A power distribution network cable leakage current and insulation state on-line monitoring system and method

Abstract

This invention discloses an online monitoring system and method for leakage current and insulation status of power distribution network cables, belonging to the field of power system transmission and distribution technology. To address the problems of poor fault prediction accuracy and low correlation between multi-source data, key features characterizing cable health status are extracted. A more comprehensive feature set is formed by combining multi-source data, enabling information from different data sources to be matched and correlated. The system analyzes the correlation between leakage current and temperature, humidity, partial discharge, and cable load, achieving multi-parameter fusion monitoring, predicting future leakage current data trends, quickly identifying potential fault precursors, and triggering an early warning mechanism when a potential fault risk is predicted. This allows the system to provide early warnings before faults occur. Furthermore, characterizing features of cable insulation status are extracted from the fused data, enabling real-time and accurate assessment of cable insulation status, and achieving remote monitoring and early warning of cable leakage current and insulation status.

Description

Technical Field

[0001] This invention relates to the field of power system transmission and distribution technology, and in particular to an online monitoring system and method for leakage current and insulation status of distribution network cables. Background Technology

[0002] Monitoring leakage current and insulation status of distribution network cables is crucial for ensuring the safe and stable operation of the power grid. Leakage current monitoring can promptly detect cable insulation aging or damage, preventing potential fire risks, while insulation status assessment helps identify potential faults in advance, avoiding sudden power outages. This monitoring not only improves the reliability of the power grid but also reduces maintenance costs and extends cable lifespan, playing a significant role in promoting the development of smart grids.

[0003] However, the following problems still exist in actual operation:

[0004] Existing monitoring systems often rely on a single data source or simple data analysis methods. Data from multiple sources often exist in isolation, making it difficult to effectively correlate and synthesize them, and thus difficult to comprehensively and accurately predict cable faults. Summary of the Invention

[0005] The purpose of this invention is to provide an online monitoring system and method for leakage current and insulation status of power distribution network cables, so as to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an online monitoring system for leakage current and insulation status of power distribution network cables, comprising:

[0007] The data acquisition module is used for:

[0008] It interacts with high-precision leakage current sensors, temperature sensors, humidity sensors and partial discharge monitoring sensors deployed at key cable nodes in the power distribution network, collects sensor data periodically or continuously, and performs preliminary data formatting processing.

[0009] Data transmission module, used for:

[0010] The data collected by the data acquisition module is transmitted to the cloud server and regional data center via wireless communication, and the data is encrypted during the data transmission process.

[0011] The data processing module is used for:

[0012] The received data is cleaned and stored in a distributed database, where it is then standardized and normalized.

[0013] The fault prediction module is used for:

[0014] Perform trend analysis and fault feature extraction on leakage current data, and predict potential cable fault risks based on the analysis results;

[0015] The integrated monitoring module is used for:

[0016] By integrating multi-source data such as leakage current, temperature, humidity, partial discharge, and cable operating load parameters, and based on the correlation between various parameters through data fusion analysis, and combined with the results of multi-parameter analysis, a comprehensive assessment of the cable insulation condition is conducted.

[0017] The remote monitoring module is used for:

[0018] It receives control commands sent remotely via a web interface and a mobile app, generates a user interface to display real-time monitoring data and fault diagnosis results, and monitors the device status of each monitoring node in real time, including sensor working status and power supply status.

[0019] Furthermore, the data acquisition module includes:

[0020] Sensor interface unit, used for:

[0021] Connect to a high-precision leakage current sensor, temperature sensor, humidity sensor and partial discharge monitoring sensor, trigger data acquisition tasks at regular intervals or according to preset conditions, read the raw data of each sensor, the raw data includes leakage current value, temperature value, humidity value and partial discharge information, and add timestamp and sensor ID information to each type of sensor data;

[0022] The data verification unit is used for:

[0023] The collected data is checked for reasonableness. Data that fails the check is discarded, and data that passes the check is preprocessed, including data compression and data smoothing.

[0024] Furthermore, the data processing module includes:

[0025] The data cleaning unit is used for:

[0026] Identify and remove outliers from the original data and handle missing values; perform data integrity checks and consistency verification.

[0027] Data storage unit, used for:

[0028] The cleaned data is stored in a distributed database, historical data is archived, and historical data is cleaned up and the database is backed up regularly.

[0029] Data standardization units are used for:

[0030] The data collected by different sensors is standardized and converted into standard units. The data is then normalized to scale the data range to the interval (0-1). The standardized and normalized data is then output to the fault prediction module.

[0031] Furthermore, the fault prediction module includes:

[0032] Feature extraction unit, used for:

[0033] The data processing module receives cleaned, standardized, and normalized data, and performs time series processing on the data based on sliding window, differencing, and seasonal adjustment.

[0034] Feature data that characterizes the health status of the cable is extracted from leakage current data. The feature data includes mean, variance, peak value, slope, and waveform complexity. Combined with the features of temperature, humidity, and partial discharge parameters, cross-feature extraction is performed.

[0035] Anomaly detection unit, used for:

[0036] Time series analysis is performed on leakage current data to identify long-term trends, seasonal variations, or periodic patterns. Based on the ARIMA model, future leakage current data trends are predicted. Anomaly detection is performed on real-time data to identify data points that deviate from the normal pattern as potential fault precursors.

[0037] Furthermore, the fault prediction module also includes:

[0038] Fault prediction unit, used for:

[0039] The linear regression model is trained using historical failure data and normal operation data as training sets, evaluated using a test set, and iteratively optimized based on the evaluation results.

[0040] Based on the results of the fault prediction model, an early warning threshold is set. When the predicted potential fault risk exceeds the threshold, the early warning mechanism is automatically triggered, and early warning information is sent to relevant personnel through the remote monitoring module. The early warning information includes the fault type, predicted occurrence time, and scope of impact.

[0041] Furthermore, the fusion monitoring module includes:

[0042] Multi-source data integration unit, used for:

[0043] It receives multi-source data on leakage current, temperature, humidity, partial discharge, and cable operating load from the data processing module after standardization and normalization, and stores the integrated multi-source data in a distributed database.

[0044] The data fusion processing unit is used for:

[0045] Time alignment and interpolation operations are performed on multi-source data, and multi-source data are fused. The parameter information of each multi-source data is integrated through the fusion algorithm to analyze the correlation between leakage current and temperature, humidity, partial discharge and cable load.

[0046] Furthermore, the fusion monitoring module also includes:

[0047] Insulation condition assessment unit, used for:

[0048] Characteristic features of cable insulation status are extracted from the fused data, including the trend of insulation resistance variation, the intensity and frequency of partial discharge;

[0049] Feature selection and dimensionality reduction are performed on the representation features;

[0050] The neural network model is trained by replacing historical data, and real-time data is input into the trained evaluation model to make online judgments on the insulation status. The insulation status of the cable is judged based on the model output.

[0051] Furthermore, the remote monitoring module includes:

[0052] User interface generation unit, used for:

[0053] The system receives real-time monitoring data, fault diagnosis results, and cable insulation status data of the cable, and generates a user interface including a web interface and a mobile APP interface. The user interface includes a data display area, a chart area, and a control command input area. The real-time monitoring data is displayed on the user interface in the form of charts, graphs, and dashboards, and the data is updated in real time.

[0054] Control instruction unit, used for:

[0055] The system receives control commands sent by users through a web interface or mobile app, parses the received control commands, identifies the command type and parameters, sends the parsed control commands to the corresponding modules or devices for execution, and receives execution result feedback, including execution success, execution failure, or execution in progress.

[0056] Furthermore, the remote monitoring module also includes:

[0057] The equipment status monitoring unit is used for:

[0058] The device status data of each monitoring node is obtained from the data acquisition module. The device status data includes the working status of the sensors and the power supply status. The collected device status data is analyzed to determine whether the device is operating normally. The device status monitoring is recorded in the log and a device status report is generated periodically.

[0059] Furthermore, an online monitoring method for leakage current and insulation status of distribution network cables, applied to the aforementioned online monitoring system for leakage current and insulation status of distribution network cables, includes the following steps:

[0060] Step 1: Data acquisition and processing. Real-time acquisition of raw data from cable nodes. Preliminary formatting of the raw sensor data. Data verification. Cleaning of the verified data. Standardization and normalization of the cleaned data.

[0061] Step 2: Fault prediction and early warning. Extract characteristic data representing the health status of the cable from the cleaned and standardized data, perform trend analysis and anomaly detection on leakage current data, identify potential fault signs, set early warning thresholds, and automatically trigger the early warning mechanism to send early warning information to relevant personnel when the predicted potential fault risk exceeds the threshold.

[0062] Step 3: Insulation condition assessment. This involves integrating and fusing multi-source data such as leakage current, temperature, humidity, partial discharge, and cable operating load, analyzing the correlation between parameters, extracting the characterization features of the cable insulation condition, and performing online judgment and assessment of the insulation condition.

[0063] Step 4: Remote monitoring feedback, receiving control commands sent by users, displaying monitoring data and fault diagnosis results in real time, monitoring the equipment status of each monitoring node, recording equipment status monitoring in the log, and generating reports periodically.

[0064] Compared with the prior art, the beneficial effects of the present invention are:

[0065] 1. This invention, through time series processing and cross-feature extraction, can fully mine the potential information in the data, extract key features that can characterize the health status of cables, and form a more comprehensive feature set by combining multi-source data. This helps to improve the accuracy and reliability of fault prediction, track the changing trend of leakage current data in real time, identify anomalies in the data in a timely manner, predict the future changing trend of leakage current data, and compare it with real-time data to quickly discover potential fault signs. It automatically sets a warning threshold based on the prediction results and triggers a warning mechanism when the predicted potential fault risk exceeds the threshold. This enables the system to provide early warnings before the fault occurs, ensuring that maintenance personnel can obtain fault information in a timely manner and take corresponding measures.

[0066] 2. This invention synchronizes multi-source data in time through preprocessing steps such as time alignment and interpolation, enabling information from different data sources to match and correlate. By integrating parameter information from various multi-source data through a fusion algorithm, the correlation between leakage current and temperature, humidity, partial discharge, and cable load is analyzed. This helps to better understand the complex changes in cable insulation status, improves the intelligence level of the monitoring system, extracts the characterization features of cable insulation status from the fused data, and uses a neural network model to make online judgments on insulation status. This enables real-time and accurate assessment of cable insulation status, providing reliable decision-making basis for maintenance personnel. By inputting data into the trained assessment model in real time, the fusion monitoring module can achieve dynamic monitoring of cable insulation status, helping to reduce the possibility of faults and improve the safety and stability of the power grid. Attached Figure Description

[0067] Figure 1 This is a schematic diagram of the online monitoring system module for leakage current and insulation status of the present invention;

[0068] Figure 2 This is a schematic diagram of the online monitoring method for leakage current and insulation status of the present invention. Detailed Implementation

[0069] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0070] To address the technical problems of existing monitoring systems often relying on a single data source or simple data analysis methods, where multi-source data often exists in isolation, making effective correlation and comprehensive analysis difficult, and thus hindering the comprehensive and accurate prediction of cable faults, please refer to [the relevant documentation / reference]. Figure 1-2 The present invention provides the following technical solutions:

[0071] An online monitoring system for leakage current and insulation status of power distribution network cables includes:

[0072] The data acquisition module is used for:

[0073] It interacts with high-precision leakage current sensors, temperature sensors, humidity sensors and partial discharge monitoring sensors deployed at key cable nodes in the power distribution network, collects sensor data periodically or continuously, and performs preliminary data formatting processing.

[0074] Data transmission module, used for:

[0075] The data collected by the data acquisition module is transmitted to the cloud server and regional data center via wireless communication, and the data is encrypted during the data transmission process.

[0076] The data processing module is used for:

[0077] The received data is cleaned and stored in a distributed database, where it is then standardized and normalized.

[0078] The fault prediction module is used for:

[0079] Perform trend analysis and fault feature extraction on leakage current data, and predict potential cable fault risks based on the analysis results;

[0080] The integrated monitoring module is used for:

[0081] By integrating multi-source data such as leakage current, temperature, humidity, partial discharge, and cable operating load parameters, and based on the correlation between various parameters through data fusion analysis, and combined with the results of multi-parameter analysis, a comprehensive assessment of the cable insulation condition is conducted.

[0082] The remote monitoring module is used for:

[0083] It receives control commands sent remotely via a web interface and a mobile app, generates a user interface to display real-time monitoring data and fault diagnosis results, and monitors the device status of each monitoring node in real time, including sensor working status and power supply status.

[0084] In the above embodiments, the system monitors key parameters of the cable in real time, such as leakage current, temperature, humidity and partial discharge, through high-precision sensors. It can detect abnormal conditions of the cable in a timely manner and predict potential fault risks, which helps to discover and solve problems in the early stage, prevent the fault from expanding, and ensure the stable operation of the power grid.

[0085] In the above embodiments, data from multiple sensors are integrated and analyzed, and data fusion technology is used to reveal the correlation between various parameters. The comprehensive evaluation method of multi-source data can more comprehensively and accurately reflect the insulation status and health status of the cable, providing maintenance personnel with a more scientific basis for decision-making. Remote monitoring functions are provided through a web interface and mobile APP, enabling maintenance personnel to view real-time monitoring data and fault diagnosis results of the cable anytime and anywhere.

[0086] In the above embodiments, the system's automation and intelligence characteristics reduce the workload of maintenance personnel and lower the risk of human error. At the same time, by detecting and predicting faults early, it avoids greater losses caused by the expansion of faults, thereby reducing maintenance costs. Real-time monitoring and early warning functions help to detect and deal with potential cable problems in a timely manner, avoiding accidents such as power outages or equipment damage caused by cable faults, and enhancing the safety and stability of the power grid.

[0087] The data acquisition module includes:

[0088] Sensor interface unit, used for:

[0089] Connect to a high-precision leakage current sensor, temperature sensor, humidity sensor and partial discharge monitoring sensor, trigger data acquisition tasks at regular intervals or according to preset conditions, read the raw data of each sensor, the raw data includes leakage current value, temperature value, humidity value and partial discharge information, and add timestamp and sensor ID information to each type of sensor data;

[0090] The data verification unit is used for:

[0091] The collected data is checked for reasonableness. Data that fails the check is discarded, and data that passes the check is preprocessed, including data compression and data smoothing.

[0092] In the above embodiments, adding timestamps and sensor ID information to each type of sensor data facilitates subsequent data management and analysis, improves data traceability and reliability, and allows the data acquisition module to simultaneously connect to multiple types of sensors, providing a rich data source for subsequent multi-source data fusion. The fusion analysis of multi-source data can more comprehensively reflect the insulation status and health condition of the cable, improving the accuracy and reliability of fault diagnosis.

[0093] In the above embodiments, the data acquisition module adds timestamps and sensor ID information to each type of sensor data, which helps with subsequent data management and analysis. The timestamps can be used to trace the data acquisition time, and the sensor IDs can be used to distinguish data from different sensors, which facilitates data classification, storage and analysis. The automation and intelligence of the data acquisition module reduces the workload of maintenance personnel and lowers the risk of human error.

[0094] The data processing module includes:

[0095] The data cleaning unit is used for:

[0096] Identify and remove outliers from the original data and handle missing values; perform data integrity checks and consistency verification.

[0097] Data storage unit, used for:

[0098] The cleaned data is stored in a distributed database, historical data is archived, and historical data is cleaned up and the database is backed up regularly.

[0099] Data standardization units are used for:

[0100] The data collected by different sensors is standardized and converted into standard units. The data is then normalized to scale the data range to the interval (0-1). The standardized and normalized data is then output to the fault prediction module.

[0101] In the above embodiments, the data collected by different sensors are standardized and normalized, eliminating differences in dimensions and orders of magnitude between different data, making the data comparable, facilitating subsequent data analysis and processing, and helping to extract fault characteristics and conduct trend analysis more accurately. Through automated and intelligent data processing, the workload of maintenance personnel is reduced, and maintenance efficiency is improved. At the same time, high-quality data and accurate fault prediction results can help maintenance personnel locate problems more quickly, formulate solutions, and optimize maintenance strategies.

[0102] The fault prediction module includes:

[0103] Feature extraction unit, used for:

[0104] The data processing module receives cleaned, standardized, and normalized data, and performs time series processing on the data based on sliding window, differencing, and seasonal adjustment.

[0105] Feature data that characterizes the health status of the cable is extracted from leakage current data. The feature data includes mean, variance, peak value, slope, and waveform complexity. Combined with the features of temperature, humidity, and partial discharge parameters, cross-feature extraction is performed.

[0106] Anomaly detection unit, used for:

[0107] Time series analysis is performed on leakage current data to identify long-term trends, seasonal changes, or periodic patterns. Based on the ARIMA model, future leakage current data change trends are predicted. Anomaly detection is performed on real-time data to identify data points that deviate from the normal pattern as potential fault precursors.

[0108] Fault prediction unit, used for:

[0109] The linear regression model is trained using historical failure data and normal operation data as training sets, evaluated using a test set, and iteratively optimized based on the evaluation results.

[0110] Based on the results of the fault prediction model, an early warning threshold is set. When the predicted potential fault risk exceeds the threshold, the early warning mechanism is automatically triggered, and early warning information is sent to relevant personnel through the remote monitoring module. The early warning information includes the fault type, predicted occurrence time, and scope of impact.

[0111] In the above embodiments, by using time series processing and cross-feature extraction, the potential information in the data can be fully explored, and key features that can characterize the health status of the cable can be extracted. In addition, multi-source data such as temperature, humidity, and partial discharge are combined to form a more comprehensive feature set, which helps to improve the accuracy and reliability of fault prediction, track the changing trend of leakage current data in real time, identify anomalies in the data in a timely manner, predict the future changing trend of leakage current data, and compare it with real-time data to quickly discover potential fault signs. This allows the system to provide early warnings before faults occur, giving maintenance personnel more time to handle the situation.

[0112] In the above embodiments, an early warning threshold is automatically set based on the prediction results, and an early warning mechanism is triggered when a potential fault risk is predicted to exceed the threshold. This ensures that maintenance personnel can obtain fault information in a timely manner and take corresponding measures. Simultaneously, through the web interface and mobile APP of the remote monitoring module, maintenance personnel can view monitoring data and early warning information anytime, anywhere, achieving comprehensive monitoring and remote control of the distribution network cable status.

[0113] The integrated monitoring module includes:

[0114] Multi-source data integration unit, used for:

[0115] It receives multi-source data on leakage current, temperature, humidity, partial discharge, and cable operating load from the data processing module after standardization and normalization, and stores the integrated multi-source data in a distributed database.

[0116] The data fusion processing unit is used for:

[0117] Time alignment and interpolation operations are performed on multi-source data, and multi-source data are fused. The parameter information of each multi-source data is integrated through the fusion algorithm to analyze the correlation between leakage current and temperature, humidity, partial discharge and cable load.

[0118] Insulation condition assessment unit, used for:

[0119] Characteristic features of cable insulation status are extracted from the fused data, including the trend of insulation resistance variation, the intensity and frequency of partial discharge;

[0120] Feature selection and dimensionality reduction are performed on the representation features;

[0121] The neural network model is trained by replacing historical data, and real-time data is input into the trained evaluation model to make online judgments on the insulation status. The insulation status of the cable is judged based on the model output.

[0122] In the above embodiments, preprocessing steps such as time alignment and interpolation are used to synchronize multi-source data in time, enabling information from different data sources to be matched and correlated. Subsequently, the parameter information of each multi-source data is integrated through a fusion algorithm to analyze the correlation between leakage current and temperature, humidity, partial discharge and cable load. This helps to better understand the complex changes in cable insulation status and improves the intelligence level of the monitoring system.

[0123] In the above embodiments, the characteristic features of cable insulation status are extracted from the fused data, and the insulation status is judged online using a neural network model. This enables real-time and accurate assessment of cable insulation status, providing reliable decision-making basis for operation and maintenance personnel. By inputting data into the trained assessment model in real time, the fusion monitoring module can realize dynamic monitoring of cable insulation status, which helps to reduce the possibility of faults and improve the safety and stability of the power grid.

[0124] The remote monitoring module includes:

[0125] User interface generation unit, used for:

[0126] The system receives real-time monitoring data, fault diagnosis results, and cable insulation status data of the cable, and generates a user interface including a web interface and a mobile APP interface. The user interface includes a data display area, a chart area, and a control command input area. The real-time monitoring data is displayed on the user interface in the form of charts, graphs, and dashboards, and the data is updated in real time.

[0127] Control instruction unit, used for:

[0128] The system receives control commands sent by users through a web interface or mobile APP, parses the received control commands, identifies the command type and parameters, sends the parsed control commands to the corresponding modules or devices for execution, and receives execution result feedback, including execution success, execution failure, or execution in progress.

[0129] The equipment status monitoring unit is used for:

[0130] The device status data of each monitoring node is obtained from the data acquisition module. The device status data includes the working status of the sensors and the power supply status. The collected device status data is analyzed to determine whether the device is operating normally. The device status monitoring is recorded in the log and a device status report is generated periodically.

[0131] In the above embodiments, the real-time and dynamic data display method greatly enhances the user's interactive experience, enabling users to easily obtain key information and understand the cable's operating status in a timely manner. The remote control function not only improves operation and maintenance efficiency but also reduces the risk of on-site operation. Obtaining equipment status data from each monitoring node from the data acquisition module and performing real-time analysis and judgment helps to promptly detect equipment faults or abnormalities and take corresponding measures to deal with them.

[0132] In the above embodiments, the remote monitoring module integrates multiple aspects such as data acquisition, data processing, fault prediction, and equipment status monitoring, realizing comprehensive monitoring and remote management of leakage current and insulation status of power distribution network cables. This not only improves the overall operation and maintenance efficiency of the system, but also reduces manpower and material costs.

[0133] In the above embodiments, by monitoring the operating status of the cable and the working condition of the equipment in real time, the remote monitoring module can promptly detect and handle potential problems, thereby avoiding the risks of system paralysis or data loss caused by the expansion of faults, which helps to improve the reliability and stability of the system and ensure the safe operation of the power grid.

[0134] To better demonstrate the online monitoring system for leakage current and insulation status of distribution network cables, this embodiment proposes a method for online monitoring of leakage current and insulation status of distribution network cables, including the following steps:

[0135] Step 1: Data acquisition and processing. Real-time acquisition of raw data from cable nodes. Preliminary formatting of the raw sensor data. Data verification. Cleaning of the verified data. Standardization and normalization of the cleaned data.

[0136] Step 2: Fault prediction and early warning. Extract characteristic data representing the health status of the cable from the cleaned and standardized data, perform trend analysis and anomaly detection on leakage current data, identify potential fault signs, set early warning thresholds, and automatically trigger the early warning mechanism to send early warning information to relevant personnel when the predicted potential fault risk exceeds the threshold.

[0137] Step 3: Insulation condition assessment. This involves integrating and fusing multi-source data such as leakage current, temperature, humidity, partial discharge, and cable operating load, analyzing the correlation between parameters, extracting the characterization features of the cable insulation condition, and performing online judgment and assessment of the insulation condition.

[0138] Step 4: Remote monitoring feedback, receiving control commands sent by users, displaying monitoring data and fault diagnosis results in real time, monitoring the equipment status of each monitoring node, recording equipment status monitoring in the log, and generating reports periodically.

[0139] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. An online monitoring system for leakage current and insulation status of power distribution network cables, characterized in that, include: The data acquisition module is used for: It interacts with high-precision leakage current sensors, temperature sensors, humidity sensors and partial discharge monitoring sensors deployed at key cable nodes in the power distribution network, collects sensor data periodically or continuously, and performs preliminary data formatting processing. Data transmission module, used for: The data collected by the data acquisition module is transmitted to the cloud server and regional data center via wireless communication, and the data is encrypted during the data transmission process. The data processing module is used for: The received data is cleaned and stored in a distributed database, where it is then standardized and normalized. The fault prediction module is used for: Perform trend analysis and fault feature extraction on leakage current data, and predict potential cable fault risks based on the analysis results; The fault prediction module includes: Feature extraction unit, used for: The data processing module receives cleaned, standardized, and normalized data, and performs time series processing on the data based on sliding window, differencing, and seasonal adjustment. Feature data that characterizes the health status of the cable is extracted from leakage current data. The feature data includes mean, variance, peak value, slope, and waveform complexity. Combined with the features of temperature, humidity, and partial discharge parameters, cross-feature extraction is performed. Anomaly detection unit, used for: Time series analysis is performed on leakage current data to identify long-term trends, seasonal changes, or periodic patterns. Based on the ARIMA model, future leakage current data change trends are predicted. Anomaly detection is performed on real-time data to identify data points that deviate from the normal pattern as potential fault precursors. The integrated monitoring module is used for: The leakage current, temperature, humidity, partial discharge, and cable operating load parameters are integrated from multiple sources. Based on the data fusion analysis, the correlation between the parameters is analyzed, and the cable insulation status is comprehensively evaluated in combination with the results of the multi-parameter analysis. The fusion monitoring module includes: Insulation condition assessment unit, used for: Characteristic features of cable insulation status are extracted from the fused data, including the trend of insulation resistance variation, the intensity and frequency of partial discharge; Feature selection and dimensionality reduction are performed on the representation features; The neural network model is trained by replacing historical data, and real-time data is input into the trained evaluation model to make online judgments on the insulation status. The insulation status of the cable is judged based on the model output results. The remote monitoring module is used for: It receives control commands sent remotely via a web interface and a mobile app, generates a user interface to display real-time monitoring data and fault diagnosis results, and monitors the device status of each monitoring node in real time, including sensor working status and power supply status.

2. The online monitoring system for leakage current and insulation status of power distribution cables as described in claim 1, characterized in that, The data acquisition module includes: Sensor interface unit, used for: Connect to a high-precision leakage current sensor, temperature sensor, humidity sensor and partial discharge monitoring sensor, trigger data acquisition tasks at regular intervals or according to preset conditions, read the raw data of each sensor, the raw data includes leakage current value, temperature value, humidity value and partial discharge information, and add timestamp and sensor ID information to each type of sensor data; The data verification unit is used for: The collected data is checked for reasonableness. Data that fails the check is discarded, and data that passes the check is preprocessed, including data compression and data smoothing.

3. The online monitoring system for leakage current and insulation status of power distribution network cables as described in claim 2, characterized in that, The data processing module includes: The data cleaning unit is used for: Identify and remove outliers from the original data and handle missing values; perform data integrity checks and consistency verification. Data storage unit, used for: The cleaned data is stored in a distributed database, historical data is archived, and historical data is cleaned up and the database is backed up regularly. Data standardization units are used for: The data collected by different sensors is standardized and converted into standard units. The data is then normalized to scale the data range to the interval of (0-1). The standardized and normalized data is then output to the fault prediction module.

4. The online monitoring system for leakage current and insulation status of power distribution network cables as described in claim 3, characterized in that, The fault prediction module further includes: Fault prediction unit, used for: The linear regression model is trained using historical failure data and normal operation data as training sets, evaluated using a test set, and iteratively optimized based on the evaluation results. Based on the results of the fault prediction model, an early warning threshold is set. When the predicted potential fault risk exceeds the threshold, the early warning mechanism is automatically triggered, and early warning information is sent to relevant personnel through the remote monitoring module. The early warning information includes the fault type, predicted occurrence time, and scope of impact.

5. The online monitoring system for leakage current and insulation status of power distribution cables as described in claim 4, characterized in that, The fusion monitoring module also includes: Multi-source data integration unit, used for: It receives multi-source data on leakage current, temperature, humidity, partial discharge, and cable operating load from the data processing module after standardization and normalization, and stores the integrated multi-source data in a distributed database. The data fusion processing unit is used for: Time alignment and interpolation operations are performed on multi-source data, and multi-source data are fused. The parameter information of each multi-source data is integrated through the fusion algorithm to analyze the correlation between leakage current and temperature, humidity, partial discharge and cable load.

6. The online monitoring system for leakage current and insulation status of power distribution cables as described in claim 5, characterized in that, The remote monitoring module includes: User interface generation unit, used for: The system receives real-time monitoring data, fault diagnosis results, and cable insulation status data of the cable, and generates a user interface including a web interface and a mobile APP interface. The user interface includes a data display area, a chart area, and a control command input area. The real-time monitoring data is displayed on the user interface in the form of charts, graphs, and dashboards, and the data is updated in real time. Control instruction unit, used for: The system receives control commands sent by users through a web interface or mobile app, parses the received control commands, identifies the command type and parameters, sends the parsed control commands to the corresponding modules or devices for execution, and receives execution result feedback, including execution success, execution failure, or execution in progress.

7. The online monitoring system for leakage current and insulation status of power distribution cables as described in claim 6, characterized in that, The remote monitoring module also includes: The equipment status monitoring unit is used for: The device status data of each monitoring node is obtained from the data acquisition module. The device status data includes the working status of the sensors and the power supply status. The collected device status data is analyzed to determine whether the device is operating normally. The device status monitoring is recorded in the log and a device status report is generated periodically.

8. A method for online monitoring of leakage current and insulation status of distribution network cables, applied in the online monitoring system for leakage current and insulation status of distribution network cables as described in any one of claims 1-7, characterized in that, Includes the following steps: Step 1: Data acquisition and processing. Real-time acquisition of raw data from cable nodes. Preliminary formatting of the raw sensor data. Data verification. Cleaning of the verified data. Standardization and normalization of the cleaned data. Step 2: Fault prediction and early warning. Extract characteristic data representing the health status of the cable from the cleaned and standardized data, perform trend analysis and anomaly detection on leakage current data, identify potential fault signs, set early warning thresholds, and automatically trigger the early warning mechanism to send early warning information to relevant personnel when the predicted potential fault risk exceeds the threshold. Step 3: Insulation condition assessment. This involves integrating and fusing multi-source data such as leakage current, temperature, humidity, partial discharge, and cable operating load, analyzing the correlation between parameters, extracting the characterization features of the cable insulation condition, and performing online judgment and assessment of the insulation condition. Step 4: Remote monitoring feedback, receiving control commands sent by users, displaying monitoring data and fault diagnosis results in real time, monitoring the equipment status of each monitoring node, recording equipment status monitoring in the log, and generating reports periodically.

Images