Electric leakage identification system and identification method for medium and low voltage transformer area

Abstract

The invention belongs to the field of electric leakage identification, and particularly relates to a medium and low voltage transformer area electric leakage identification system, which comprises a data acquisition module, a data preprocessing module, a system control module, a fault sensing module, a knowledge graph construction module, an event processing module, a grading early warning module and a system optimization module. The system acquires electrical quantity, topology and power failure report data in real time through the data acquisition module, after the data are cleaned and calibrated by the preprocessing module, a power failure event is quickly judged by combining the fault sensing module with a topological relation, and then wide-area association between equipment and the event is constructed by utilizing a knowledge graph, so that the accurate positioning of a fault position from a transformer area to a cell unit is realized. The event processing module merges and integrates massive power failure data and reduces repeated alarms, and the first-aid repair support module is linked with a grading early warning mechanism and pushes important user early warning and first-aid repair information in a targeted manner, so that the fault positioning time is greatly shortened, the field disposal efficiency is improved, and the whole-process closed-loop management and control of low-voltage faults from sensing to disposal is ensured.

Description

Technical Field

[0001] This invention relates to the field of leakage current identification technology, and in particular to a leakage current identification system and method for medium and low voltage distribution areas. Background Technology

[0002] The low- and medium-voltage transformer area leakage current identification system is built by constructing an intelligent technology system to achieve accurate low-voltage fault determination within seconds, automatic identification of the scope of impact, and tiered early warning of frequent power outages. This improves the efficiency of fault location and handling, while accurately identifying leakage current characteristics, supporting targeted scheduling of emergency repair resources, effectively reducing complaints about frequent power outages, and comprehensively improving the quality of power supply services and the level of intelligent management of the power grid.

[0003] Existing technologies for identifying leakage current in medium and low voltage distribution areas have significant shortcomings: massive amounts of power outage data lack efficient filtering mechanisms, making it difficult to eliminate invalid information by combining topological relationships, resulting in low fault location efficiency; severe interference from faulty data and weak topological correlation analysis capabilities make it impossible to accurately determine power outage events; a lack of standardized merging mechanisms for power outage events leads to prominent issues with duplicate alarms; frequent power outage management relies on manual analysis and cannot automatically generate tiered warnings; power outage warnings for important users lack targeted delivery, resulting in inaccurate information transmission during multi-disciplinary collaborative repairs. Furthermore, the ability to extract specific leakage current features is weak, and knowledge graph construction and data fusion are insufficient, making it difficult to support integrated fault assessment. Therefore, it is necessary to design a leakage current identification system and method for medium and low voltage distribution areas. Summary of the Invention

[0004] The purpose of this invention is to provide a leakage current identification system and method for medium and low voltage distribution areas in order to solve the above-mentioned problems, thereby solving the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, this invention provides a low-voltage distribution area leakage current identification system, comprising a data acquisition module, a data preprocessing module, a system control module, a fault detection module, a knowledge graph construction module, an event processing module, a hierarchical early warning module, a system optimization module, a data management module, and a data center module. The data acquisition module and the data preprocessing module are connected; the data preprocessing module is connected to the system control module; the system control module is connected to the fault detection module; the system control module is connected to the knowledge graph construction module; the system control module is connected to the event processing module; the system control module is connected to the hierarchical early warning module; the system control module is connected to the system optimization module; the system control module is connected to the data management module; and the data management module is connected to the data center module.

[0006] Preferably, the data acquisition module includes a real-time measurement module, a power outage reporting module, a topology data module, and a historical operation data module. The real-time measurement module is connected to the power outage reporting module, the power outage reporting module is connected to the topology data module, and the topology data module is connected to the historical operation data module. The real-time measurement module is used to collect real-time electrical quantity data such as voltage and current in the distribution area, providing real-time basic data support for fault analysis; the power outage reporting module is used to collect power outage information reported by users or equipment, realizing rapid perception and reporting of power outage events; the topology data module is used to obtain the power grid topology data of the distribution area, providing network connection relationship basis for fault location; the historical operation data module is used to collect historical power outage and equipment operation data for fault mode analysis and historical pattern mining.

[0007] Preferably, the data preprocessing module includes a cleaning and filtering module, a timescale calibration module, an anomaly correction module, and a measurement optimization module. The cleaning and filtering module is connected to the timescale calibration module, the timescale calibration module is connected to the anomaly correction module, and the anomaly correction module is connected to the measurement optimization module. The cleaning and filtering module is used to remove noise and invalid data, improve data quality, and ensure the accuracy of subsequent analysis; the time stamp calibration module is used to calibrate the consistency of data timestamps to avoid fault analysis errors caused by time deviations; the anomaly correction module is used to correct abnormal information in the topology ledger to ensure the correctness of power grid structure data; and the metering optimization module is used to optimize meter data to improve the reliability and usability of metering data.

[0008] Preferably, the fault perception module includes a power outage determination module, a relationship analysis module, a bad pixel shielding module, and a feature extraction module. The power outage determination module and the relationship analysis module are connected, the relationship analysis module and the bad pixel shielding module are connected, and the bad pixel shielding module and the feature extraction module are connected. The power outage determination module is used to determine whether a power outage event has occurred based on measurement data, thereby achieving preliminary identification of power outage faults; the relationship analysis module is used to identify suspected power outage areas by combining topology structure, thereby narrowing down the scope of fault investigation; the bad point shielding module is used to accurately shield bad point data, thereby avoiding interference from invalid data in fault assessment; and the feature extraction module is used to extract leakage current features such as zero-sequence current from electrical quantities, thereby achieving specialized identification of leakage faults.

[0009] Preferably, the knowledge graph construction module includes a topological knowledge module, an association establishment module, a graph optimization module, and a model splicing module. The topological knowledge module and the association establishment module are connected, the association establishment module and the graph optimization module are connected, and the graph optimization module and the model splicing module are connected. The topology knowledge module is used to construct an integrated knowledge system for medium and low voltage distribution networks based on topology data, forming a structured topology cognition; the association establishment module is used to establish wide-area associations between equipment, topology and power outage events, realizing multi-dimensional data linkage analysis; the graph optimization module is used to optimize the structure and content of the knowledge graph, improving the graph's support capability for fault analysis; the model splicing module is used to splice and merge different data models to form a complete fault analysis data model system.

[0010] Preferably, the event-driven processing module includes a power outage merging module, a merging module, an address matching module, and a cell identification module. The power outage merging module and the merging module are connected, the merging module and the address matching module are connected, and the address matching module and the cell identification module are connected. The power outage merging module is used to merge and consolidate massive amounts of power outage data to achieve event-based management and reduce duplicate alarms; the merging module is used to establish a fault analysis event-based merging model to improve the intelligence level of power outage event handling; the address matching module is used to match user address information to achieve accurate location and description of fault locations; the community identification module is used to identify specific communities and unit numbers to provide accurate location guidance for on-site repairs.

[0011] Preferably, the hierarchical early warning module includes a user early warning module, a frequent early warning module, a hierarchical and layered module, and an emergency repair support module. The user early warning module and the frequent early warning module are connected, the frequent early warning module and the hierarchical and layered module are connected, and the hierarchical and layered module and the emergency repair support module are connected. The user early warning module is used to push early warning information to key users affected by the power outage, thereby improving emergency response efficiency; the frequent early warning module is used to generate frequent power outage early warnings based on the power outage information pool, which helps to reduce complaint work orders; the hierarchical module is used to classify and hierarchically warn power outage events, thereby achieving differentiated management of faults; and the emergency repair support module is used to provide emergency repair personnel with information such as the location and scope of the fault, thereby improving emergency repair efficiency.

[0012] Preferably, the system optimization module includes a feeder optimization module, a hierarchical protection module, a signal processing module, and an abnormal operation module. The feeder optimization module and the hierarchical protection module are connected, the hierarchical protection module and the signal processing module are connected, and the signal processing module and the abnormal operation module are connected. The feeder optimization module is used to optimize feeder automation functions and improve fault isolation and recovery efficiency; the hierarchical protection module is used to optimize hierarchical protection configuration and improve the accuracy and reliability of fault protection; the signal processing module is used to optimize signal processing in the station and feeders and improve signal transmission and identification accuracy; the abnormal operation module is used to handle abnormal power grid operation modes and ensure the stability and safety of power grid operation.

[0013] Preferably, the data management module includes an information pool management module, a historical data module, a data security module, and an interface management module. The information pool management module is connected to the historical data module, the historical data module is connected to the data security module, and the data security module is connected to the interface management module. The information pool management module manages the power outage information pool data, providing unified data storage and retrieval for fault analysis; the historical data module stores historical operating data, providing data support for fault analysis and trend prediction; the data security module ensures system data security and prevents data leakage and illegal tampering; and the interface management module manages the system's external interfaces, enabling data interaction and sharing with other systems.

[0014] A method for identifying leakage current in a medium- and low-voltage distribution area system, comprising the following steps: Step S101: Through the real-time measurement, power outage reporting, topology relationship and historical operation data acquisition modules, obtain the electrical quantity of the transformer area, power outage information, power grid topology and historical operation data; after data cleaning and filtering, time stamp synchronization calibration, ledger anomaly correction and metering data optimization, invalid data is eliminated, timestamps are calibrated and topology anomalies are corrected, providing an accurate data foundation for subsequent analysis; Step S102: Based on the preprocessed data, the power outage event determination module is used to identify the power outage event, the topology relationship analysis module is used to locate the suspected power outage area, the bad point data shielding module is used to eliminate interference data, and at the same time, leakage current features such as zero-sequence current are extracted from electrical quantities to achieve preliminary location of power outage fault and specific identification of leakage current features. Step S103: Based on topology data, construct integrated topology knowledge of medium and low voltage distribution networks, establish a wide-area correlation between equipment, topology and power outage events, improve the accuracy of the knowledge graph through the knowledge graph optimization module, and splice and merge different data models to form a structured and correlated fault analysis knowledge system; Step S104: Use the power outage event merging module to merge massive amounts of power outage data, and combine it with the event-based merging model to achieve power outage event-based management; through the address information matching and community unit identification module, accurately locate the community, unit and household number corresponding to the fault, and provide precise location guidance for on-site emergency repairs. Step S105: For important users and historically sensitive users affected by the power outage, push information through the important user early warning module; generate frequent power outage graded early warning events based on the power outage information pool, and combine the graded and layered early warning mechanism to realize differentiated fault management, while providing support information such as the scope of fault impact to the emergency repair personnel; Step S106: Regularly optimize the performance of modules such as feeder automation and hierarchical protection, and handle issues such as station signals and abnormal operations; through power outage information pool management, historical data storage, data security assurance, and interface management, achieve unified data storage, secure interaction, and sharing to support the continuous and stable operation of the system. Compared with related technologies, the leakage current identification system for medium and low voltage distribution areas provided by this invention has the following advantages: This invention provides a low- and medium-voltage transformer substation leakage current identification system. The system acquires electrical quantities, topology data, and power outage reports in real time through a data acquisition module. After cleaning and calibration by a preprocessing module, the system quickly determines power outage events based on topological relationships using a fault perception module. Furthermore, a knowledge graph is used to construct a wide-area association between devices and events, achieving precise fault location from the transformer substation to the unit level within the community. An event-based processing module merges and integrates massive amounts of power outage data, reducing duplicate alarms. The emergency repair support module, in conjunction with a tiered early warning mechanism, targets and pushes early warnings and repair information to important users, significantly shortening fault location time, improving on-site handling efficiency, and ensuring closed-loop management of the entire low-voltage fault process from perception to handling.

[0015] This invention provides a leakage current identification system for medium and low voltage distribution areas. A leakage current feature extraction module specifically identifies leakage current characteristics such as zero-sequence current. Combined with a frequent power outage early warning module, historical data is mined and analyzed to generate tiered and layered early warning events, effectively reducing frequent power outage complaint orders. The system optimization module continuously improves functions such as feeder automation and tiered protection, and, combined with anomaly handling and signal optimization, enhances grid operation stability. The data management module ensures data security and sharing, supports multi-disciplinary collaboration, and achieves intelligent management across the entire chain from fault detection and early warning to operation and maintenance optimization, significantly improving power supply reliability and user service satisfaction. Attached Figure Description

[0016] Figure 1 This is a system schematic diagram of the present invention; Figure 2 For the present invention Figure 1 Schematic diagram of the data acquisition module; Figure 3 For the present invention Figure 1 Schematic diagram of the data preprocessing module; Figure 4 For the present invention Figure 1 Schematic diagram of the fault perception module; Figure 5 For the present invention Figure 1 Schematic diagram of the knowledge graph construction module; Figure 6 For the present invention Figure 1 Schematic diagram of the event processing module; Figure 7 For the present invention Figure 1Schematic diagram of the hierarchical early warning module; Figure 8 For the present invention Figure 1 System optimization module schematic diagram; Figure 9 For the present invention Figure 1 Data management module schematic diagram; Figure 10 This is a flowchart of the process of the present invention.

[0017] Numbering on the map: 1. Data Acquisition Module; 2. Data Preprocessing Module; 3. System Control Module; 4. Fault Detection Module; 5. Knowledge Graph Construction Module; 6. Event Processing Module; 7. Hierarchical Early Warning Module; 8. System Optimization Module; 9. Data Management Module; 10. Data Center Module; 11. Real-time Measurement Module; 12. Power Outage Reporting Module; 13. Topology Data Module; 14. Historical Operation Data Module; 21. Cleaning and Filtering Module; 22. Timescale Calibration Module; 23. Anomaly Correction Module; 24. Metering Optimization Module; 41. Power Outage Judgment Module; 42. Relationship Analysis Module; 43. Defect Detection Module; 4. Feature Extraction Module; 51. Topology Knowledge Module; 52. Association Establishment Module; 53. Graph Optimization Module; 54. Model Assembly Module; 61. Power Outage Merging Module; 62. Merging Module; 63. Address Matching Module; 64. Cell Identification Module; 71. User Early Warning Module; 72. Frequent Early Warning Module; 73. Hierarchical and Layered Module; 74. Emergency Repair Support Module; 81. Feeder Optimization Module; 82. Hierarchical Protection Module; 83. Signal Processing Module; 84. Abnormal Operation Module; 91. Information Pool Management Module; 92. Historical Data Module; 93. Data Security Module; 94. Interface Management Module. Detailed Implementation

[0018] like Figure 1-10 As shown, the specific implementation adopts the following technical solution: Example: A leakage current identification system for medium and low voltage distribution areas includes a data acquisition module 1, a data preprocessing module 2, a system control module 3, a fault detection module 4, a knowledge graph construction module 5, an event processing module 6, a hierarchical early warning module 7, a system optimization module 8, a data management module 9, and a data center module 10. The data acquisition module 1 and the data preprocessing module 2 are connected. The data preprocessing module 2 is connected to the system control module 3. The system control module 3 is connected to the fault detection module 4. The system control module 3 is connected to the knowledge graph construction module 5. The system control module 3 is connected to the event processing module 6. The system control module 3 is connected to the hierarchical early warning module 7. The system control module 3 is connected to the system optimization module 8. The system control module 3 is connected to the data management module 9. The data management module 9 is connected to the data center module 10.

[0019] The data acquisition module 1 includes a real-time measurement module 11, a power outage reporting module 12, a topology data module 13, and a historical operation data module 14. The real-time measurement module 11 is connected to the power outage reporting module 12, the power outage reporting module 12 is connected to the topology data module 13, and the topology data module 13 is connected to the historical operation data module 14. The real-time measurement module 11 is used to collect real-time electrical quantity data such as voltage and current in the transformer area, providing real-time basic data support for fault analysis; the power outage reporting module 12 is used to collect power outage information reported by users or equipment, realizing rapid perception and reporting of power outage events; the topology data module 13 is used to obtain the topology data of the transformer area power grid, providing a basis for network connection relationships for fault location; the historical operation data module 14 is used to collect historical power outage and equipment operation data, for fault mode analysis and historical pattern mining.

[0020] The data preprocessing module 2 includes a cleaning and filtering module 21, a timescale calibration module 22, an anomaly correction module 23, and a measurement optimization module 24. The cleaning and filtering module 21 is connected to the timescale calibration module 22, the timescale calibration module 22 is connected to the anomaly correction module 23, and the anomaly correction module 23 is connected to the measurement optimization module 24. The cleaning and filtering module 21 is used to remove noise and invalid data, improve data quality, and ensure the accuracy of subsequent analysis; the time stamp calibration module 22 is used to calibrate the consistency of data timestamps to avoid fault analysis errors caused by time deviations; the anomaly correction module 23 is used to correct abnormal information in the topology ledger to ensure the correctness of power grid structure data; and the metering optimization module 24 is used to optimize meter data and improve the reliability and availability of metering data.

[0021] The fault perception module 4 includes a power outage determination module 41, a relationship analysis module 42, a bad pixel shielding module 43, and a feature extraction module 44. The power outage determination module 41 is connected to the relationship analysis module 42, the relationship analysis module 42 is connected to the bad pixel shielding module 43, and the bad pixel shielding module 43 is connected to the feature extraction module 44. The power outage determination module 41 is used to determine whether a power outage event has occurred based on measurement data, thereby achieving preliminary identification of power outage faults; the relationship analysis module 42 is used to identify suspected power outage areas by combining topology structure, thereby narrowing down the scope of fault investigation; the bad point shielding module 43 is used to accurately shield bad point data, thereby avoiding interference from invalid data in fault assessment; the feature extraction module 44 is used to extract leakage current features such as zero-sequence current from electrical quantities, thereby achieving specific identification of leakage faults.

[0022] The knowledge graph construction module 5 includes a topology knowledge module 51, an association establishment module 52, a graph optimization module 53, and a model splicing module 54. The topology knowledge module 51 and the association establishment module 52 are connected, the association establishment module 52 and the graph optimization module 53 are connected, and the graph optimization module 53 and the model splicing module 54 are connected. The topology knowledge module 51 is used to construct an integrated knowledge system for medium and low voltage distribution networks based on topology data, forming a structured topology cognition; the association establishment module 52 is used to establish a wide-area association between equipment, topology and power outage events, realizing multi-dimensional data linkage analysis; the graph optimization module 53 is used to optimize the structure and content of the knowledge graph, improving the graph's support capability for fault analysis; the model splicing module 54 is used to splice and merge different data models to form a complete fault analysis data model system.

[0023] The event-based processing module 6 includes a power outage merging module 61, a merging module 62, an address matching module 63, and a cell identification module 64. The power outage merging module 61 and the merging module 62 are connected, the merging module 62 and the address matching module 63 are connected, and the address matching module 63 and the cell identification module 64 are connected. The power outage merging module 61 is used to merge and consolidate massive amounts of power outage data to achieve event-based management and reduce duplicate alarms; the merging module 62 is used to establish a fault analysis event-based merging model to improve the intelligence level of power outage event handling; the address matching module 63 is used to match user address information to achieve accurate location and description of the fault location; the community identification module 64 is used to identify specific communities and unit numbers to provide accurate location guidance for on-site emergency repairs.

[0024] The graded early warning module 7 includes a user early warning module 71, a frequent early warning module 72, a graded and layered module 73, and an emergency repair support module 74. The user early warning module 71 is connected to the frequent early warning module 72, the frequent early warning module 72 is connected to the graded and layered module 73, and the graded and layered module 73 is connected to the emergency repair support module 74. The user early warning module 71 is used to push early warning information to important users affected by the power outage, thereby improving emergency response efficiency; the frequent early warning module 72 is used to generate frequent power outage early warnings based on the power outage information pool, thereby helping to reduce complaint work orders; the hierarchical module 73 is used to classify and hierarchically warn power outage events, thereby achieving differentiated management of faults; the emergency repair support module 74 is used to provide emergency repair personnel with information such as the location and scope of the fault, thereby improving emergency repair efficiency.

[0025] The system optimization module 8 includes a feeder optimization module 81, a hierarchical protection module 82, a signal processing module 83, and an abnormal operation module 84. The feeder optimization module 81 is connected to the hierarchical protection module 82, the hierarchical protection module 82 is connected to the signal processing module 83, and the signal processing module 83 is connected to the abnormal operation module 84. The feeder optimization module 81 is used to optimize feeder automation functions and improve fault isolation and recovery efficiency; the hierarchical protection module 82 is used to optimize hierarchical protection configuration and improve the accuracy and reliability of fault protection; the signal processing module 83 is used to optimize signal processing in the station and feeders and improve signal transmission and identification accuracy; the abnormal operation module 84 is used to handle abnormal power grid operation modes and ensure the stability and safety of power grid operation.

[0026] The data management module 9 includes an information pool management module 91, a historical data module 92, a data security module 93, and an interface management module 94. The information pool management module 91 is connected to the historical data module 92, the historical data module 92 is connected to the data security module 93, and the data security module 93 is connected to the interface management module 94. The information pool management module 91 is used to manage the power outage information pool data, providing unified data storage and retrieval for fault analysis; the historical data module 92 is used to store historical operating data, providing data support for fault analysis and trend prediction; the data security module 93 is used to ensure system data security and prevent data leakage and illegal tampering; the interface management module 94 is used to manage the system's external interfaces, enabling data interaction and sharing with other systems.

[0027] A method for identifying leakage current in a medium- and low-voltage distribution area system, comprising the following steps: Step S101: Through the real-time measurement, power outage reporting, topology relationship and historical operation data acquisition modules, obtain the electrical quantity of the transformer area, power outage information, power grid topology and historical operation data; after data cleaning and filtering, time stamp synchronization calibration, ledger anomaly correction and metering data optimization, invalid data is eliminated, timestamps are calibrated and topology anomalies are corrected, providing an accurate data foundation for subsequent analysis; Step S102: Based on the preprocessed data, the power outage event determination module is used to identify the power outage event, the topology relationship analysis module is used to locate the suspected power outage area, the bad point data shielding module is used to eliminate interference data, and at the same time, leakage current features such as zero-sequence current are extracted from electrical quantities to achieve preliminary location of power outage fault and specific identification of leakage current features. Step S103: Based on topology data, construct integrated topology knowledge of medium and low voltage distribution networks, establish a wide-area correlation between equipment, topology and power outage events, improve the accuracy of the knowledge graph through the knowledge graph optimization module, and splice and merge different data models to form a structured and correlated fault analysis knowledge system; Step S104: Use the power outage event merging module to merge massive amounts of power outage data, and combine it with the event-based merging model to achieve power outage event-based management; through the address information matching and community unit identification module, accurately locate the community, unit and household number corresponding to the fault, and provide precise location guidance for on-site emergency repairs. Step S105: For important users and historically sensitive users affected by the power outage, push information through the important user early warning module; generate frequent power outage graded early warning events based on the power outage information pool, and combine the graded and layered early warning mechanism to realize differentiated fault management, while providing support information such as the scope of fault impact to the emergency repair personnel; Step S106: Regularly optimize the performance of modules such as feeder automation and hierarchical protection, and handle issues such as station signals and abnormal operation; through power outage information pool management, historical data storage, data security assurance and interface management, realize unified data storage, secure interaction and sharing, and support the continuous and stable operation of the system.

Claims

1. A leakage current identification system for medium and low voltage distribution areas, comprising a data acquisition module (1), a data preprocessing module (2), a system control module (3), a fault perception module (4), a knowledge graph construction module (5), an event processing module (6), a hierarchical early warning module (7), a system optimization module (8), a data management module (9), and a data center module (10), characterized in that: The data acquisition module (1) is connected to the data preprocessing module (2), the data preprocessing module (2) is connected to the system control module (3), the system control module (3) is connected to the fault perception module (4), the system control module (3) is connected to the knowledge graph construction module (5), the system control module (3) is connected to the event processing module (6), the system control module (3) is connected to the hierarchical early warning module (7), the system control module (3) is connected to the system optimization module (8), the system control module (3) is connected to the data management module (9), and the data management module (9) is connected to the data center module (10).

2. The low-voltage distribution area leakage current identification system according to claim 1, characterized in that: The data acquisition module (1) includes a real-time measurement module (11), a power outage reporting module (12), a topology data module (13), and a historical operation data module (14). The real-time measurement module (11) is connected to the power outage reporting module (12), the power outage reporting module (12) is connected to the topology data module (13), and the topology data module (13) is connected to the historical operation data module (14). The real-time measurement module (11) is used to collect real-time electrical quantity data such as voltage and current in the distribution area to provide real-time basic data support for fault analysis. The power outage reporting module (12) is used to collect power outage information reported by users or equipment to realize rapid perception and reporting of power outage events. The topology data module (13) is used to obtain the topology data of the distribution area power grid to provide network connection relationship basis for fault location. The historical operation data module (14) is used to collect historical power outage and equipment operation data for fault mode analysis and historical pattern mining.

3. The low-voltage distribution area leakage current identification system according to claim 1, characterized in that: The data preprocessing module (2) includes a cleaning and filtering module (21), a timescale calibration module (22), an anomaly correction module (23), and a metering optimization module (24). The cleaning and filtering module (21) is connected to the timescale calibration module (22), the timescale calibration module (22) is connected to the anomaly correction module (23), and the anomaly correction module (23) is connected to the metering optimization module (24). The cleaning and filtering module (21) is used to remove noise and invalid data, improve data quality, and ensure the accuracy of subsequent analysis. The timescale calibration module (22) is used to calibrate the consistency of data timestamps to avoid fault analysis errors caused by time deviations. The anomaly correction module (23) is used to correct abnormal information in the topology ledger to ensure the correctness of power grid structure data. The metering optimization module (24) is used to optimize meter data and improve the reliability and availability of meter data.

4. The leakage current identification system for medium and low voltage distribution areas according to claim 1, characterized in that: The fault perception module (4) includes a power outage determination module (41), a relationship analysis module (42), a bad spot shielding module (43), and a feature extraction module (44). The power outage determination module (41) and the relationship analysis module (42) are connected. The relationship analysis module (42) and the bad spot shielding module (43) are connected. The bad spot shielding module (43) and the feature extraction module (44) are connected. The power outage determination module (41) is used to determine whether a power outage event has occurred based on the measurement data, and to realize the preliminary identification of power outage faults. The relationship analysis module (42) is used to identify suspected power outage areas by combining the topology structure, and to narrow down the scope of fault investigation. The bad spot shielding module (43) is used to accurately shield bad spot data and avoid interference from invalid data to fault judgment. The feature extraction module (44) is used to extract leakage current features such as zero-sequence current from electrical quantities, and to realize the special identification of leakage faults.

5. A low-voltage distribution area leakage current identification system according to claim 1, characterized in that: The knowledge graph construction module (5) includes a topology knowledge module (51), an association establishment module (52), a graph optimization module (53), and a model splicing module (54). The topology knowledge module (51) and the association establishment module (52) are connected. The association establishment module (52) and the graph optimization module (53) are connected. The graph optimization module (53) and the model splicing module (54) are connected. The topology knowledge module (51) is used to construct an integrated knowledge system for medium and low voltage distribution networks based on topology data to form a structured topology cognition. The association establishment module (52) is used to establish a wide-area association between equipment, topology, and power outage events to realize multi-dimensional data linkage analysis. The graph optimization module (53) is used to optimize the structure and content of the knowledge graph to improve the graph's support capability for fault analysis. The model splicing module (54) is used to splice and integrate different data models to form a complete fault analysis data model system.

6. The leakage current identification system for medium and low voltage distribution areas according to claim 1, characterized in that: The event processing module (6) includes a power outage merging module (61), a merging module (62), an address matching module (63), and a cell identification module (64). The power outage merging module (61) and the merging module (62) are connected. The merging module (62) and the address matching module (63) are connected. The address matching module (63) and the cell identification module (64) are connected. The power outage merging module (61) is used to merge and consolidate massive amounts of power outage data to achieve event-based management and reduce duplicate alarms. The merging module (62) is used to establish a fault analysis event-based merging model to improve the intelligence level of power outage event processing. The address matching module (63) is used to match user address information to achieve accurate location and description of fault location. The cell identification module (64) is used to identify specific cell and unit number to provide accurate location guidance for on-site emergency repair.

7. A medium- and low-voltage distribution area leakage current identification system according to claim 1, characterized in that: The hierarchical early warning module (7) includes a user early warning module (71), a frequent early warning module (72), a hierarchical layering module (73), and an emergency repair support module (74). The user early warning module (71) and the frequent early warning module (72) are connected. The frequent early warning module (72) and the hierarchical layering module (73) are connected. The hierarchical layering module (73) and the emergency repair support module (74) are connected. The user early warning module (71) is used to push early warning information to important users involved in the power outage, thereby improving the efficiency of emergency response. The frequent early warning module (72) is used to generate frequent power outage early warnings based on the power outage information pool, thereby helping to reduce complaint work orders. The hierarchical layering module (73) is used to conduct hierarchical early warnings for power outage events, thereby achieving differentiated management of faults. The emergency repair support module (74) is used to provide emergency repair personnel with information such as the location and scope of the fault, thereby improving the efficiency of emergency repairs.

8. A medium- and low-voltage distribution area leakage current identification system according to claim 1, characterized in that: The system optimization module (8) includes a feeder optimization module (81), a hierarchical protection module (82), a signal processing module (83), and an abnormal operation module (84). The feeder optimization module (81) and the hierarchical protection module (82) are connected, the hierarchical protection module (82) and the signal processing module (83) are connected, and the signal processing module (83) and the abnormal operation module (84) are connected. The feeder optimization module (81) is used to optimize the feeder automation function and improve the efficiency of fault isolation and recovery. The hierarchical protection module (82) is used to optimize the hierarchical protection configuration and improve the accuracy and reliability of fault protection. The signal processing module (83) is used to optimize the signal processing in the station and feeder, and improve the signal transmission and identification accuracy. The abnormal operation module (84) is used to handle abnormal power grid operation modes and ensure the stability and security of power grid operation.

9. A medium- and low-voltage distribution area leakage current identification system according to claim 1, characterized in that: The data management module (9) includes an information pool management module (91), a historical data module (92), a data security module (93), and an interface management module (94). The information pool management module (91) is connected to the historical data module (92), the historical data module (92) is connected to the data security module (93), and the data security module (93) is connected to the interface management module (94). The information pool management module (91) is used to manage the power outage information pool data and provide unified data storage and retrieval for fault analysis. The historical data module (92) is used to store historical operating data and provide data support for fault analysis and trend prediction. The data security module (93) is used to ensure system data security and prevent data leakage and illegal tampering. The interface management module (94) is used to manage the system's external interfaces and realize data interaction and sharing with other systems.

10. The identification method of a medium- and low-voltage distribution area leakage current identification system according to any one of claims 1-9, characterized in that: The specific steps include: Step S101: Through the real-time measurement, power outage reporting, topology relationship and historical operation data acquisition modules, obtain the electrical quantity of the transformer area, power outage information, power grid topology and historical operation data; after data cleaning and filtering, time stamp synchronization calibration, ledger anomaly correction and metering data optimization, invalid data is eliminated, timestamps are calibrated and topology anomalies are corrected, providing an accurate data foundation for subsequent analysis; Step S102: Based on the preprocessed data, the power outage event determination module is used to identify the power outage event, the topology relationship analysis module is used to locate the suspected power outage area, the bad point data shielding module is used to eliminate interference data, and at the same time, leakage current features such as zero-sequence current are extracted from electrical quantities to achieve preliminary location of power outage fault and specific identification of leakage current features. Step S103: Based on topology data, construct integrated topology knowledge of medium and low voltage distribution networks, establish a wide-area correlation between equipment, topology and power outage events, improve the accuracy of the knowledge graph through the knowledge graph optimization module, and splice and merge different data models to form a structured and correlated fault analysis knowledge system; Step S104: Use the power outage event merging module to merge massive amounts of power outage data, and combine it with the event-based merging model to achieve power outage event-based management; through the address information matching and community unit identification module, accurately locate the community, unit and household number corresponding to the fault, and provide precise location guidance for on-site emergency repairs. Step S105: For important users and historically sensitive users affected by the power outage, push information through the important user early warning module; generate frequent power outage graded early warning events based on the power outage information pool, and combine the graded and layered early warning mechanism to realize differentiated fault management, while providing support information such as the scope of fault impact to the emergency repair personnel; Step S106: Regularly optimize the performance of modules such as feeder automation and hierarchical protection, and handle issues such as station signals and abnormal operation; through power outage information pool management, historical data storage, data security assurance and interface management, realize unified data storage, secure interaction and sharing, and support the continuous and stable operation of the system.

Images