A high-voltage cable lead seal defect monitoring system based on resistance value

Abstract

The present invention discloses a high-voltage cable lead seal defect monitoring system based on resistance values, which relates to the field of cable monitoring and includes: an instruction management module for connecting to the power transmission grid of the cable, obtaining the acquisition permission of the power supply operation status data, and editing and sending control instructions for each functional module; a model construction module for real-time collecting the operation parameters of several lead seal nodes and associated cables in a specified cable section, integrating them into power supply operation status data, and constructing a three-dimensional lead seal model; a trend monitoring module for inputting the real-time power supply operation status data of the current cable section into the three-dimensional lead seal model and outputting the resistance change trends of several lead seal nodes; by capturing and marking the abnormal states of several nodes in a specified cable section, generating an efficient detection path, improving the path planning efficiency, shortening the detection time, ensuring the maximum detection coverage, and avoiding external environmental interference at the same time, and predicting crack propagation more accurately through a more accurate model.

Description

Technical Field

[0001] The present invention relates to the technical field of cable monitoring, in particular to a high-voltage cable lead seal defect monitoring system based on resistance value. Background Art

[0002] High-voltage cables are widely used in power transmission and distribution systems, especially in urban power grids, industrial parks, and large-scale infrastructure. They are usually buried underground or laid along structures such as buildings and bridges. As high-voltage cables age, material aging or external environmental factors such as water intrusion, soil corrosion, and mechanical damage may cause lead seal defects. These defects may lead to reduced cable insulation performance, which in turn may cause safety accidents such as short circuits, power outages, and even fires. Since the reliability and safety of power systems are of paramount importance, an effective monitoring system is needed to promptly detect and evaluate cable defects.

[0003] Traditional monitoring methods, such as eddy current monitoring or infrared monitoring, lack sensitivity when detecting tiny defects, resulting in early defects not being discovered in time. They are unable to respond quickly after defects occur, causing defects to expand to an irreversible stage. They only analyze single data and have high limitations.

[0004] For daily node monitoring, the existing node selection relies on manual experience, node evaluation is one-sided, the detection path is inefficient and time-consuming, the defect prediction is rough and has large errors, and it is impossible to accurately simulate crack growth. Summary of the Invention

[0005] (1) Technical Problems Solved: In response to the above-mentioned shortcomings of the prior art, the present invention provides a high-voltage cable seal defect monitoring system based on resistance value, which can effectively solve the problems of the prior art.

[0006] (2) Technical solution: To achieve the above objectives, the present invention is implemented through the following technical solution. The present invention discloses a high-voltage cable seal defect monitoring system based on resistance value, including: an instruction management module for connecting to the cable transmission power grid, obtaining the collection authority of power supply operation status data, and editing and sending control instructions for each functional module.

[0007] The model building module is used to collect the operating parameters of several seal nodes and associated cables in a specified cable segment in real time, integrate them into power supply operation status data, and build a three-dimensional seal model.

[0008] The trend monitoring module is used to input the real-time power supply operation status data of the current cable segment into the seal three-dimensional model, output the resistance change trends of several seal nodes, set the early warning threshold, and determine whether the resistance change trend of a node has resistance fluctuations beyond the preset range.

[0009] A detection planning unit, which is used to capture key nodes in the cable section with abnormal resistance fluctuations, generate infrared detection points based on the key nodes, and generate an optimal defect detection path.

[0010] A defect evaluation module, which is used to detect defects in the sealed area through the optimal defect detection path, obtain multi-modal defect data, fuse and classify them, and evaluate the defect performance coefficients of several nodes.

[0011] A fission prediction module, which is used for coherent fusion of defect performance coefficients in the time series, and predicts the future periodic growth process of cracks based on the fusion result.

[0012] A fission verification module, which is used to inject the prediction result of the fission prediction module into the three-dimensional model of the seal in reverse, simulate and verify the crack propagation path, automatically update the verified parameters to each functional module, and integrate the prediction results submitted by the fission prediction module within a preset number of cycles as a monitoring report.

[0013] Furthermore, a sub-module is deployed at the lower level of the detection planning unit. The sub-module includes a node recognition module, a positioning generation module, and a path planning module. The node recognition module and the positioning generation module are interconnected through a wireless network, and the positioning generation module and the path planning module are interconnected through a wireless network, where: The node recognition module is used to capture the sealed nodes with resistance fluctuations exceeding the preset range, evaluate the influence of the sealed nodes through the current path and the distribution of heat and cold flows, and mark the sealed nodes whose abnormal fluctuation influence meets the marking standard during the current monitoring period as key nodes.

[0014] The positioning generation module is used to select the optimal infrared detection points for the key nodes through the quantum annealing optimization algorithm. The points cover the key nodes and their neighborhoods within the preset scale and conform to the direction of the maximum thermal radiation gradient.

[0015] The path planning module is used to generate a preliminary path set based on several infrared detection points provided by the positioning generation module, and receive manual active modification to generate a final path set.

[0016] Furthermore, the power supply operation status data collected by the model construction module includes: current, voltage, operating temperature of the specified cable section, cable layer structure, geometric features, and physical properties.

[0017] Furthermore, the working logic of the lead seal three-dimensional model constructed by the model construction module is as follows: calculate the Joule heat distribution through the current path distribution, correct the heat source model by combining real-time temperature monitoring data to generate a dynamic temperature field, and iteratively update the thermal stress distribution of each node according to the thermal conductivity coefficients of the cable layer metal sheath, insulation layer, and lead seal layer; based on the resistivity temperature coefficient of the lead seal material, calculate the node resistance value in real time, quantify the influence coefficients of local deformation on the conductor cross-sectional area and path length, and update the resistance calculation result.

[0018] Furthermore, in the judgment stage of the trend monitoring module, its initial warning threshold is set based on the material fatigue characteristics, and the threshold bandwidth is customized and adjusted in combination with historical working condition data. If the slope exceeds the threshold for 3 consecutive cycles and the curvature mutation degree reaches the preset standard mutation degree, another classification warning is triggered and submitted to the instruction management module.

[0019] Furthermore, during the defect detection process of the defect assessment module, based on the final path set generated by the detection planning unit, capture the surface temperature field distribution of the lead seal, identify local overheating areas, penetrate the cable layer structure, detect internal air gaps or cracks in the lead seal, combine the resistance fluctuation trend, locate the current leakage or electromagnetic anomaly areas, and through timestamp synchronization and spatial coordinate mapping, unify the infrared hot spots, ultrasonic reflection signals, and electromagnetic field intensity into the lead seal three-dimensional model coordinate system, weight the confidence of the three types of data, extract fusion features, perform feature classification based on the fusion features, identify annular cracks, axial cracks, punctiform corrosion, closed cracks, open cracks, and delamination defects, and based on the comprehensive classification results, output the final defect type label, and conduct a comprehensive assessment based on the severity coefficient, risk diffusion coefficient, and emergency intervention index, and output the defect performance coefficient.

[0020] Furthermore, the defect performance coefficient obtained by the defect assessment module is cross-validated with the resistance change trend obtained by the trend monitoring module. When the deviation between the two exceeds 15%, a re-detection protocol is triggered, and a correction instruction is submitted to the detection planning unit. After the correction instruction passes, a detection path is regenerated and data is collected again.

[0021] Furthermore, the calculation formula for the fission prediction module to predict the future cycle growth process of cracks is: ; in the above formula, represents the predicted crack growth amount at time point , represents the time increment, indicating the predicted future time interval, represents the fusion index tensor, represents the norm order, represents the material impedance coefficient, represents any instantaneous moment in the time process, represents the predicted start time point, Represents the instantaneous change rate of the defect fusion index F at time , represents the time differential element, indicating the contribution of the micro-variation of the defect state, represents the activation function, represents the total number of environmental coupling parameters, represents the i-th environmental coupling parameter, indicating the weights of several environmental factors, represents the i-th environmental impact factor, indicating the quantification index of the specific environmental conditions at time point . represents the exponential function.

[0022] Furthermore, the instruction management module is connected to the distribution module through wireless network interaction. The distribution module is used to provide authentication to the control ends of each cable section in the current cycle. The control ends that pass the authentication obtain the dynamic allocation instructions for each cable section from the instruction management module, and submit the feedback data of each control end to the instruction management module as the target within a preset time.

[0023] Furthermore, the instruction management module is connected to the model construction module through wireless network interaction, the model construction module is connected to the trend monitoring module through wireless network interaction, the trend monitoring module is connected to the detection planning unit through wireless network interaction, the detection planning unit is connected to the defect assessment module through wireless network interaction, the defect assessment module is connected to the fission prediction module through wireless network interaction, and the fission prediction module is connected to the fission verification module through wireless network interaction.

[0024] (3) Beneficial effects: By adopting the technical solution provided by the present invention, compared with the known prior art, the following beneficial effects are achieved. 1. By constructing a three-dimensional model of the lead seal, the system is allowed to dynamically adjust the model under various operating conditions, making the monitoring more accurate, being able to reflect the real state of the cable in real time, avoiding misjudgment, improving the recognition accuracy of abnormal resistance fluctuations, giving early warnings of potential faults, and reducing the risk of accidents.

[0025] 2. By capturing and marking the abnormal states of several nodes of the specified cable section, multi-dimensional analysis is provided for the evaluation of key nodes, and small changes can also be sensitively captured, ensuring that the system can timely identify the nodes that have the greatest impact on the occurrence of defects, thereby conducting targeted monitoring, improving the accuracy rate of defect early warning, fusing and evaluating the monitoring data. In the case of small samples, the system can maintain a high accuracy rate, effectively integrating data such as thermal imaging and ultrasonic waves, analyzing the defect characteristics and change trends, and enhancing the fault detection ability.

[0026] 3. Generate an efficient detection path through an optimized algorithm, improve the path planning efficiency, shorten the detection time, ensure the maximization of the detection coverage, avoid external environmental interference at the same time, enhance the reliability of the data, predict crack propagation more accurately through a more accurate model, and dynamically adjust parameters, significantly improving the prediction accuracy to help maintenance personnel prepare countermeasures in advance. Brief Description of the Drawings

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0028] Figure 1 It is a framework schematic diagram of the high-voltage cable lead seal defect monitoring system based on resistance value of the present invention.

[0029] Figure 2 It is a framework schematic diagram of the detection planning unit in the present invention.

[0030] The reference numerals in the figure respectively represent: 1. Instruction management module; 2. Model construction module; 3. Trend monitoring module; 4. Detection planning unit; 41. Node identification module; 42. Positioning generation module; 43. Path planning module; 5. Defect evaluation module; 6. Fission prediction module; 7. Fission verification module; 8. Allocation module. Detailed Embodiments

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0032] The following further describes the present invention with reference to the embodiments.

[0033] Embodiment 1: A high-voltage cable lead seal defect monitoring system based on resistance value in this embodiment, as Figure 1 and Figure 2As shown in the figure, it includes: an instruction management module 1, which is used to connect to the power transmission grid of the cable, obtain the acquisition authority of the power supply operation status data, and edit and send control instructions to each functional module; the instruction management module 1 is connected to a distribution module 8 through wireless network interaction. The distribution module 8 is used to provide identity authentication to the control ends of each cable segment in the current cycle. The control ends that pass the authentication obtain the dynamic allocation instructions for each cable segment from the instruction management module 1, and centrally submit the feedback data of each control end to the instruction management module 1 within a preset time.

[0034] A model construction module 2 is used to collect the operation parameters of several lead seal nodes and associated cables in a specified cable segment in real time, integrate them into power supply operation status data, and construct a three-dimensional lead seal model; the power supply operation status data includes: current, voltage, operating temperature of the specified cable segment, cable layer structure, geometric features, and physical properties.

[0035] The working logic of the three-dimensional lead seal model is as follows: calculate the Joule heat distribution through the current path distribution, correct the heat source model by combining real-time temperature monitoring data, generate a dynamic temperature field, and iteratively update the thermal stress distribution of each node according to the heat conduction coefficients of the metal sheath, insulation layer, and lead seal layer of the cable layer.

[0036] Based on the resistivity temperature coefficient of the lead seal material, the node resistance value is calculated in real time, the influence coefficients of local deformation on the conductor cross-sectional area and path length are quantified, and the resistance calculation result is updated.

[0037] A trend monitoring module 3 is used to input the real-time power supply operation status data of the current cable segment into the three-dimensional lead seal model, output the resistance change trends of several lead seal nodes, set an early warning threshold, and judge whether there is a resistance fluctuation exceeding the preset range in the resistance change trend of a certain node; during the judgment stage of the trend monitoring module 3, its initial early warning threshold is set based on the material fatigue characteristics, and the threshold bandwidth is customized and adjusted in combination with historical working condition data. If the slope exceeds the threshold for 3 consecutive cycles and the curvature mutation degree reaches the preset standard mutation degree, another hierarchical early warning is triggered and submitted to the instruction management module 1; the setting of the early warning threshold is based on the material fatigue characteristics and historical working condition data, and can be customized and adjusted, thus enhancing the flexibility and reliability of the system under different working conditions. Compared with the traditional monitoring technology with a fixed threshold, this mechanism greatly improves the accuracy of early warning.

[0038] A detection planning unit 4 is used to capture the key nodes in the cable segment with abnormal resistance fluctuations, generate infrared detection points based on the key nodes, and generate the best defect detection path.

[0039] The detection planning unit 4 is subordinate to sub-modules. The sub-modules include a node recognition module 41, a positioning generation module 42, and a path planning module 43. The node recognition module 41 and the positioning generation module 42 are interconnected through a wireless network, and the positioning generation module 42 and the path planning module 43 are interconnected through a wireless network. Among them: The node recognition module 41 is used to capture the sealed nodes with resistance fluctuations beyond the preset range, evaluate the influence of the sealed nodes through the current path and the cold and heat flow distribution, and mark the sealed nodes with abnormal fluctuation influence that meet the marking standard during the current monitoring period as key nodes.

[0040] The positioning generation module 42 is used to select the optimal infrared detection points for the key nodes through the quantum annealing optimization algorithm. The points cover the key nodes and their neighborhoods with a preset scale and conform to the maximum thermal radiation gradient direction.

[0041] The path planning module 43 is used to generate a preliminary path set based on several infrared detection points provided by the positioning generation module 42 and receive manual active modification to generate a final path set.

[0042] The defect evaluation module 5 is used to detect the defects in the sealed area through the best defect detection path, obtain multi-modal defect data, fuse and classify them, and evaluate the defect performance coefficients of several nodes.

[0043] The fission prediction module 6 is used to coherently fuse the defect performance coefficients in the time series and predict the future periodic growth process of the crack based on the fusion result.

[0044] The fission verification module 7 is used to reverse-inject the prediction result of the fission prediction module 6 into the three-dimensional model of the seal, simulate and verify the crack propagation path, automatically update the verified parameters to each functional module, and integrate the prediction results submitted by the fission prediction module 6 within a preset number of cycles as a monitoring report.

[0045] The instruction management module 1 and the model construction module 2 are interconnected through a wireless network, the model construction module 2 and the trend monitoring module 3 are interconnected through a wireless network, the trend monitoring module 3 and the detection planning unit 4 are interconnected through a wireless network, the detection planning unit 4 and the defect evaluation module 5 are interconnected through a wireless network, the defect evaluation module 5 and the fission prediction module 6 are interconnected through a wireless network, and the fission prediction module 6 and the fission verification module 7 are interconnected through a wireless network.

[0046] Compared with the prior art, collecting various operating parameters of the cable segment in real time and using them to construct a 3D model of the lead seal improves the response speed and accuracy of the cable operating state, enabling the timely detection of potential defects. By calculating the Joule heat distribution and correcting the heat source model, the system can dynamically generate the temperature field and update the thermal stress distribution, providing a more accurate characterization of the cable's thermal dynamic behavior and its impacts. Compared with the static model, it offers a more comprehensive monitoring ability.

[0047] Capturing the nodes with abnormal resistance fluctuations in real time and marking them ensures a rapid response to potential problems, enabling the system to focus on high-risk areas, thereby reducing the risks of false alarms and missed alarms. Selecting the best detection points to ensure that the infrared detection covers the key nodes and their neighborhoods, meeting the maximum thermal radiation gradient, optimizes the traditional detection method and improves the efficiency and accuracy of defect detection.

[0048] Fusing and classifying the data collected from various detection methods helps to form a more comprehensive evaluation of the defect manifestation coefficient, integrating the advantages of different types of data and providing more accurate detection results. By performing time series fusion on the defect manifestation coefficient and predicting the growth process of the crack in the future cycle, the dynamic monitoring of the cable's health state is achieved, enabling the maintenance personnel to take measures in advance and reducing the downtime and maintenance costs.

[0049] Example 2: On other levels, this example also provides a calculation formula for predicting the growth process of the crack in the future cycle. The calculation formula for predicting the growth process of the crack in the future cycle is: ; In the above formula, represents the predicted crack growth amount at time point , usually the length or depth of the crack, represents the time increment, indicating the predicted future time interval, represents the fusion index tensor, including three-dimensional features of spatial position, defect intensity, and propagation tendency, represents the norm order, represents the material impedance coefficient, represents any instantaneous moment in the time process, represents the predicted starting time point, represents the instantaneous change rate of the defect fusion index F at time , represents the time differential element, indicating the contribution of the micro change in the defect state, represents the activation function, used for non-linear adjustment and conversion of the output range, represents the total number of environmental coupling parameters, represents the i-th environmental coupling parameter, indicating the weights of several environmental factors, represents the i-th environmental impact factor, indicating at time point Quantification indices of specific environmental conditions represents the modulus or length under the norm, reflecting the intensity and comprehensive influence of the current defect manifestation represents the exponential function, indicating the non-linear characteristics of the crack length or depth growth process

[0050] Crack growth amount is based on the current state and environmental influence to predict the future growth state of the crack. Using to calculate the performance of the current defect under a specific norm is to quantify the strength of the influence. The material impedance coefficient divided by the modulus length is to consider the characteristics of the material, the ability to affect crack propagation. The exponential integral part describes the time evolution of the defect manifestation and models the influence process on future crack propagation. The environmental coupling parameter and influence factor then make the model adapt to the crack growth behavior occurring under different environmental conditions

[0051] Example 3: In this example, a process for defect detection is provided, specifically: Based on the final path set generated by the detection planning unit 4, control the mobile detection device equipped with an infrared thermal imager, an ultrasonic flaw detector, and an electromagnetic sensor to scan along the key path points such as the direction of the maximum thermal radiation gradient, capture the surface temperature field distribution of the lead seal, identify local overheating areas, penetrate the cable layer structure, detect air gaps or cracks inside the lead seal, combine the resistance fluctuation trend, locate the current leakage or electromagnetic anomaly areas, through timestamp synchronization and spatial coordinate mapping, unify the infrared hot spot spatial resolution of 0.5 mm, the ultrasonic reflection signal accuracy of ±0.1 mm, and the electromagnetic field strength sensitivity of 1 μT to the lead seal three-dimensional model coordinate system, weight the confidence of the three types of data, extract fusion features, specifically the coupling index of the temperature gradient and the ultrasonic attenuation rate, the phase difference between the resistance volatility and the magnetic field distortion, and the degree of multi-parameter deviation from the normal working condition calculated based on the Mahalanobis distance. Based on the fusion features, perform feature classification to identify circular cracks, axial cracks, pitting corrosion, closed cracks, open cracks, and delamination defects. Integrate the classification results, output the final defect type label, and perform a comprehensive evaluation based on the severity coefficient, risk diffusion coefficient, and emergency intervention index to output the defect manifestation coefficient

[0052] The severity coefficient is specifically the Z-score standardization weighting of the crack depth, temperature anomaly value, and resistance offset, with a weight ratio of 4:3:3; the risk diffusion coefficient is specifically: calculating the crack edge roughness based on the fractal dimension and predicting the expansion tendency by combining heat flux simulation; the emergency intervention index is specifically: balancing the maintenance cost and failure probability through the NSGA-II multi-objective optimization algorithm, and outputting a 0-1 standardized value to ensure that the entire process from data collection to coefficient evaluation is completed within a typical value of 5 minutes in a single monitoring cycle.

[0053] Working principle: The instruction management module 1 is responsible for connecting to the power grid and permission management, the model construction module 2 collects data, the trend monitoring module 3 analyzes the resistance trend, the detection planning unit 4 processes abnormal nodes, the defect evaluation module 5 detects defects, the fission prediction module 6 performs time series prediction, the fission verification module 7 conducts simulation verification, and the allocation module 8 is responsible for identity verification.

[0054] By collecting key operating parameters such as current and temperature in real time and establishing a three-dimensional model of the lead seal, the dynamic monitoring and abnormal warning of the cable status are realized, improving the response speed and accuracy of the system. Secondly, by introducing the quantum annealing optimization algorithm, the system can efficiently select infrared detection points to ensure the comprehensiveness and accuracy of defect detection.

[0055] In addition, the defect manifestation coefficient is used for time series coherent fusion to predict the future growth process of cracks, enhancing the preventive maintenance ability of the system, reducing the risk of potential damage. The intelligent parameter update and monitoring report integration functions of the system improve the data processing efficiency, provide a reliable basis for subsequent decision-making, and promote the safe operation of high-voltage cables.

[0056] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A high-voltage cable lead seal defect monitoring system based on resistance value, characterized in that, Including: An instruction management module, which is used to connect to the power transmission grid of the cable, obtain the acquisition permission of the power supply operation status data, and edit and send the control instructions of each functional module; A model construction module, which is used to collect the operation parameters of several lead seal nodes and associated cables in a specified cable section in real time, integrate them into power supply operation status data, and construct a three-dimensional lead seal model; A trend monitoring module, which is used to input the real-time power supply operation status data of the current cable section into the three-dimensional lead seal model, output the resistance change trends of several lead seal nodes, set an early warning threshold, and judge whether there is a resistance fluctuation beyond the preset range in the resistance change trend of a certain node; A detection planning unit, which is used to capture the key nodes in the cable section with abnormal resistance fluctuations, generate infrared detection points according to the key nodes, and generate the optimal defect detection path; A defect evaluation module, which is used to detect defects in the lead seal area through the optimal defect detection path, obtain multi-modal defect data and fuse and classify them, and evaluate the defect performance coefficients of several nodes; A fission prediction module, which is used for coherent fusion of defect performance coefficients in the time series, and predicts the future periodic growth process of cracks based on the fusion result; A fission verification module, which is used to reverse inject the prediction result of the fission prediction module into the three-dimensional lead seal model, simulate and verify the crack propagation path, automatically update the verified parameters to each functional module, and integrate the prediction results submitted by the fission prediction module within a preset number of cycles as a monitoring report; A sub-module is deployed under the detection planning unit. The sub-module includes a node identification module, a positioning generation module, and a path planning module. The node identification module and the positioning generation module are connected through wireless network interaction, and the positioning generation module and the path planning module are connected through wireless network interaction, where: The node identification module is used to capture the lead seal nodes with resistance fluctuations exceeding the preset range, evaluate the influence of the lead seal nodes through the current path and the distribution of heat and cold flows, and mark the lead seal nodes whose abnormal fluctuation influence meets the marking standard during the current monitoring period as key nodes; The positioning generation module is used to select the optimal infrared detection points for the key nodes through the quantum annealing optimization algorithm. The points cover the key nodes and their neighborhoods with a preset scale and conform to the direction of the maximum thermal radiation gradient; The path planning module is used to generate a preliminary path set based on several infrared detection points provided by the positioning generation module, and receive manual active modification to generate a final path set; The working logic of the three-dimensional lead seal model constructed by the model construction module is as follows: Calculate the Joule heat distribution through the current path distribution, correct the heat source model in combination with the real-time temperature monitoring data, generate a dynamic temperature field, and iteratively update the thermal stress distribution of each node according to the thermal conductivity coefficients of the cable layer metal sheath, insulation layer, and lead seal layer; Based on the resistivity temperature coefficient of the lead seal material, calculate the node resistance value in real time, quantify the influence coefficients of local deformation on the conductor cross-sectional area and path length, and update the resistance calculation result.

2. The high-voltage cable lead seal defect monitoring system based on resistance value according to claim 1, wherein The power supply operation status data collected by the model construction module includes: current, voltage, operating temperature of the specified cable section, cable layer structure, geometric features, and physical properties.

3. The high-voltage cable lead seal defect monitoring system based on resistance value according to claim 1, characterized in that During the judgment phase, the initialization warning threshold of the trend monitoring module is set based on the fatigue characteristics of the material, and the threshold bandwidth is customized by combining historical working condition data. If the slope exceeds the threshold for 3 consecutive cycles and the curvature mutation degree reaches the preset standard mutation degree, another level of warning is triggered and submitted to the instruction management module.

4. A high-voltage cable lead seal defect monitoring system based on resistance value according to claim 1, characterized in that, During the defect detection process of the defect assessment module, based on the final path set generated by the detection planning unit, the surface temperature field distribution of the seal is captured, local overheating areas are identified, the cable layer structure is penetrated, air gaps or cracks inside the seal are detected, and the current leakage or electromagnetic anomaly areas are located by combining the resistance fluctuation trend. Through timestamp synchronization and spatial coordinate mapping, the infrared hot spots, ultrasonic reflection signals, and electromagnetic field intensities are unified into the three-dimensional model coordinate system of the seal, the confidence levels of the three types of data are weighted, fusion features are extracted, and feature classification is performed based on the fusion features to identify annular cracks, axial cracks, punctiform corrosion, closed cracks, open cracks, and delamination defects. Based on the comprehensive classification results, the final defect type label is output, and a comprehensive evaluation is performed based on the severity coefficient, risk diffusion coefficient, and emergency intervention index, and the defect performance coefficient is output.

5. A high-voltage cable lead seal defect monitoring system based on resistance value according to claim 1, characterized in that, The defect performance coefficient obtained by the defect assessment module and the resistance change trend obtained by the trend monitoring module are cross-validated. When the deviation between the two exceeds 15%, a re-detection protocol is triggered, and the detection planning unit is submitted to trigger a correction instruction. After the correction instruction passes, a detection path is regenerated and data is collected again.

6. The high-voltage cable lead seal defect monitoring system based on resistance value according to claim 1, characterized in that The calculation formula for the fission prediction module to predict the future periodic growth process of cracks is as follows: ; In the above formula, represents the predicted crack growth amount at the time point , represents the time increment, indicating the predicted future time interval, represents the fusion index tensor, represents the norm order, represents the material impedance coefficient, represents any instantaneous moment in the time process, represents the starting time point of prediction, represents the instantaneous change rate of the defect fusion index F at the moment , represents the time differential element, indicating the contribution of the micro-variation of the defect state, represents the activation function, represents the total number of environmental coupling parameters, represents the i-th environmental coupling parameter, indicating the weights of several environmental factors, represents the i-th environmental impact factor, indicating the quantification index of the specific environmental conditions at the time point , represents the exponential function.

7. A high-voltage cable lead seal defect monitoring system based on resistance value according to claim 1, characterized in that, The instruction management module is wirelessly connected to a distribution module. The distribution module is used to provide identity verification to the control ends of each cable segment in the current cycle. The control ends that pass the verification obtain the dynamic distribution instructions for each cable segment from the instruction management module, and the feedback data of each control end is centrally submitted to the instruction management module within a preset time.

8. The high-voltage cable lead seal defect monitoring system based on resistance value according to claim 1, characterized in that The instruction management module is wirelessly connected to the model construction module, the model construction module is wirelessly connected to the trend monitoring module, the trend monitoring module is wirelessly connected to the detection planning unit, the detection planning unit is wirelessly connected to the defect assessment module, the defect assessment module is wirelessly connected to the fission prediction module, and the fission prediction module is wirelessly connected to the fission verification module.

Images