Self-adaptive wave recording method and device for fault identification, equipment and medium

Abstract

The invention provides a self-adaptive wave recording method and device for fault recognition, electronic equipment and a storage medium, and the method comprises the steps: carrying out the classification of hidden faults in a power distribution network based on the actual engineering data of the power distribution network, and obtaining a classification result; analyzing various types of hidden faults in the classification result to obtain energy distribution rules of various frequency bands corresponding to the various types of hidden faults; constructing a self-adaptive wave recording rule based on the energy distribution rule of each frequency band corresponding to each type of hidden fault; and performing adaptive wave recording on the target line based on the adaptive wave recording rule to obtain a wave recording result. According to the self-adaptive wave recording scheme for fault identification provided by the invention, hidden faults in the power distribution network can be identified more accurately, automation of self-adaptive wave recording is realized, and misjudgment and missed judgment caused by dependence on manual intervention are reduced, so that the power supply reliability of the power distribution network is improved.

Description

Technical Field

[0001] The present application relates to the technical field of relay protection for electric power systems, and in particular to an adaptive recording method, device, electronic equipment and storage medium for fault identification. Background Art

[0002] Electricity is of vital importance in modern society. As an indispensable form of energy, it has a profound impact on the national economy and people's lives. As an important link between the transmission network and power users, the distribution network is responsible for efficiently distributing and transmitting electric energy. The reliability of its operation directly affects the normal production and life of power users.

[0003] However, during the operation of the distribution network, hidden faults are a common and thorny problem. Hidden faults refer to problems that exist in the power system but are not easy to detect. These faults may pose a potential threat to the stability of the system and the normal operation of the equipment. Although hidden faults occur for a short time, their signals are weak and easy to repeat, making them difficult to locate, gradually damaging system performance, and may eventually cause equipment failure or system collapse, thereby reducing the power supply reliability of the distribution network. These hidden faults are of various types and have significant differences in characteristics. It is impossible to summarize unified characteristics and difficult to quickly and intelligently identify them, resulting in difficulty in daily distribution line maintenance, low personnel efficiency and high investment, long system recovery time and difficult evaluation.

[0004] At present, the distribution automation system can isolate the fault in a limited area after the fault occurs, but further fault finding still mainly relies on experience judgment, which is inefficient, time-consuming, and labor-intensive. More than 50% of hidden faults still cannot be accurately checked, laying hidden dangers for subsequent faults. Therefore, in order to efficiently improve the power supply reliability of the distribution network, it is urgent to study the key technologies of hidden fault identification and realize intelligent identification to improve the reliability of power supply.

[0005] Traditional fault recording technology has obvious shortcomings when dealing with hidden faults. Since the fault signals of hidden faults are weak, traditional recording technology often has difficulty in capturing key fault information, resulting in the inability to correctly start fault recording. In this case, missed or misjudged hidden faults often occur, which seriously affects the fault handling efficiency and power supply reliability of the distribution network. It can be seen that the existing technology has many shortcomings in the identification and recording of hidden faults, and a new method that can effectively overcome these problems is urgently needed to improve the fault identification capability and power supply reliability of the distribution network.

[0006] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the invention

[0007] In response to the above technical problems, the present application provides an adaptive recording method, device, electronic device and storage medium for fault identification, which solves the problem that the fault recording cannot be started correctly because the fault signal of the hidden fault is weak and it is difficult to capture the fault information during the recording of hidden faults in the distribution network, thereby improving the fault identification capability and power supply reliability of the distribution network.

[0008] In order to solve the above technical problems, the present application provides an adaptive recording method for fault identification, comprising the following steps:

[0009] Based on actual engineering data of the distribution network, the hidden faults in the distribution network are classified to obtain classification results;

[0010] Analyze various types of hidden faults in the classification results to obtain energy distribution rules of various frequency bands corresponding to various types of hidden faults;

[0011] Based on the energy distribution law of each frequency band corresponding to the various types of hidden faults, an adaptive recording rule is constructed;

[0012] Based on the adaptive recording rule, the target line is adaptively recorded to obtain a recording result.

[0013] Furthermore, in some embodiments of the present application, it also includes:

[0014] Performing fault analysis on the target fault line based on the wave recording result to obtain a fault analysis result;

[0015] Based on the fault analysis result, corresponding alarm information is generated and pushed.

[0016] Furthermore, in some embodiments of the present application, the hidden faults in the distribution network are classified based on the actual engineering data of the distribution network to obtain the classification results, including:

[0017] Acquiring actual engineering data of the distribution network and performing data preprocessing;

[0018] The cluster mining algorithm is used to cluster the pre-processed data of the actual distribution network project to obtain the corresponding hidden fault data;

[0019] According to the waveform features corresponding to the hidden fault data, the hidden fault data is classified to obtain corresponding classification results.

[0020] Further, in some embodiments of the present application, the classifying the hidden fault data to obtain corresponding classification results includes:

[0021] Define the fault type corresponding to the hidden fault, the fault type includes tree barrier fault, lightning arrester breakdown fault and small animal bridging fault, the tree barrier type includes nonlinear permanent grounding fault and instantaneous grounding fault;

[0022] The hidden data is classified based on the fault type to obtain a corresponding classification result.

[0023] Further, in some embodiments of the present application, the definition of the fault type corresponding to the hidden fault includes tree barrier faults, lightning arrester breakdown faults and small animal bridging faults, and the tree barrier type includes nonlinear permanent grounding faults and instantaneous grounding faults, including:

[0024] The fault caused by a tree branch falling on the busbar is defined as a nonlinear permanent grounding fault;

[0025] The fault caused by tree branches hanging on the wire is defined as an instantaneous ground fault;

[0026] The lightning arrester failure caused by meteorological conditions is defined as the lightning arrester breakdown failure;

[0027] Faults caused by small animal jumper circuits are defined as small animal jumper faults.

[0028] Furthermore, in some embodiments of the present application, the various types of hidden faults in the classification results are analyzed to obtain energy distribution rules of various frequency bands corresponding to the various types of hidden faults, including:

[0029] Based on the classification results, analyzing the fault waveform characteristics corresponding to the zero-sequence current in each type of hidden fault;

[0030] Based on the fault waveform characteristics, a spectrum analysis is performed on the zero-sequence current in each type of hidden fault to determine the energy distribution law of each frequency band corresponding to each type of hidden fault.

[0031] Further, in some embodiments of the present application, the step of adaptively recording the target line based on the adaptive recording rule to obtain the recording result includes:

[0032] Real-time measurement of the current zero-sequence current waveform and current energy distribution law of the target line;

[0033] Based on the current zero-sequence current waveform and the current energy distribution law, matching is performed with a preset fault judgment rule to obtain a matching result;

[0034] After determining that the match is successful based on the matching result, adaptively recording the target line based on the adaptive recording rule, and collecting zero-sequence current waveform data of the target line;

[0035] Based on the collected zero-sequence current waveform data, a waveform recording result is generated.

[0036] Accordingly, the present application also provides an adaptive wave recording device for fault identification, comprising:

[0037] A classification module, used for classifying hidden faults in the distribution network based on actual engineering data of the distribution network to obtain classification results;

[0038] An analysis module, used to analyze various types of hidden faults in the classification results to obtain energy distribution rules of various frequency bands corresponding to various types of hidden faults;

[0039] A construction module, used to construct an adaptive recording rule based on the energy distribution law of each frequency band corresponding to the various types of hidden faults;

[0040] The wave recording module is used to perform adaptive wave recording on the target line based on the adaptive wave recording rule to obtain a wave recording result.

[0041] The present application also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the adaptive recording method for fault identification as described above are implemented.

[0042] The present application also provides a storage medium storing a computer program that can be loaded by a processor and execute the adaptive waveform recording method for fault identification as described above.

[0043] Implementing the embodiments of the present application has the following beneficial effects:

[0044] As described above, the present application provides an adaptive recording method, device, electronic device and storage medium for fault identification, and the adaptive recording method for fault identification includes: based on the actual engineering data of the distribution network, classifying the hidden faults in the distribution network to obtain the classification results; analyzing the various types of hidden faults in the classification results to obtain the energy distribution laws of each frequency band corresponding to the various types of hidden faults; constructing adaptive recording rules based on the energy distribution laws of each frequency band corresponding to the various types of hidden faults; adaptively recording the target line based on the adaptive recording rules to obtain the recording results. The adaptive recording scheme for fault identification provided by the present application can more accurately identify the hidden faults in the distribution network by analyzing the zero-sequence current waveform characteristics and the frequency band energy distribution law, and use the fault waveform characteristics and energy distribution law as the starting criteria to realize the automation of adaptive recording, reduce the dependence on manual intervention, reduce the misjudgment and missed judgment of hidden faults through precise feature analysis and criterion setting, improve the operation reliability of the distribution network, and help reduce the impact of faults on the distribution network by quickly and accurately identifying and responding to hidden faults, and improve the continuity and reliability of power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.

[0046] Figure 1 It is a schematic diagram of an application scenario of an adaptive wave recording method for fault identification provided in an embodiment of the present application;

[0047] Figure 2 It is a flowchart of an adaptive wave recording method for fault identification provided by an embodiment of the present application;

[0048] Figure 3 It is a time domain diagram of zero-sequence current of a busbar with a tree branch provided in an embodiment of the present application;

[0049] Figure 4 It is a time domain diagram of zero-sequence current of a tree branch hanging line provided in an embodiment of the present application;

[0050] Figure 5 It is a time domain diagram of the zero-sequence current of the lightning arrester provided in the embodiment of the present application;

[0051] Figure 6 It is a schematic diagram of the energy proportion of zero-sequence current in different frequency bands under the tree branch-mounted busbar provided in an embodiment of the present application;

[0052] Figure 7 It is a schematic diagram of the energy proportion of zero-sequence current in different frequency bands under the tree branch hanging line provided in an embodiment of the present application;

[0053] Figure 8 It is a schematic diagram of the energy proportion of zero-sequence current in different frequency bands under the breakdown of the lightning arrester provided in the embodiment of the present application;

[0054] Fig. 9 is another flow chart of an adaptive wave recording method for fault identification provided by an embodiment of the present application;

[0055] Fig.10 It is a structural schematic diagram of an adaptive recording device for fault identification provided in an embodiment of the present application;

[0056] Fig.11 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0057] The realization of the purpose, functional features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings have shown clear embodiments of this application, which will be described in more detail later. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0058] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0059] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0060] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0062] The present application provides an adaptive recording method, device, electronic device and storage medium for fault identification.

[0063] The adaptive recording device for fault identification can be integrated into an electronic device, which can be a smart phone, a tablet computer, a laptop or a desktop computer, but is not limited thereto. The electronic device can be directly or indirectly connected to the server through wired or wireless communication. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. This application does not limit this.

[0064] See also Figure 1 , Figure 1 FIG. 1 is an application environment diagram of an adaptive wave recording method for fault identification in one embodiment. Figure 1 , the adaptive recording method for fault identification can be applied to an adaptive recording system for fault identification. Among them, the adaptive recording system for fault identification may include a terminal 110 and a server 120. The terminal 110 and the server 120 are connected through a network, and the terminal 110 can be a desktop terminal or a mobile terminal, and the mobile terminal can be at least one of a mobile phone, a tablet computer, a laptop computer, etc. The server 120 can be implemented as an independent server or a server cluster composed of multiple servers. The terminal 110 is used to classify the hidden faults in the distribution network based on the actual engineering data of the distribution network to obtain the classification results; analyze the various types of hidden faults in the classification results to obtain the energy distribution laws of each frequency band corresponding to the various types of hidden faults; construct an adaptive recording rule based on the energy distribution laws of each frequency band corresponding to the various types of hidden faults; based on the adaptive recording rules, the target line is adaptively recorded to obtain the recording results.

[0065] The signal of hidden faults is weak and easy to repeat, which is difficult to locate, gradually damaging the system performance, and may eventually lead to equipment failure or system crash, thereby reducing the power supply reliability of the distribution network. These hidden faults are of various types, and their characteristics are significantly different. It is impossible to summarize unified characteristics, and it is difficult to quickly and intelligently identify them, which leads to difficulties in daily distribution line maintenance, low personnel input efficiency, high investment, long system recovery time and difficult evaluation. After the fault occurs, distribution automation can isolate the fault in a limited area, but further search still mainly relies on experience judgment, which is inefficient, time-consuming, and labor-intensive. More than 50% of hidden faults still cannot be accurately checked, which lays hidden dangers for subsequent faults. Therefore, in order to efficiently improve the power supply reliability of the distribution network, it is urgent to study the key technologies of hidden fault identification and realize intelligent identification to improve the reliability of power supply.

[0066] It should be noted that the order of description of the following embodiments is not intended to limit the priority order of the embodiments.

[0067] The present application provides an adaptive recording method for fault identification, comprising: classifying hidden faults in a distribution network based on actual engineering data of the distribution network to obtain classification results; analyzing various types of hidden faults in the classification results to obtain energy distribution rules in various frequency bands corresponding to various types of hidden faults; constructing adaptive recording rules based on energy distribution rules in various frequency bands corresponding to various types of hidden faults; and adaptively recording a target line based on the adaptive recording rules to obtain a recording result.

[0068] See also Figure 2 , Figure 2 1 is a flow chart of an adaptive wave recording method for fault identification provided by an embodiment of the present application. The adaptive wave recording method for fault identification provided by this embodiment may specifically include the following steps:

[0069] S1. Based on the actual engineering data of the distribution network, the hidden faults in the distribution network are classified to obtain the classification results;

[0070] Specifically, for step S1, based on the actual engineering data of the distribution network, the hidden faults in the distribution network are classified. For example, according to the common hidden obstacles in the actual engineering conditions of the distribution network, the fault types are divided into three situations: tree obstacles, lightning arrester breakdown, and small animal bridging, so as to realize adaptive recording of the vast majority of hidden faults encountered in engineering practice.

[0071] S2. Analyze various types of hidden faults in the classification results to obtain energy distribution rules of various frequency bands corresponding to various types of hidden faults;

[0072] Specifically, for step S2, by analyzing the transient voltage and current recording data in the existing fault cases, the zero-sequence current waveform distortion characteristics are used to characterize the characteristics of different hidden faults in the distribution network. Therefore, the energy distribution law of zero-sequence current in different frequency bands is used to distinguish different hidden faults in the distribution network, and then the three common hidden faults in the distribution network are divided by performing spectrum analysis on the instantaneous value of zero-sequence current.

[0073] S3. Construct adaptive recording rules based on the energy distribution rules of each frequency band corresponding to various types of hidden faults;

[0074] Specifically, for step S3, based on the fault waveform characteristics of zero-sequence current under different fault types, the start criterion of adaptive recording is constructed. The time to start recording is inferred according to the characteristics of the fault waveform to achieve adaptive recording of different hidden faults in the distribution network.

[0075] S4. Adaptively record the target line based on the adaptive recording rules to obtain the recording results;

[0076] Specifically, for step S4, the target line is adaptively recorded based on the constructed adaptive recording rules to obtain the recording results. Based on the energy distribution law of zero-sequence current in different frequency bands of three common hidden faults in the distribution network, the adaptive recording of the distribution automation terminal is started to collect and record the zero-sequence current waveform of the fault line during the fault. This step is the process of actually capturing fault data, which provides a basis for subsequent fault analysis and processing.

[0077] It can be seen that the adaptive recording method for fault identification provided in this embodiment can more accurately identify hidden faults in the distribution network and reduce missed judgments and misjudgments through the adaptive recording method; quickly and accurately identify and respond to faults, reduce the impact of faults on the operation of the distribution network, and improve the reliability of power supply; automated fault identification and recording reduce reliance on manual inspections, reduce maintenance costs and human resource consumption; and can dynamically adjust the recording strategy according to the power grid status, thereby improving the flexibility and response speed of the system.

[0078] Furthermore, in some embodiments, the adaptive waveform recording method for fault identification in this embodiment further includes:

[0079] S51. Perform fault analysis on the target fault line based on the recording results to obtain the fault analysis results;

[0080] S52. Based on the fault analysis results, generate corresponding alarm information and push it.

[0081] Specifically, this embodiment also provides a method for fault analysis and alarm push based on the recording results, and based on the obtained recording results, an in-depth fault analysis is performed on the target fault line. This step involves a detailed inspection of the recording data to identify the specific type and location of the fault. According to the results of the fault analysis, corresponding alarm information is generated. These alarm messages should contain key information such as the type, location, and possible impact of the fault so that relevant personnel can take prompt action. The generated alarm information is pushed to relevant maintenance personnel or automation systems through appropriate communication channels. This may include text messages, emails, mobile application notifications, or other real-time communication methods.

[0082] In order to improve the efficiency and effectiveness of fault handling, this embodiment also integrates automation tools to automatically trigger a series of preset response measures once a fault is detected, such as isolating the fault area, rerouting power, etc.; develop an intelligent alarm system that can push alarm information according to the severity and type of the fault and provide suggestions for fault handling; use augmented reality technology to provide real-time fault location and fault type information to on-site staff to improve the efficiency of fault location and repair; collect and analyze historical fault data to identify potential failure modes and trends, and further optimize fault prediction and response strategies; deploy the fault analysis and alarm system on a cloud platform to improve the scalability, reliability and remote access capabilities of the system.

[0083] This embodiment can respond to faults quickly, reduce power outage time, and improve user satisfaction through automated fault analysis and alarm push; timely alarms and accurate fault information can help maintenance personnel handle faults safely and reduce accident risks; through the intelligent alarm system, maintenance resources can be allocated more reasonably, and the most urgent and most influential faults can be handled first; using technologies such as augmented reality and big data analysis, the efficiency of fault location and repair can be improved, and maintenance costs can be reduced; through continuous data analysis and optimization, the system can better adapt to changing grid conditions and improve overall resilience and stability.

[0084] Further, in some embodiments, step S1 “classifying hidden faults in the distribution network based on actual engineering data of the distribution network to obtain classification results” may specifically include:

[0085] S11. Obtain actual engineering data of the distribution network and perform data preprocessing;

[0086] S12. clustering the preprocessed distribution network actual project data using a clustering mining algorithm to obtain the corresponding hidden fault data;

[0087] S13. Classify the hidden fault data according to the waveform features corresponding to the hidden fault data to obtain corresponding classification results.

[0088] Specifically, for step S1, the actual engineering data of the distribution network is obtained, and data preprocessing is performed to ensure the quality and availability of the data. The preprocessing includes steps such as denoising, normalization, and missing value processing. The clustering mining algorithm is used to cluster the preprocessed actual engineering data of the distribution network to obtain the corresponding hidden fault data. Clustering algorithms include K-means, hierarchical clustering, DBSCAN, etc. According to the waveform characteristics corresponding to the hidden fault data, the hidden fault data is classified to obtain the corresponding classification results.

[0089] In order to improve the accuracy and efficiency of fault classification, this embodiment also uses machine learning algorithms, such as support vector machines (SVM) or neural networks, to perform more detailed classification of fault data; combines multiple types of data (such as current, voltage, temperature, etc.) for comprehensive analysis to improve the accuracy of fault detection; implements real-time data stream processing technology to analyze and classify data immediately when it is generated, thereby improving response speed; develops an adaptive clustering algorithm that can dynamically adjust the clustering strategy according to the characteristics of the data to adapt to different fault modes; and creates interactive visualization tools to help engineers intuitively understand the clustering results and fault classification, thereby performing more accurate fault analysis.

[0090] This embodiment can improve the accuracy of fault classification and reduce misjudgments and missed judgments by using advanced data analysis technology and multimodal data fusion; implement real-time data stream processing technology to quickly respond to faults in the power grid and improve the response speed of the system; the adaptive clustering algorithm can improve the efficiency of data processing, reduce manual intervention, and reduce maintenance costs; through visualization tools, engineers can understand fault data more intuitively and make more accurate decisions; the adaptive clustering algorithm enables the system to adapt to different fault modes and power grid conditions and improve the robustness of the system.

[0091] Further, in some embodiments, the “classifying the hidden fault data to obtain corresponding classification results” in step S13 may specifically include:

[0092] Define the fault types corresponding to hidden faults, including tree barrier faults, arrester breakdown faults and small animal bridging faults. Tree barrier faults include nonlinear permanent grounding faults and instantaneous grounding faults.

[0093] The hidden data is classified based on the fault type to obtain the corresponding classification results.

[0094] Furthermore, in some embodiments, the fault types corresponding to the hidden faults are defined, and the fault types include tree barrier faults, lightning arrester breakdown faults, and small animal bridging faults. The tree barrier type includes nonlinear permanent grounding faults and instantaneous grounding faults, including:

[0095] The fault caused by a tree branch falling on the busbar is defined as a nonlinear permanent grounding fault;

[0096] The fault caused by tree branches hanging on the wire is defined as an instantaneous ground fault;

[0097] The lightning arrester failure caused by meteorological conditions is defined as the lightning arrester breakdown failure;

[0098] Faults caused by small animal jumper circuits are defined as small animal jumper faults.

[0099] Specifically, for step S13, according to the common hidden faults in the actual engineering conditions of the distribution network, the fault types are divided into three situations: tree obstacles, lightning arrester breakdown, and small animal bridging, so as to achieve adaptive recording of most hidden faults encountered in engineering practice.

[0100] Among them, the definition of tree branch falling on busbar is that under nonlinear permanent grounding fault, a relatively stable grounding loop is formed between the distribution line and the grounded object, accompanied by continuous arcing, the arc discharge point is concentrated in a certain part, and the arcing-arcing-reignition process occurs periodically; the definition of tree branch hanging on the line is that the grounding fault caused by intermittent tree branches hanging on the line shows the process of arc burning-extinguishing-reignition; the definition of small animal bridging is that small animals are connected to the weak insulation of the line, and the arc discharge can destroy the contact relationship between the small animals and the conductor, resulting in the grounding fault only appearing instantaneously, that is, the arc burning discharge only occurs once or twice, and then the line resumes normal operation; the definition of lightning arrester breakdown is that when the meteorological conditions change, such as lightning, storms or strong winds, the lightning arrester may be affected by the weather and broken down, resulting in a linear permanent grounding fault, a stable grounding loop is formed between the distribution line and the earth, there is no obvious arcing phenomenon or only an extremely weak arc appears.

[0101] This embodiment can improve the accuracy of fault classification by specifying the fault type definition and using intelligent image recognition technology; integrating environmental factors and developing fault prediction models can enhance the system's fault prediction ability and reduce the occurrence of unexpected faults; the application of machine learning models can quickly and automatically classify faults, improve response speed, and reduce power outage time; the automated fault management system can reduce manual intervention, maintenance costs, and human resource consumption.

[0102] Furthermore, in some embodiments, step S2 of "analyzing various types of hidden faults in the classification results to obtain energy distribution rules of various frequency bands corresponding to various types of hidden faults" may specifically include:

[0103] Based on the classification results, the fault waveform characteristics corresponding to the zero-sequence current in each type of hidden fault are analyzed;

[0104] Based on the fault waveform characteristics, the zero-sequence current in each type of hidden fault is analyzed spectrally to determine the energy distribution law of each frequency band corresponding to each type of hidden fault.

[0105] Specifically, for step S2, by analyzing the transient voltage and current recording data in the existing fault cases, it is found that the zero-sequence current waveform distortion characteristics can better characterize the characteristics of different hidden faults in the distribution network. Therefore, the energy distribution law of zero-sequence current in different frequency bands is used to distinguish different hidden faults occurring in the distribution network, and then the three common hidden faults in the distribution network are divided by spectrum analysis of the instantaneous value of zero-sequence current. For example, the recording data is subjected to wavelet packet transformation to extract quantities in different frequency bands, and the frequency domain quantities below 150Hz are divided into low-frequency quantities, 150-200Hz into medium-frequency quantities, and above 200Hz into high-frequency quantities. The energy proportions of low, medium, and high-frequency quantities in different fault scenarios are analyzed.

[0106] Among them, the energy proportion of the frequency band of 150-200Hz in the zero-sequence current under the grounding fault caused by tree branches falling on the busbar is the largest; the total energy proportion of the high-frequency band above 200Hz in the zero-sequence current on the line after the grounding fault caused by tree branches hanging on the wire is the largest; the energy proportion of the frequency band below 150Hz in the zero-sequence current under the arrester breakdown fault is the highest; although the "transient value" feature will appear in the zero-sequence current under the grounding fault caused by tree branches hanging on the wire and the grounding fault caused by small animals bridging, the number of occurrences is different to distinguish the grounding fault caused by tree branches hanging on the wire and the grounding fault caused by small animals bridging.

[0107] In actual field, even if a lightning arrester breakdown failure occurs without arcing, the corresponding zero-sequence current waveform is not necessarily a completely standard sine wave due to measurement errors and other reasons. In this scenario, the measured zero-sequence current contains a certain high-frequency component, which will increase the proportion of energy in the high-frequency band, resulting in the energy distribution characteristics of different frequency bands may not be able to distinguish between the slight distortion of the sine waveform caused by measurement errors and the flat shoulder distortion caused by stable arcing. In order to highlight the differences in the high-frequency components of zero-sequence current in different scenarios, the harmonic center of gravity is used to characterize them.

[0108] In a specific embodiment, according to different waveform characteristics, the periodic "shoulder distortion" of the zero-sequence current waveform is used as a characteristic of a permanent single-phase grounding fault with stable arcing in the distribution network; the "transient values" with extremely short duration that appear multiple times in the zero-sequence current waveform are used as a characteristic of an intermittent grounding fault with multi-frequency unstable arcing; the "transient value" that appears only once or twice in the zero-sequence current waveform is used as a characteristic of an instantaneous grounding fault in the line; the zero-sequence current waveform that basically presents a stable sine wave is used as a characteristic of a linear permanent single-phase grounding fault in the line. The recorded data is subjected to wavelet packet transformation to extract quantities in different frequency bands, and the frequency domain quantities below 150 Hz are divided into low-frequency quantities, 150 to 200 Hz into medium-frequency quantities, and above 200 Hz into high-frequency quantities using a multi-resolution analysis method. The energy proportion rules of the low, medium, and high frequency band quantities under different fault scenarios are analyzed. Figure 3 The zero-sequence current time domain diagram of the busbar with tree branches is analyzed. Figure 6 The energy proportion of zero-sequence current in different frequency bands under the busbar with fallen branches can be seen. Among the energy proportions of zero-sequence current in different frequency bands under the grounding fault caused by the busbar with fallen branches, the energy proportion of the frequency band of 150-200Hz is the largest. Figure 4 The zero-sequence current time domain diagram of the tree branch hanging line is analyzed Figure 7 The energy proportion of zero-sequence current in different frequency bands under the tree branches hanging on the line shows that the total energy proportion of high frequency bands above 200Hz in the zero-sequence current on the line after the grounding fault caused by the tree branches hanging on the line is the largest; Figure 5 The arrester breakdown zero-sequence current time domain diagram is analyzed to obtain Figure 8 The energy proportion of zero-sequence current in different frequency bands under lightning arrester breakdown shows that the energy proportion of zero-sequence current in different frequency bands under lightning arrester breakdown fault is the highest in the frequency band below 150Hz; although the "transient value" feature will appear in the zero-sequence current under the grounding fault caused by tree branches hanging on the wire and the grounding fault caused by small animals bridging, the number of occurrences is different to distinguish the grounding fault caused by tree branches hanging on the wire and the grounding fault caused by small animals bridging. In the actual field, even if a lightning arrester breakdown fault without arcing occurs, the corresponding zero-sequence current waveform is not necessarily a completely standard sine wave due to measurement errors and other reasons. In this scenario, the measured zero-sequence current contains a certain high-frequency component, which will increase the energy proportion of the high-frequency band, resulting in the energy distribution characteristics of different frequency bands may not be able to distinguish the slight distortion of the sine waveform caused by measurement errors and the flat shoulder distortion caused by stable arcing. In order to highlight the differences in the high-frequency components of zero-sequence current in different scenarios, the harmonic center of gravity is used to characterize it. The expression of the harmonic center of gravity in the zero-sequence current is shown in the formula

[0109]

[0110] In the formula: K is the harmonic gravity center; j represents the harmonic order; N is the total number of harmonics; I represents the amplitude of different frequency components. It can be seen from the formula that the harmonic gravity center K is calculated by multiplying the amplitude of each harmonic component by the harmonic order and then accumulating and summing them. It can reflect the difference of different high-frequency harmonic quantities in the zero-sequence current under fault. The higher the frequency, the greater the weight of the harmonic gravity center K. The variation law of the harmonic gravity center of nonlinear permanent grounding fault under different fault scenarios, its value ranges from 1 to 4; in contrast, the harmonic gravity center value of linear permanent grounding fault under different fault scenarios varies between 0 and 0.7. This shows that there are obvious differences in the corresponding harmonic gravity center characteristic quantities after the occurrence of nonlinear permanent grounding fault and linear permanent grounding fault.

[0111] This embodiment uses spectrum analysis and machine learning technology to more accurately identify and classify hidden faults in the distribution network; the adaptive threshold setting algorithm enables the system to dynamically adjust according to the power grid status, thereby improving the flexibility and response speed of the system; advanced signal processing technology can reduce misjudgment and ensure the reliability of fault analysis results; the real-time data analysis platform can quickly respond to faults in the power grid, reduce power outage time, and improve power supply reliability; accurate fault analysis helps to more reasonably allocate maintenance resources and give priority to the most urgent and most influential faults.

[0112] Further, in some embodiments, step S3 "constructing adaptive recording rules based on the energy distribution laws of each frequency band corresponding to various types of hidden faults" may specifically include: collecting zero-sequence current waveform data in the distribution network, including data under normal operation and various fault conditions. De-noising and normalizing the collected data to improve data quality. Performing spectrum analysis on the zero-sequence current waveform to extract energy distribution characteristics of different frequency bands. Selecting the frequency band energy distribution characteristics most relevant to the fault type, such as the energy proportion of a specific frequency band, the center of gravity of harmonics, etc. Using machine learning algorithms (such as support vector machines, random forests, neural networks) to classify different fault modes. Based on the classification results, generating energy distribution laws corresponding to each fault mode. Define adaptive recording rules, which start and adjust recording strategies based on the energy distribution characteristics of the fault mode. Set energy distribution thresholds for each fault mode, and trigger recording when real-time data exceeds these thresholds. Real-time monitoring of zero-sequence current waveforms and energy distribution laws in the distribution network. Dynamically adjust recording parameters such as sampling frequency and recording duration based on the matching of real-time data with preset rules. The effectiveness of the adaptive recording rules is verified through historical data and simulated faults. The recording rules are optimized and adjusted according to the verification results to improve the accuracy and adaptability of the rules.

[0113] In addition, deep learning techniques, such as convolutional neural networks (CNN) or recurrent neural networks (RNN), can be used to identify complex fault modes and energy distribution patterns. Edge computing technology can be used to achieve real-time data processing and rule application at the edge nodes of the distribution network to reduce latency.

[0114] This embodiment constructs an effective adaptive recording rule, which can dynamically adjust the recording strategy according to the actual operating status of the distribution network, thereby improving the accuracy and response speed of fault detection.

[0115] Further, in some embodiments, step S4 "adaptively recording the target line based on the adaptive recording rule to obtain the recording result" may specifically include:

[0116] Real-time measurement of the current zero-sequence current waveform and current energy distribution law of the target line;

[0117] Based on the current zero-sequence current waveform and the current energy distribution law, matching is performed with the preset fault judgment rule to obtain a matching result;

[0118] After the matching is determined to be successful based on the matching result, adaptive waveform recording is performed on the target line based on the adaptive waveform recording rule to collect zero-sequence current waveform data of the target line;

[0119] Based on the collected zero-sequence current waveform data, the recording result is generated.

[0120] Specifically, for step S4, based on the energy distribution law of zero-sequence current of three common hidden faults in the distribution network in different frequency bands as a criterion, the adaptive recording function of the distribution automation terminal is started to collect the zero-sequence current waveform of the fault line.

[0121] First, the current zero-sequence current waveform and current energy distribution law of the target line are measured in real time. This step is the basis of adaptive recording and ensures the real-time and accuracy of the recording data. Then, based on the real-time measured zero-sequence current waveform and energy distribution law, it is matched with the preset fault judgment rules to obtain the matching result. This step is the key link in determining whether a fault has occurred. After the match is successful, the target line is adaptively recorded based on the adaptive recording rules to collect the zero-sequence current waveform data of the target line. Finally, based on the collected zero-sequence current waveform data, the recording results are generated to provide a basis for subsequent fault analysis and processing.

[0122] In order to improve the efficiency and accuracy of adaptive recording, this embodiment can also use intelligent algorithms, such as genetic algorithms or particle swarm optimization, to optimize adaptive recording rules and improve matching accuracy and efficiency; use big data analysis technology to analyze historical recording data to discover potential fault modes and patterns, and further optimize recording rules; apply edge computing technology to disperse data processing and analysis tasks to the edge of the network to reduce latency and improve response speed; use machine learning models, such as deep neural networks, to perform feature extraction and pattern recognition on recording data to improve the accuracy of fault judgment; develop an adaptive threshold adjustment mechanism to dynamically adjust the threshold of fault judgment rules according to the real-time status of the power grid and historical data; build a visual monitoring platform to display recording data and fault judgment results in real time, so as to facilitate operators to quickly understand and respond.

[0123] This embodiment can improve the accuracy of fault detection and reduce misjudgments and missed judgments through the application of intelligent algorithm optimization and machine learning models; the improvement of edge computing technology and real-time data processing capabilities can speed up fault response and reduce power outage time; the automated fault detection and recording system can reduce manual intervention, reduce maintenance costs and human resource consumption; fast and accurate fault handling can reduce users' power outage time and improve user satisfaction and service quality; the visual monitoring platform provides operators with intuitive fault information and improves decision-making support capabilities.

[0124] In a specific embodiment, this embodiment also provides a specific implementation method of an adaptive recording method for fault identification, such as Fig. 9 As shown, the specific process is as follows:

[0125] 101. According to the common hidden faults in the actual engineering conditions of the distribution network, the fault types are divided into three types: tree obstacles, lightning arrester breakdown and small animal bridging, so as to realize the adaptive recording of most hidden faults encountered in engineering practice;

[0126] 102. The energy distribution law of zero-sequence current in different frequency bands is used to distinguish different hidden faults in the power grid, and then the three common hidden faults in the power grid are divided by spectrum analysis of the instantaneous value of zero-sequence current;

[0127] 103. Based on the energy distribution law of zero-sequence current in different frequency bands of three common hidden faults in distribution network, the adaptive waveform recording of distribution automation terminal is started to record the zero-sequence current waveform of fault line during fault.

[0128] This embodiment provides an adaptive recording method suitable for the identification of hidden faults in distribution automation terminals. First, the commonly occurring hidden faults in the distribution network are classified, and the fault waveform characteristics of zero-sequence current under different fault types are summarized and analyzed; further, the zero-sequence current waveform characteristics under different fault types are mathematically described using different frequency band energy distribution characteristics and harmonic center of gravity, so as to infer the start criterion of adaptive hidden fault recording based on these waveform characteristics, so as to realize adaptive recording of different hidden faults in the distribution network. This embodiment effectively overcomes the omission or misjudgment of hidden faults in traditional recording technology, and can perform adaptive recording according to different hidden fault characteristics, making up for the deficiency of traditional recording capabilities that cannot identify common hidden faults, and solving the problem that the fault recording cannot be started correctly in the distribution network hidden fault recording because the fault signal of the hidden fault is weak and it is difficult to capture the fault information.

[0129] In summary, this embodiment provides an adaptive recording method for fault identification, which classifies hidden faults in the distribution network based on actual engineering data of the distribution network to obtain classification results; analyzes various types of hidden faults in the classification results to obtain energy distribution laws of various frequency bands corresponding to various types of hidden faults; constructs adaptive recording rules based on energy distribution laws of various frequency bands corresponding to various types of hidden faults; and adaptively records the target line based on the adaptive recording rules to obtain recording results. The adaptive recording scheme for fault identification provided in this embodiment can more accurately identify hidden faults in the distribution network by analyzing zero-sequence current waveform characteristics and frequency band energy distribution laws, uses fault waveform characteristics and energy distribution laws as start-up criteria, realizes the automation of adaptive recording, reduces dependence on manual intervention, reduces misjudgment and missed judgment of hidden faults through precise feature analysis and criterion setting, improves the operation reliability of the distribution network, and helps reduce the impact of faults on the distribution network by quickly and accurately identifying and responding to hidden faults, and improves the continuity and reliability of power supply.

[0130] In order to facilitate better implementation of an adaptive recording method for fault identification in an embodiment of the present application, an adaptive recording device for fault identification is also provided in an embodiment of the present application. The meanings of the terms are the same as those in the adaptive recording method for fault identification described above, and the specific implementation details can refer to the description in the method embodiment.

[0131] See also Fig.10 , Fig.10 A schematic diagram of the structure of an adaptive recording device for fault identification provided in an embodiment of the present application, wherein the adaptive recording device for fault identification may specifically include a classification module 201, an analysis module 202, a construction module 203 and a recording module 204, which may be specifically as follows:

[0132] A classification module 201 is used to classify hidden faults in the distribution network based on actual engineering data of the distribution network to obtain classification results;

[0133] The analysis module 202 is used to analyze various types of hidden faults in the classification results to obtain energy distribution rules of various frequency bands corresponding to various types of hidden faults;

[0134] A construction module 203 is used to construct an adaptive recording rule based on the energy distribution law of each frequency band corresponding to various types of hidden faults;

[0135] The wave recording module 204 is used to perform adaptive wave recording on the target line based on the adaptive wave recording rule to obtain the wave recording result.

[0136] Furthermore, in some embodiments, it also includes:

[0137] A fault module is used to perform fault analysis on the target fault line based on the wave recording result to obtain the fault analysis result;

[0138] The alarm module is used to generate and push corresponding alarm information based on the fault analysis results.

[0139] Furthermore, in some embodiments, the classification module 201 may specifically include:

[0140] An acquisition unit, used to acquire actual engineering data of the distribution network and perform data preprocessing;

[0141] The clustering unit is used to cluster the data of the actual distribution network project after preprocessing by using a clustering mining algorithm to obtain the corresponding hidden fault data;

[0142] The classification unit is used to classify the hidden fault data according to the waveform characteristics corresponding to the hidden fault data to obtain corresponding classification results.

[0143] Furthermore, in some embodiments, the classification unit is specifically used to: define the fault type corresponding to the hidden fault, the fault types including tree barrier type faults, lightning arrester breakdown type faults and small animal bridging type faults, the tree barrier type includes nonlinear permanent grounding faults and instantaneous grounding faults; classify the hidden data based on the fault type to obtain the corresponding classification results.

[0144] Furthermore, in some embodiments, fault types corresponding to hidden faults are defined, and the fault types include tree barrier faults, lightning arrester breakdown faults and small animal bridging faults. The tree barrier type includes nonlinear permanent grounding faults and instantaneous grounding faults, including: defining the fault caused by tree branches falling on the bus as a nonlinear permanent grounding fault; defining the fault caused by tree branches hanging on the line as an instantaneous grounding fault; defining the fault of the lightning arrester caused by the influence of meteorological conditions as a lightning arrester breakdown fault; defining the fault caused by small animals bridging the line as a small animal bridging fault.

[0145] Furthermore, in some embodiments, the analysis module 202 may specifically include:

[0146] A waveform feature unit, used to analyze the fault waveform feature corresponding to the zero-sequence current in each type of hidden fault based on the classification result;

[0147] The spectrum analysis unit is used to perform spectrum analysis on the zero-sequence current in each type of hidden fault based on the fault waveform characteristics, and determine the energy distribution law of each frequency band corresponding to each type of hidden fault.

[0148] Furthermore, in some embodiments, the wave recording module 204 may specifically include:

[0149] A measuring unit, used for measuring the current zero-sequence current waveform and current energy distribution law of the target line in real time;

[0150] A matching unit is used to match the current zero-sequence current waveform and the current energy distribution law with a preset fault judgment rule to obtain a matching result;

[0151] A collection unit, for performing adaptive wave recording on a target line based on an adaptive wave recording rule after determining that the match is successful based on the matching result, and collecting zero-sequence current waveform data of the target line;

[0152] The waveform recording unit is used to generate waveform recording results based on the collected zero-sequence current waveform data.

[0153] In summary, the adaptive recording device for fault identification provided in this embodiment classifies the hidden faults in the distribution network based on the actual engineering data of the distribution network through the classification module 201 to obtain the classification results; analyzes the various types of hidden faults in the classification results through the analysis module 202 to obtain the energy distribution laws of each frequency band corresponding to the various types of hidden faults; constructs adaptive recording rules based on the energy distribution laws of each frequency band corresponding to the various types of hidden faults through the construction module 203; and adaptively records the target line based on the adaptive recording rules through the recording module 204 to obtain the recording results. It can be seen that the adaptive recording device for fault identification provided in this embodiment can more accurately identify hidden faults in the distribution network by analyzing the zero-sequence current waveform characteristics and the frequency band energy distribution law, and use the fault waveform characteristics and energy distribution law as the starting criteria to realize the automation of adaptive recording and reduce the dependence on manual intervention. Through precise feature analysis and criterion setting, it can reduce the misjudgment and omission of hidden faults, improve the operational reliability of the distribution network, and quickly and accurately identify and respond to hidden faults, which helps to reduce the impact of faults on the distribution network and improve the continuity and reliability of power supply.

[0154] In addition, the present application also provides an electronic device, such as Fig.11 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application. Specifically, the electronic device may include a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, an input unit 304 and other components. Those skilled in the art can understand that Fig.11 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0155] The processor 301 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 302, and calling data stored in the memory 302, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0156] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and the adaptive wave recording method for fault identification by running the software programs and modules stored in the memory 302. The memory 302 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device, etc. In addition, the memory 302 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 can also include a memory controller to provide the processor 301 with access to the memory 302.

[0157] The electronic device also includes a power supply 303 for supplying power to each component. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions. The power supply 303 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0158] The electronic device may further include an input unit 304, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0159] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302, thereby realizing various functions, as follows:

[0160] Based on the actual engineering data of the distribution network, the hidden faults in the distribution network are classified to obtain the classification results; the various types of hidden faults in the classification results are analyzed to obtain the energy distribution laws of each frequency band corresponding to the various types of hidden faults; based on the energy distribution laws of each frequency band corresponding to the various types of hidden faults, adaptive recording rules are constructed; based on the adaptive recording rules, the target line is adaptively recorded to obtain the recording results.

[0161] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0162] The embodiments of the present application can more accurately identify hidden faults in the distribution network by analyzing the zero-sequence current waveform characteristics and the energy distribution law of the frequency band, and use the fault waveform characteristics and energy distribution law as the starting criteria to realize the automation of adaptive recording and reduce the dependence on manual intervention. Through precise feature analysis and criterion setting, the misjudgment and omission of hidden faults are reduced, and the operational reliability of the distribution network is improved. By quickly and accurately identifying and responding to hidden faults, it helps to reduce the impact of faults on the distribution network and improve the continuity and reliability of power supply.

[0163] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0164] To this end, an embodiment of the present application provides a storage medium in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any one of the adaptive recording methods for fault identification provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0165] Based on the actual engineering data of the distribution network, the hidden faults in the distribution network are classified to obtain the classification results; the various types of hidden faults in the classification results are analyzed to obtain the energy distribution laws of each frequency band corresponding to the various types of hidden faults; based on the energy distribution laws of each frequency band corresponding to the various types of hidden faults, adaptive recording rules are constructed; based on the adaptive recording rules, the target line is adaptively recorded to obtain the recording results.

[0166] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0167] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. Since the instructions stored in the storage medium can execute the steps in any one of the adaptive wave recording methods for fault identification provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the adaptive wave recording methods for fault identification provided in the embodiments of the present application can be achieved, as detailed in the previous embodiments, which will not be repeated here.

[0168] The above is a detailed introduction to an adaptive recording method, device, electronic device and storage medium for fault identification provided in an embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An adaptive recording method for fault identification, characterized in that: The steps include: Based on actual engineering data of the distribution network, the hidden faults in the distribution network are classified to obtain classification results; Analyze various types of hidden faults in the classification results to obtain energy distribution rules of various frequency bands corresponding to various types of hidden faults; Based on the energy distribution law of each frequency band corresponding to the various types of hidden faults, an adaptive recording rule is constructed; Based on the adaptive recording rule, the target line is adaptively recorded to obtain a recording result.

2. The adaptive recording method for fault identification according to claim 1, characterized in that: Also includes: Performing fault analysis on the target fault line based on the wave recording result to obtain a fault analysis result; Based on the fault analysis result, corresponding alarm information is generated and pushed.

3. The adaptive recording method for fault identification according to claim 1, characterized in that: The method of classifying the hidden faults in the distribution network based on the actual engineering data of the distribution network to obtain the classification results includes: Acquiring actual engineering data of the distribution network and performing data preprocessing; The cluster mining algorithm is used to cluster the pre-processed data of the actual distribution network project to obtain the corresponding hidden fault data; According to the waveform features corresponding to the hidden fault data, the hidden fault data is classified to obtain corresponding classification results.

4. The adaptive recording method for fault identification according to claim 3, characterized in that: The classifying the hidden fault data to obtain corresponding classification results includes: Define the fault type corresponding to the hidden fault, the fault type includes tree barrier fault, lightning arrester breakdown fault and small animal bridging fault, the tree barrier type includes nonlinear permanent grounding fault and instantaneous grounding fault; The hidden data is classified based on the fault type to obtain a corresponding classification result.

5. The adaptive recording method for fault identification according to claim 4, characterized in that: The definition of the fault type corresponding to the hidden fault includes tree barrier faults, lightning arrester breakdown faults and small animal bridging faults. The tree barrier type includes nonlinear permanent grounding faults and instantaneous grounding faults, including: The fault caused by a tree branch falling on the busbar is defined as a nonlinear permanent grounding fault; The fault caused by tree branches hanging on the wire is defined as an instantaneous ground fault; The lightning arrester failure caused by meteorological conditions is defined as the lightning arrester breakdown failure; Faults caused by small animal jumper circuits are defined as small animal jumper faults.

6. The adaptive recording method for fault identification according to claim 1, characterized in that: The various types of hidden faults in the classification results are analyzed to obtain energy distribution rules of various frequency bands corresponding to the various types of hidden faults, including: Based on the classification results, analyzing the fault waveform characteristics corresponding to the zero-sequence current in each type of hidden fault; Based on the fault waveform characteristics, a spectrum analysis is performed on the zero-sequence current in each type of hidden fault to determine the energy distribution law of each frequency band corresponding to each type of hidden fault.

7. The adaptive recording method for fault identification according to claim 1, characterized in that: The step of adaptively recording the target line based on the adaptive recording rule to obtain a recording result includes: Real-time measurement of the current zero-sequence current waveform and current energy distribution law of the target line; Based on the current zero-sequence current waveform and the current energy distribution law, matching is performed with a preset fault judgment rule to obtain a matching result; After determining that the match is successful based on the matching result, adaptively recording the target line based on the adaptive recording rule, and collecting zero-sequence current waveform data of the target line; Based on the collected zero-sequence current waveform data, a waveform recording result is generated.

8. An adaptive recording device for fault identification, characterized in that: include: A classification module, used for classifying hidden faults in the distribution network based on actual engineering data of the distribution network to obtain classification results; An analysis module, used to analyze various types of hidden faults in the classification results to obtain energy distribution rules of various frequency bands corresponding to various types of hidden faults; A construction module, used to construct an adaptive recording rule based on the energy distribution law of each frequency band corresponding to the various types of hidden faults; The wave recording module is used to perform adaptive wave recording on the target line based on the adaptive wave recording rule to obtain the wave recording result.

9. An electronic device, characterized in that: include: A memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the adaptive recording method for fault identification as described in any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the adaptive waveform recording method for fault identification as claimed in any one of claims 1 to 7.

Images