Power communication network fault clustering method based on K-mean value
Patent Information
- Application Number
- CN202410968358.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-19
AI Technical Summary
[0003]当电力通信网发生故障时通过收集数据,然后通过聚类方法能够及时的查出故障问题,而现有的电力通信网故障故障聚类方法其准确性不够高,为了解决该技术问题现提出基于K-均值的电力通信网故障聚类方法及系统
[0047] The power communication network fault clustering method based on K-means provided by the present invention obtains a line data set to be detected of the current formed by the lines in the power outage area; preprocesses the line data set; and performs preprocessing on the line data set. Mining the line data set to obtain frequent item sets; performing Laplace transform on the frequent item sets to obtain the relative entropy set of line characteristic currents; Perform attribute processing of enhanced data features on the entropy set to obtain an enhanced relative entropy set; use K-means clustering algorithm to perform clustering processing on the enhanced relative entropy set to obtain clustering results, and then obtain circuit fault data; through the line The data set is preprocessed and mined, so that the problem data can be accurately found, and the attributes of the data can be enhanced to improve the accuracy of clustering.
Smart Images

Figure CN118981655A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of fault analysis, and in particular to a K-means-based power communication network fault clustering method. Background Art
[0002] The safe and stable operation of the power system has become a prerequisite for social development. An effective power communication network fault diagnosis system can quickly and accurately diagnose faulty components, which is of great significance to the stable operation of the power communication network.
[0003] When a fault occurs in the power communication network, the fault problem can be detected in time by collecting data and then using the clustering method. However, the accuracy of the existing power communication network fault clustering method is not high enough. In order to solve this technical problem, a power communication network fault clustering method and system based on K-means is proposed. Summary of the invention
[0004] In order to solve the technical problems existing in the above-mentioned prior art, the present invention provides a power communication network fault clustering method based on K-means.
[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:
[0006] In a first aspect, in an embodiment provided by the present invention, a power communication network fault clustering method based on K-means is provided, the method comprising the following steps:
[0007] Acquire a line data set to be detected of currents formed by lines in a power outage area;
[0008] Preprocessing the line data set;
[0009] Mining the preprocessed route dataset to obtain frequent itemsets;
[0010] Perform Laplace transform on the frequent item sets to obtain the relative entropy set of line characteristic current;
[0011] Performing attribute processing of enhanced data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set;
[0012] The enhanced relative entropy set is clustered using the K-means clustering algorithm to obtain clustering results and then obtain circuit fault data.
[0013] As a further solution of the present invention, the line data set is current waveform data of two cycles after the moment of line fault in the power outage area.
[0014] As a further solution of the present invention, the preprocessing of the line data set includes:
[0015] The line data set is cleaned and pre-processed.
[0016] As a further solution of the present invention, mining the preprocessed line data set to obtain frequent item sets includes:
[0017] The Aprior i algorithm is used to mine the preprocessed line data set to obtain frequent item sets.
[0018] As a further solution of the present invention, Laplace transform is performed on the frequent item set to obtain a relative entropy set of the line characteristic current, including:
[0019] Perform feature extraction on frequent item sets to obtain feature current sets;
[0020] The characteristic current set is transformed to obtain a relative entropy set corresponding to the characteristic current set.
[0021] As a further embodiment of the present invention,.
[0022] As a further solution of the present invention, the method of performing attribute processing of enhanced data features on the relative entropy set of the line characteristic current to obtain an enhanced relative entropy set includes:
[0023] The relative entropy set of the line characteristic current is processed based on the deep autoencoder to obtain an enhanced relative entropy set.
[0024] As a further solution of the present invention, the deep autoencoder includes an encoder and a decoder;
[0025] The mathematical expression of the encoder is:
[0026] h=f(Wz+b);
[0027] In the formula, z is the sample data set; W and b are the weight and bias values of the encoder respectively;
[0028] The mathematical expression of the decoder is:
[0029]
[0030] Where z is the sample data set; W′ and b′ are the weights and bias values of the decoder.
[0031] As a further solution of the present invention, a K-means clustering algorithm is used to perform clustering processing on the enhanced relative entropy set to obtain a clustering result, including:
[0032] S601, selecting K first center points from the enhanced relative entropy set, wherein K is preset;
[0033] S602, for each data point in the enhanced relative entropy set, calculating the Euclidean distance between the data point and the nearest center point C;
[0034] S603, selecting a second center point according to a probability formula;
[0035] S604. Repeat steps S602 and S603 to obtain K second center points.
[0036] As a further solution of the present invention, the calculation formula of the Euclidean distance is as follows:
[0037]
[0038] Where D i (x) is the Euclidean distance, (a i , b i ) is x i The coordinates of (b i , b j ) are the coordinates of the center point C.
[0039] In a second aspect, in another embodiment provided by the present invention, a fault clustering system for a power communication network fault based on a K-means clustering algorithm is provided, the system comprising: a raw data acquisition module 100, a preprocessing module 200, a frequent item set acquisition module 300, a Laplace transform module 400, an enhanced processing module 500 and a clustering module 600;
[0040] The raw data acquisition module 100 is used to obtain a line data set to be detected of currents formed by lines in a power outage area;
[0041] The preprocessing module 200 is used to preprocess the line data set;
[0042] The frequent item set acquisition module 300 is used to mine the preprocessed line data set to obtain frequent item sets;
[0043] The Laplace transform module 400 is used to perform attribute processing of enhanced data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set;
[0044] The enhanced processing module 500 is used to perform attribute processing of enhanced data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set;
[0045] The clustering module 600 is used to perform clustering processing on the enhanced relative entropy set using the K-means clustering algorithm to obtain a clustering result, and then obtain circuit fault data.
[0046] The technical solution provided by the present invention has the following beneficial effects:
[0047] The K-means-based power communication network fault clustering method provided by the present invention obtains a line data set to be detected of currents formed by lines in a power outage area; preprocesses the line data set; mines the preprocessed line data set to obtain frequent item sets; performs Laplace transform on the frequent item sets to obtain a relative entropy set of line characteristic currents; performs attribute processing of enhancing data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set; clusters the enhanced relative entropy set using a K-means clustering algorithm to obtain a clustering result, and then obtains circuit fault data; by preprocessing the line data set and performing mining processing, problem data can be accurately found, and attribute enhancement processing is performed on the data to improve the accuracy of clustering.
[0048] These and other aspects of the present invention will be more clearly understood in the following description of the embodiments. It should be understood that the above general description and the following detailed description are only exemplary and explanatory and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying creative work.
[0050] Figure 1 The present invention is a flowchart of a method for clustering power communication network faults based on K-means according to an embodiment of the present invention.
[0051] Figure 2 This is a specific flow chart of S30 in the K-means-based power communication network fault clustering method according to an embodiment of the present invention.
[0052] Figure 3 This is a specific flow chart of S40 in the K-means-based power communication network fault clustering method according to an embodiment of the present invention.
[0053] Figure 4 This is a specific flow chart of S60 in the K-means-based power communication network fault clustering method according to an embodiment of the present invention.
[0054] Figure 5 This is a structural diagram of a power communication network fault clustering system based on a K-means clustering algorithm according to an embodiment of the present invention.
[0055] In the figure: original data collection module-100, preprocessing module-200, frequent item set acquisition module-300, Laplace transform module-400, enhanced processing module-500, clustering module-600. DETAILED DESCRIPTION
[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0057] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.
[0058] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0059] Specifically, the embodiments of the present invention are further described below in conjunction with the accompanying drawings.
[0060] See also Figure 1 , Figure 1 is a flow chart of a K-means-based power communication network fault clustering method provided by an embodiment of the present invention, such as Figure 1 As shown, the K-means-based power communication network fault clustering method includes steps S10 to S50.
[0061] S10, obtaining a line data set to be detected of currents formed by lines in a power outage area;
[0062] In an embodiment of the present invention, the line data set is current waveform data of two cycles after the moment of line fault in the power outage area.
[0063] S20, preprocessing the line data set;
[0064] In an embodiment of the present invention, the step S20 of preprocessing the line data set includes:
[0065] The line data set is cleaned and pre-processed.
[0066] S30, mining the preprocessed route data set to obtain frequent item sets;
[0067] In an embodiment of the present invention, the step S30 of mining the preprocessed line data set to obtain frequent item sets includes:
[0068] The April algorithm is used to mine the preprocessed line data set to obtain frequent itemsets.
[0069] It should be noted that the April algorithm is the first association rule mining algorithm. It pioneered the use of support-based pruning technology to systematically control the exponential growth of candidate item sets.
[0070] See also Figure 2 In an embodiment of the present invention, the method of mining the preprocessed line data set using the April algorithm to obtain frequent item sets includes the following steps:
[0071] S301, scanning the preprocessed line data set, and extracting candidate 1-item sets, and according to a given minimum support s, extracting item sets whose frequency is not less than the support s to form frequent 1-item sets.
[0072] S302, scan the preprocessed line data set and extract the set of candidate 2-item sets, and judge each 2-item set in the set, exclude the 2-item sets that do not contain frequent 1-item sets, and form a new set as a candidate set. Select the frequent 2-item sets according to the support s.
[0073] S303, repeat the idea of S302 to obtain frequent 3-item sets, frequent 4-item sets, ... frequent n-item sets, and none of the n+1-item sets meets the support threshold condition.
[0074] S304: Given the confidence, determine whether each frequent item set rule is a valid rule, calculate the lift of the rule, and determine whether the strong rule is valid.
[0075] S40. Perform Laplace transform on the frequent item set to obtain a relative entropy set of the line characteristic current.
[0076] See also Figure 3 In an embodiment of the present invention, S40, performing Laplace transform on the frequent item set to obtain a relative entropy set of the line characteristic current, includes:
[0077] S401, extracting features from frequent item sets to obtain feature current sets;
[0078] S402: transform the characteristic current set to obtain a relative entropy set corresponding to the characteristic current set.
[0079] S50, performing attribute processing of enhancing data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set;
[0080] In an embodiment of the present invention, the step S50 of performing attribute processing of enhancing data features on the relative entropy set of the line characteristic current to obtain an enhanced relative entropy set includes:
[0081] The relative entropy set of the line characteristic current is processed based on the deep autoencoder to obtain an enhanced relative entropy set.
[0082] Deep AutoEncoder (AE) is an unsupervised learning algorithm that can achieve lossless input and output of data, while converting input data from high-dimensional space to low-dimensional space, further reducing the amount of calculation. Deep AutoEncoder consists of two parts: encoder and decoder. Assuming that the encoder is a function h = f(z), the decoder is a function
[0083] The mathematical expressions of the encoder and decoder are:
[0084] h=f(Wz+b)
[0085]
[0086] Where z is the sample data set; W and b are the weight and bias values of the encoder respectively; W′ and b′ are the weight and bias values of the decoder.
[0087] When the amount of data in the encoder and decoder is too large, the autoencoder will copy the complete input data to the decoder, which makes it difficult to play the role of dimensionality reduction. Therefore, this paper adds sparse constraints to the autoencoder network, the purpose of which is to limit the number of neurons in the network. Sparsity refers to the number of 0s in the data. Let the sparse term be Ω(h), then the sparse loss function is as follows:
[0088] f Loss =L(z,g(f(x)))+Ω(h).
[0089] S60, clustering the enhanced relative entropy set using a K-means clustering algorithm to obtain a clustering result, and then obtain circuit fault data.
[0090] See also Figure 4 In an embodiment of the present invention, the step S60 of clustering the enhanced relative entropy set using a K-means clustering algorithm to obtain a clustering result includes:
[0091] S601, selecting K first center points C from the enhanced relative entropy set; wherein K is preset;
[0092] S602, for each data point in the enhanced relative entropy set, calculating the Euclidean distance between the data point and the nearest center point C;
[0093] The calculation formula of Euclidean distance is as follows:
[0094]
[0095] Where D i (x) is the Euclidean distance, (a i , b i ) is x i The coordinates of (b i , b j ) are the coordinates of the center point C.
[0096] The cumulative value calculation formula of Euclidean distance is:
[0097] S j =ΣD i (x) 2 .
[0098] S603, the second center point C is selected according to the probability formula j ;
[0099] The probability formula is as follows:
[0100]
[0101] S604, repeat steps S502 and S503 to obtain K second center points C j .
[0102] The K-means clustering algorithm of the present invention can accurately cluster faults to obtain fault information.
[0103] The present invention can accurately and effectively improve the accuracy of fault clustering.
[0104] The present invention obtains a line data set to be detected of currents formed by lines in a power outage area; preprocesses the line data set; mines the preprocessed line data set to obtain frequent item sets; performs Laplace transform on the frequent item sets to obtain a relative entropy set of line characteristic currents; performs attribute processing of enhancing data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set; clusters the enhanced relative entropy set using a K-means clustering algorithm to obtain a clustering result, and then obtains circuit fault data; by preprocessing and mining the line data set, problem data can be accurately found, and attribute enhancement processing is performed on the data to improve the accuracy of clustering.
[0105] It should be understood that, although described in a certain order, these steps are not necessarily performed in sequence in the above order. Unless there is clear explanation in this article, the execution of these steps does not have strict order restriction, and these steps can be performed in other orders. Moreover, a part of the steps of the present embodiment may include a plurality of steps or a plurality of stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a part of the steps or stages in other steps or other steps.
[0106] In one embodiment, see Figure 4 As shown, in an embodiment of the present invention, a power communication network fault clustering system based on the K-means clustering algorithm is also provided, which includes an original data acquisition module 100, a preprocessing module 200, a frequent item set acquisition module 300, a Laplace transform module 400, an enhanced processing module 500 and a clustering module 600.
[0107] The raw data acquisition module 100 is used to obtain a line data set to be detected of currents formed by lines in a power outage area.
[0108] In an embodiment of the present invention, the line data set is current waveform data of two cycles after the moment of line fault in the power outage area.
[0109] The preprocessing module 200 is used to preprocess the line data set.
[0110] In the embodiment of the present invention, the preprocessing module 200 is used to perform cleaning and screening preprocessing on the line data set.
[0111] The frequent item set acquisition module 300 is used to mine the preprocessed route data set to obtain frequent item sets.
[0112] In the embodiment of the present invention, the frequent itemset acquisition module 300 is used to mine the preprocessed line data set using the Aprili algorithm to obtain frequent itemsets.
[0113] The Laplace transform module 400 is used to perform attribute processing of enhancing data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set.
[0114] In an embodiment of the present invention, the Laplace transform module 400 is used to process the relative entropy set of the line characteristic current based on a deep autoencoder to obtain an enhanced relative entropy set.
[0115] The enhanced processing module 500 is used to perform attribute processing of enhanced data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set.
[0116] The clustering module 600 is used to perform clustering processing on the enhanced relative entropy set using the K-means clustering algorithm to obtain a clustering result, and then obtain circuit fault data.
[0117] In one embodiment, see Figure 5 As shown, in an embodiment of the present invention, a computer device is also provided, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus.
[0118] Memory, used to store computer programs;
[0119] The processor is used to execute the computer program stored in the memory to execute the power communication network fault clustering method based on the K-mens clustering algorithm. When the processor executes the instructions, the steps in the above method embodiment are implemented:
[0120] S10, obtaining a line data set to be detected of currents formed by lines in a power outage area;
[0121] S20, preprocessing the line data set;
[0122] S30, mining the preprocessed route data set to obtain frequent item sets;
[0123] S40, performing Laplace transform on the frequent item set to obtain a relative entropy set of line characteristic current;
[0124] S50, performing attribute processing of enhancing data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set;
[0125] S60, clustering the enhanced relative entropy set using a K-means clustering algorithm to obtain a clustering result, and then obtain circuit fault data.
[0126] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
[0127] The communication interface is used for communication between the above terminal and other devices.
[0128] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.
[0129] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.
[0130] The computer device includes user devices and network devices. The user devices include but are not limited to computers, smart phones, PDAs, etc. The network devices include but are not limited to a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of computers or network servers based on cloud computing (Cloud Computing), wherein cloud computing is a type of distributed computing, a super virtual computer consisting of a group of loosely coupled computer sets. The computer device can be operated alone to implement the present invention, or it can be connected to the network and implement the present invention through interactive operations with other computer devices in the network. The network where the computer device is located includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, VPN network, etc.
[0131] It should be further understood that the term “and / or” used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0132] In one embodiment of the present invention, a storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented:
[0133] S10, obtaining a line data set to be detected of currents formed by lines in a power outage area;
[0134] S20, preprocessing the line data set;
[0135] S30, mining the preprocessed route data set to obtain frequent item sets;
[0136] S40, performing Laplace transform on the frequent item set to obtain a relative entropy set of line characteristic current;
[0137] S50, performing attribute processing of enhancing data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set;
[0138] S60, clustering the enhanced relative entropy set using a K-means clustering algorithm to obtain a clustering result, and then obtain circuit fault data.
[0139] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiment method can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the process of the embodiment of the above-mentioned method. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory.
[0140] It should be understood that, as used herein, the singular form "a" or "an" is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations of one or more of the items listed in association. The serial numbers of the embodiments disclosed in the above embodiments of the present invention are for description only and do not represent the advantages and disadvantages of the embodiments.
[0141] Those skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the above embodiments of the present invention, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.
Claims
1. A K-means-based power communication network fault clustering method, characterized in that: The method includes: Acquire a line data set to be detected of currents formed by lines in a power outage area; Preprocessing the line data set; Mining the preprocessed route dataset to obtain frequent itemsets; Perform Laplace transform on the frequent item sets to obtain the relative entropy set of line characteristic current; Performing attribute processing of enhanced data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set; The enhanced relative entropy set is clustered using the K-means clustering algorithm to obtain clustering results and then obtain circuit fault data.
2. The power communication network fault clustering method based on K-means according to claim 1, characterized in that: The line data set is current waveform data of two cycles after the line fault in the power outage area.
3. The power communication network fault clustering method based on K-means according to claim 1, characterized in that: The preprocessing of the line data set includes: The line data set is cleaned and pre-processed.
4. The power communication network fault clustering method based on K-means according to claim 1, characterized in that: The method of mining the preprocessed line data set to obtain frequent item sets includes: The Apriori algorithm is used to mine the preprocessed line data set to obtain frequent itemsets.
5. The K-means-based power communication network fault clustering method according to claim 4, characterized in that: Perform Laplace transform on the frequent item sets to obtain the relative entropy set of line characteristic current, including: Perform feature extraction on frequent item sets to obtain feature current sets; The characteristic current set is transformed to obtain a relative entropy set corresponding to the characteristic current set.
6. The power communication network fault clustering method based on K-means according to claim 1, characterized in that: The method of performing attribute processing of enhancing data features on the relative entropy set of the line characteristic current to obtain an enhanced relative entropy set includes: The relative entropy set of the line characteristic current is processed based on the deep autoencoder to obtain an enhanced relative entropy set.
7. The K-means-based power communication network fault clustering method according to claim 6, characterized in that: The deep autoencoder comprises an encoder and a decoder; The mathematical expression of the encoder is: h=f(Wz+b); In the formula, z is the sample data set; W and b are the weight and bias values of the encoder respectively; The mathematical expression of the decoder is: Where z is the sample data set; W′ and b′ are the weights and bias values of the decoder.
8. The power communication network fault clustering method based on K-means according to claim 1, characterized in that: The enhanced relative entropy set is clustered using the K-means clustering algorithm to obtain clustering results, including: S601, selecting K first center points from the enhanced relative entropy set, wherein K is preset; S602, for each data point in the enhanced relative entropy set, calculating the Euclidean distance between the data point and the nearest center point C; S603, selecting a second center point according to a probability formula; S604. Repeat steps S602 and S603 to obtain K second center points.
9. The power communication network fault clustering method based on K-means according to claim 1, characterized in that: The calculation formula of Euclidean distance is as follows: Where D i (x) is the Euclidean distance, (a i , b i ) is x i The coordinates of (b i , b j ) are the coordinates of the center point C.
10. A fault clustering system for power communication network based on K-means clustering algorithm, characterized in that: The system includes: an original data acquisition module, a preprocessing module, a frequent item set acquisition module, a Laplace transform module, an enhanced processing module and a clustering module; The raw data acquisition module is used to obtain a line data set to be detected of currents formed by lines in a power outage area; The preprocessing module is used to preprocess the line data set; The frequent item set acquisition module is used to mine the preprocessed line data set to obtain frequent item sets; The Laplace transform module is used to perform attribute processing of enhanced data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set; The strong processing module is used to perform attribute processing of enhancing data features on the relative entropy set of the line characteristic current set to obtain an enhanced relative entropy set; The clustering module is used to perform clustering processing on the enhanced relative entropy set using the K-means clustering algorithm to obtain a clustering result, and then obtain circuit fault data.
