Clustering, mentioned in the embodiments of this application, is a commonly used data analysis method that can group similar data points into clusters.

[0064] The embodiments of this application are described below with reference to the accompanying drawings.

[0065] Please see Figure 1 The above is a flowchart illustrating an anomaly identification method for mixed gas insulation equipment based on multi-source information processing, as provided in an embodiment of this application. Figure 1 As shown, the method includes:

[0066] 101. Obtain the raw data, which includes the principal components of the statistical characteristic parameters of the multi-band signals in the sulfur hexafluoride-nitrogen mixed gas insulation equipment;

[0067] 102. Perform dimensionality reduction processing on the above original data to obtain dimensionality-reduced data;

[0068] 103. Based on the dimensionality reduction data mentioned above, the discharge clustering algorithm is used to calculate and obtain the anomaly identification results.

[0069] The method in this embodiment is executed by an anomaly detection device. In practical applications, it can be executed on a terminal device.

[0070] Specifically, the principal components of the statistical feature parameters of multi-band ultra-high frequency signals in the insulation equipment can be extracted as raw data to generate the corresponding matrix. Then, the matrix is ​​dimensionality reduced, and the discharge clustering algorithm is used to calculate the clustering result, i.e., the anomaly identification result, based on the obtained dimensionality-reduced data.

[0071] First, let's explain the dimensionality reduction of the original data.

[0072] In one optional implementation, step 102 includes:

[0073] Generate the original dataset matrix based on the above original data;

[0074] Calculate the covariance matrix of the original dataset matrix mentioned above;

[0075] The eigenvalues ​​and corresponding eigenvectors of the covariance matrix are calculated and obtained. The corresponding eigenvectors are then rearranged in descending order of the eigenvalues ​​to obtain the target matrix.

[0076] Multiply the original dataset matrix above by the target matrix above to obtain the parameter matrix;

[0077] The first k row vectors in the parameter matrix are obtained as the k-dimensional data after the original data is reduced to the above k dimensions, where k is a positive integer.

[0078] In one alternative implementation, the original dataset matrix described above is represented as:

[0079]

[0080] Where n represents the number of the aforementioned UHF signal bands, m represents the number of statistical feature parameters, and x represents the element in the matrix. nm This represents the m-th statistical characteristic parameter in the n-th frequency band, where m and n can both be positive integers.

[0081] Specifically, calculate the covariance matrix of the matrix X mentioned above:

[0082]

[0083]

[0084] Among them, a i Let X represent the i-th column vector of matrix X.

[0085] Furthermore, the eigenvalues ​​and corresponding eigenvectors of matrix V can be obtained. Then, the eigenvalues ​​are arranged in descending order, and their corresponding eigenvectors are rearranged sequentially to obtain the target matrix V'. The original dataset matrix X is multiplied by V' to obtain the parameter matrix B.

[0086] B=XV′

[0087] The first k row vectors in matrix B correspond to the first k principal components, which are the data after reducing the original dataset X to k dimensions.

[0088] In an optional implementation, step 103 includes:

[0089] 31. Obtain the number of clusters and select the initial cluster;

[0090] 32. Calculate the Euclidean distance from each data point in the dimensionality-reduced data to the cluster center, assign each data point to the nearest cluster, and update the cluster center of each cluster; repeat this step until the cluster centers no longer change, the clustering is complete, and the above anomaly identification results are obtained.

[0091] The number of clusters mentioned above can be equal to the number of discharge types p, where the discharge types are the types of discharge defects, such as surface discharge, floating discharge, and tip discharge.

[0092] The above method of selecting initial clusters can be to randomly select p initial clusters, where p is a positive integer.

[0093] In electrical equipment, partial discharge of insulation mainly includes corona discharge, spark discharge, surface discharge, and floating discharge. Different discharge types have different fault signals and gas decomposition products.

[0094] Specifically, step 32 above includes: calculating the Euclidean distance from each data point to the cluster center.

[0095]

[0096] Each point is assigned to the nearest cluster, and then the cluster center of each cluster is updated:

[0097]

[0098] Wherein, t(ψ) j ) represents the number of points in the same cluster.

[0099] Repeat this process until the cluster center no longer changes.

[0100] In one optional implementation, k = 2; the dimensionality-reduced data are the first and second principal components of the original data after dimensionality reduction.

[0101] The above anomaly identification results include a clustering result scatter plot, where the horizontal axis of the clustering result scatter plot is the first principal component, and the vertical axis of the clustering result scatter plot is the second principal component.

[0102] Specifically, in the embodiments of this application, the anomaly identification results obtained can be output in the form of a clustering result scatter plot.

[0103] Visualizing clustering results can help users better understand and analyze data. The scatter plot involved in this embodiment is a commonly used visualization method, which can be used to display the location and distribution of data points in the clustering results. Through the scatter plot, users can intuitively understand the location and size of each cluster in the clustering results, thus enabling better data analysis.

[0104] For example, in one embodiment, the original dataset matrix is ​​represented as:

[0105]

[0106] Where n is the number of UHF signal bands, in this embodiment n = 3; m is the number of statistical feature parameters, in this embodiment m = 435;

[0107] Calculate the covariance matrix of X and its eigenvectors and eigenvalues;

[0108] Extract the eigenvectors corresponding to the two largest eigenvalues, and multiply them by X on the left to obtain the first and second principal components of the original dataset after dimensionality reduction.

[0109] Based on the experimental results, the discharge types were classified into three categories: surface discharge, floating discharge, and tip discharge. Therefore, the number of clusters k (p mentioned above) in the k-means clustering was determined to be 3, and 3 initial cluster centers were randomly selected.

[0110] Calculate the Euclidean distance from each point to the cluster center, assign each point to the nearest cluster, and then update the cluster center of each cluster; repeat this step until the cluster center no longer changes.

[0111] Correspondingly, the clustering identification results are as follows: Figure 2 As shown in the results, this method can achieve high-accuracy discharge type identification.

[0112] Figure 2 This is a schematic diagram of a clustering result scatter plot provided in an embodiment of this application. Figure 2 As shown, the horizontal axis of the scatter plot represents the first principal component, and the vertical axis represents the second principal component. It displays the distribution of data points of three types—surface discharge, floating discharge, and tip discharge—relative to the cluster center. Different types of data points are displayed in different colors, achieving high-accuracy discharge type identification.

[0113] Optionally, the anomaly identification results in this application embodiment may also include other output forms, such as bar charts or text information, and this application embodiment does not limit this.

[0114] The anomaly identification method for mixed gas insulation equipment based on multi-dimensional information processing in this application embodiment utilizes multi-frequency signals in the SF6 / N2 mixed gas insulation system for efficient identification of discharge types, significantly enhancing the partial discharge monitoring capability of SF6 / N2 mixed gas insulation equipment.

[0115] Based on the description of the foregoing method embodiments, this application also discloses an anomaly identification device.

[0116] Figure 3 This is a schematic diagram of the structure of an anomaly detection device provided in an embodiment of this application, as shown below. Figure 3 As shown, the anomaly detection device 300 may include:

[0117] The acquisition module 310 acquires raw data, which includes multi-band signals in the sulfur hexafluoride-nitrogen mixed gas insulation equipment.

[0118] Dimensionality reduction module 320 is used to perform dimensionality reduction processing on the original data to obtain dimensionality-reduced data;

[0119] Clustering module 330 is used to perform calculations based on the dimensionality reduction data using a discharge clustering algorithm to obtain anomaly identification results.

[0120] Optionally, the aforementioned dimensionality reduction module 320 is specifically used for:

[0121] Generate the original dataset matrix based on the above original data;

[0122] Calculate the covariance matrix of the original dataset matrix mentioned above;

[0123] The eigenvalues ​​and corresponding eigenvectors of the covariance matrix are calculated and obtained. The corresponding eigenvectors are then rearranged in descending order of the eigenvalues ​​to obtain the target matrix.

[0124] Multiply the original dataset matrix above by the target matrix above to obtain the parameter matrix;

[0125] The first k row vectors in the parameter matrix are obtained as the data after the original data is reduced to the above k dimensions, where k is a positive integer.

[0126] Optionally, the original dataset matrix above is:

[0127]

[0128] Where n represents the number of the aforementioned UHF signal bands, m represents the number of statistical feature parameters, and x represents the element in the matrix. nm This represents the m-th statistical characteristic parameter in the n-th frequency band.

[0129] Optionally, k = 2; the dimensionality-reduced data are the first and second principal components of the original data after dimensionality reduction.

[0130] The above anomaly identification results include a clustering result scatter plot, where the horizontal axis of the clustering result scatter plot is the first principal component, and the vertical axis of the clustering result scatter plot is the second principal component.

[0131] Optionally, the clustering module 330 mentioned above is specifically used for:

[0132] Obtain the number of clusters and select the initial cluster;

[0133] Calculate the Euclidean distance from each data point in the dimensionality-reduced data to the cluster center, assign each data point to the nearest cluster, and update the cluster center of each cluster; repeat this step until the cluster centers no longer change, the clustering is complete, and the above anomaly identification results are obtained.

[0134] Optionally, the number of clusters mentioned above is equal to the number of discharge types, p;

[0135] The above selection of initial clusters includes randomly selecting p initial clusters.

[0136] Optionally, the above discharge types include one or more of the following:

[0137] Surface discharge, floating discharge, and tip discharge.

[0138] It is understood that the relevant content concerning each module in the above-mentioned device has been described in detail in the foregoing method embodiments, and specific details can be found in the method embodiments; that is, the anomaly identification device provided in this application can perform the following... Figure 1 Any steps in the illustrated embodiments will not be described in detail here.

[0139] In one embodiment of this application, an electronic device is also proposed.

[0140] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 400 includes a processor 401 and a memory 402. The memory 402 stores a computer program, which, when executed by the processor 401, will perform actions such as... Figure 1 Any step in the method embodiment shown. The electronic device 400 may also include input / output devices, etc. In specific embodiments, the electronic device may be a server, terminal device, etc.

[0141] In one embodiment, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor 401, causes the processor 401 to perform any of the steps in the above method embodiments.

[0142] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0143] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0144] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for anomaly identification of hybrid gas insulation equipment based on multi-source information processing, characterized in that, The method includes: Obtain raw data, which includes the principal components of the statistical characteristic parameters of multi-band ultra-high frequency signals in the sulfur hexafluoride-nitrogen mixed gas insulation equipment; The original data is subjected to dimensionality reduction processing to obtain dimensionality-reduced data; Based on the reduced-dimensional data, a discharge clustering algorithm is used to calculate and obtain anomaly identification results.

2. The anomaly identification method for mixed gas insulation equipment based on multi-source information processing according to claim 1, characterized in that, The step of performing dimensionality reduction processing on the original data to obtain dimensionality-reduced data includes: Generate an original dataset matrix based on the original data; Calculate the covariance matrix of the original dataset matrix; The eigenvalues ​​and corresponding eigenvectors of the covariance matrix are calculated, and the corresponding eigenvectors are rearranged in descending order of the eigenvalues ​​to obtain the target matrix. Multiply the original dataset matrix by the target matrix to obtain the parameter matrix; The first k row vectors in the parameter matrix are obtained as the data after the original data is reduced to k dimensions, where k is a positive integer.

3. The anomaly identification method for mixed gas insulation equipment based on multi-source information processing according to claim 2, characterized in that, The original dataset matrix is: Wherein, n is the number of UHF signal bands, m is the number of statistical feature parameters, and x is the element in the matrix. nm This represents the m-th statistical characteristic parameter in the n-th frequency band.

4. The anomaly identification method for mixed gas insulation equipment based on multi-source information processing according to claim 2 or 3, characterized in that, k = 2; the dimensionality-reduced data are the first and second principal components of the original data after dimensionality reduction; The anomaly identification results include a clustering result scatter plot, where the horizontal axis of the clustering result scatter plot is the first principal component, and the vertical axis of the clustering result scatter plot is the second principal component.

5. The anomaly identification method for mixed gas insulation equipment based on multi-source information processing according to claim 1, characterized in that, The anomaly identification results obtained by using a discharge clustering algorithm based on the dimensionality reduction data include: Obtain the number of clusters and select the initial cluster; Calculate the Euclidean distance from each data point in the dimensionality-reduced data to the cluster center, assign each data point to the nearest cluster, and update the cluster center of each cluster; repeat this step until the cluster center no longer changes, the clustering is completed, and the anomaly identification result is obtained.

6. The anomaly identification method for mixed gas insulation equipment based on multi-source information processing according to claim 5, characterized in that, The number of clusters is equal to the number of discharge types, p; The selection of initial clusters includes randomly selecting p initial clusters.

7. The anomaly identification method for mixed gas insulation equipment based on multi-source information processing according to claim 6, characterized in that, The discharge type includes one or more of the following: Surface discharge, floating discharge, and tip discharge.

8. An anomaly detection device, characterized in that, include: The acquisition module acquires raw data, which includes multi-band signals in the sulfur hexafluoride-nitrogen mixed gas insulation equipment. The dimensionality reduction module is used to perform dimensionality reduction processing on the original data to obtain dimensionality-reduced data; The clustering module is used to perform calculations based on the dimensionality-reduced data using a discharge clustering algorithm to obtain anomaly identification results.

9. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, the processor performs the steps of the method as described in any one of claims 1-7.

Images