Device and method for testing penetration of power pipeline

Abstract

The invention relates to the technical field of direct current transmission detection, in particular to a device and method for testing power pipeline connection, and the device comprises a power parameter collection module which is used for collecting current signals and voltage signals in a power pipeline, measuring temperature values at a plurality of positions, obtaining insulation resistance at each node, and measuring grounding resistance of a plurality of grounding points; and summarizing the measurement data to generate an electric power parameter set. According to the invention, through integration and analysis of measurement data of current, voltage, temperature, insulation resistance and grounding resistance, comprehensive monitoring and evaluation of the state of the power pipeline are realized. After the data are integrated, by calculating the mean value, the variance and the peak value of the data and analyzing the spatial distribution of the temperature and the frequency characteristics of the grounding resistance, the understanding of the behavior of the power system is enhanced. According to the data analysis mode, the prediction capability of potential risks and the sensitivity of fault detection are improved, and serious equipment faults and service interruption are effectively avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of direct current power transmission detection, and in particular to a device and method for testing the penetration of a power pipeline. Background Art

[0002] Power pipelines are a common type of component in various electrical equipment. Due to the inevitable plugging and unplugging, bending, vibration, pulling, aging and other reasons during use, it is very easy to cause damage to the wires, which requires the use of measuring devices for detection.

[0003] However, existing technologies mainly rely on physical inspections and simple fault diagnosis methods, which have difficulty capturing subtle changes caused by aging, environmental impacts, or improper operation of power lines. When dealing with complex or hidden faults, it is difficult to detect problems in a timely manner, such as tiny cracks or insulation degradation inside power lines, until these problems are seriously identified when they affect performance. This reactive maintenance strategy increases operating costs and may cause significant economic losses and safety accidents due to sudden power outages. The shortcomings of existing technologies in predictive maintenance and risk management cannot meet the needs of highly automated and intelligent modern power systems. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a device and method for testing the penetration of power pipelines.

[0005] In order to achieve the above object, the present invention adopts the following technical solution: A device for testing the penetration of a power pipeline comprises: The power parameter acquisition module is used to collect current signals and voltage signals in the power pipeline, measure temperature values ​​at multiple locations, obtain insulation impedance at each node, measure grounding resistance at multiple grounding points, summarize the measurement data, and generate a power parameter set; A signal feature extraction module, used to calculate the mean, variance and peak value of the current data and the voltage data based on the power parameter set, analyze the spatial distribution characteristics of the temperature value, extract the change trend of the insulation impedance, calculate the frequency characteristics of the ground resistance, and obtain the signal feature set; A weight calculation module is used to count the value range of each signal feature based on the signal feature set; calculate the frequency of occurrence of each signal feature; obtain the probability distribution of the signal feature; calculate the information entropy of each signal feature, calculate the weight value based on the information entropy, normalize each signal feature, and generate a feature weight set; A continuity assessment module is used to multiply each feature in the signal feature set by the corresponding weight based on the feature weight set to obtain a weighted feature value; summarize the weighted feature values ​​to obtain a total weighted value, and compare the total weighted value with a standard threshold; determine the continuity of the power pipeline, record the determination result, and obtain a continuity assessment result; The decision support module is used to analyze the continuity change trend based on the continuity assessment results and the historical data of the power pipeline; evaluate the risk level of the power pipeline according to the continuity change trend, generate maintenance suggestions, and output decision suggestions.

[0006] Preferably, the power parameter acquisition module includes: The electric signal acquisition submodule is used to collect real-time current signals based on power pipelines, connect current sensors at each key node, record the current value collected each time, collect real-time voltage signals using voltage sensors, record the voltage value collected each time, organize current values ​​and voltage values, and generate electric signal data sets; The temperature and impedance measurement submodule is used to use a temperature probe to contact at multiple locations, measure the temperature value at each location, record the temperature result at each location, connect at each node through an insulation tester, obtain the insulation impedance value of the node, record the insulation impedance data, use a ground resistance meter to connect at the grounding point, measure the ground resistance value, record the ground resistance data, organize the temperature value and the ground resistance data, and generate an environmental parameter set; The data aggregation submodule is used to merge the current data, voltage data, temperature data, insulation impedance data and ground resistance data based on the electrical signal data set and the environmental parameter set, organize them into a unified data format, and generate an electric power parameter set.

[0007] Preferably, the signal feature extraction module includes: A statistical feature calculation submodule, for calculating the mean, variance and peak value of the current data based on the power parameter set, recording the calculation results, calculating the mean, variance and peak value of the voltage data, recording the calculation results, arranging the statistical features of the current and voltage, and generating a statistical feature set of the electric signal; A trend analysis submodule is used to analyze the distribution of temperature data at each location based on the environmental parameter set, identify the temperature change law, extract the change trend of insulation impedance data, calculate the frequency characteristics of ground resistance data, organize the analysis results, and generate an environmental parameter feature set; The feature integration submodule is used to match the electrical signal features with the environmental features based on the electrical signal statistical feature set and the environmental parameter feature set, integrate the feature data, form a complete feature set, and obtain the signal feature set.

[0008] Preferably, the weight calculation module includes: A feature statistics submodule is used to count the value range of each feature, calculate the frequency of occurrence of each signal feature, sort the statistical data, and generate a feature statistics set based on the signal feature set; An information entropy calculation submodule is used to calculate the information entropy value of each signal feature based on the feature statistical set, record the calculation result, calculate the initial weight according to the information entropy value, and generate an initial weight set; The weight normalization submodule is used to normalize the initial weights based on the initial weight set, adjust the proportional relationship of the weight values, make the total weight equal to one, and generate a feature weight set.

[0009] Preferably, the connectivity assessment module includes: A weighted feature calculation submodule, for multiplying each feature value in the signal feature set by the corresponding weight based on the feature weight set, calculating the weighted feature value, recording the calculation result, and generating a weighted feature set; A total weighted value calculation submodule is used to add the weighted feature values ​​based on the weighted feature set to obtain a total weighted value, record the total weighted value, and generate a total weighted value result; The continuity judgment submodule is used to compare the total weighted value with the standard threshold based on the total weighted value result; judge the continuity status of the power pipeline, record the judgment result, and obtain the continuity evaluation result.

[0010] Preferably, the decision support module includes: The trend analysis submodule is used to arrange the continuity results in chronological order based on the continuity assessment results and the historical data of the power pipeline, analyze the trend of continuity changes, identify abnormal change points, and generate continuity trend analysis results.

[0011] Preferably, the decision support module further includes: A risk assessment submodule, for assessing the current risk level of the power pipeline based on the continuity trend analysis result, identifying potential risk factors, determining the risk level classification, and generating a risk assessment result; The suggestion generation submodule is used to formulate corresponding maintenance measures, write maintenance suggestions, and output decision suggestions based on the risk assessment results.

[0012] The present invention provides a device and method for using the method for testing the continuity of a power pipeline, comprising the following steps: Collect current signals and voltage signals in power pipelines, measure temperature values ​​at multiple locations, obtain insulation impedance at each node, measure grounding resistance at multiple grounding points, summarize measurement data, and generate power parameter sets; Based on the power parameter set, the mean, variance and peak value of the current data and the voltage data are calculated, the spatial distribution characteristics of the temperature value are analyzed, the variation trend of the insulation impedance is extracted, the frequency characteristics of the grounding resistance are calculated, and the signal feature set is obtained; Based on the signal feature set, count the value range of each signal feature; calculate the frequency of occurrence of each signal feature; obtain the probability distribution of the signal feature; calculate the information entropy of each signal feature, calculate the weight value based on the information entropy, normalize each signal feature, and generate a feature weight set; Based on the feature weight set, each feature in the signal feature set is multiplied by the corresponding weight to obtain a weighted feature value; the weighted feature values ​​are summarized to obtain a total weighted value, and the total weighted value is compared with a standard threshold; the continuity of the power pipeline is judged, the judgment result is recorded, and the continuity assessment result is obtained; Based on the continuity assessment results, combined with the historical data of the power pipeline, the continuity change trend is analyzed; according to the continuity change trend, the risk level of the power pipeline is evaluated, maintenance suggestions are generated, and decision suggestions are output.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, comprehensive monitoring and evaluation of the power pipeline status is achieved by integrating and analyzing the measurement data of current, voltage, temperature, insulation impedance and ground resistance. After integrating these data, the understanding of the behavior of the power system is enhanced by calculating the mean, variance and peak value of the data, and analyzing the spatial distribution of temperature and the frequency characteristics of ground resistance. This data analysis method improves the ability to predict potential risks and the sensitivity of fault detection, effectively avoiding serious equipment failures and service interruptions. This strategy significantly improves the efficiency of preventive maintenance and the operational safety of the system, ensures real-time and dynamic monitoring, and has a higher effect than traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0016] See also Figure 1 The present invention provides a technical solution: a device for testing the continuity of a power pipeline comprises: The power parameter acquisition module is used to collect current signals in the power pipeline using current sensors, collect voltage signals using voltage sensors, measure temperature values ​​at multiple locations using temperature probes, obtain insulation impedance at each node using insulation testers, measure grounding resistance at multiple grounding points using ground resistance meters, summarize measurement data, and generate a power parameter set; The signal feature extraction module is used to calculate the mean, variance and peak value of the current data and voltage data based on the power parameter set, analyze the spatial distribution characteristics of the temperature value, extract the change trend of the insulation impedance, calculate the frequency characteristics of the grounding resistance, integrate each analysis result, and obtain the signal feature set; The weight calculation module is used to count the value range of each signal feature based on the signal feature set; calculate the frequency of occurrence of each signal feature; obtain the probability distribution of the signal feature; calculate the information entropy of each signal feature, calculate the weight value based on the information entropy, normalize each signal feature, and generate a feature weight set; The continuity assessment module is used to multiply each feature in the signal feature set by the corresponding weight based on the feature weight set to obtain a weighted feature value; summarize the weighted feature values ​​to obtain a total weighted value, and compare the total weighted value with the standard threshold; judge the continuity of the power pipeline, record the judgment result, and obtain the continuity assessment result; The decision support module is used to analyze the trend of connectivity changes based on the connectivity assessment results and the historical data of the power pipelines; evaluate the risk level of the power pipelines according to the connectivity change trend, generate maintenance recommendations, and output decision recommendations.

[0017] Specifically, by integrating and analyzing the measurement data of current, voltage, temperature, insulation impedance and ground resistance, comprehensive monitoring and evaluation of the power pipeline status is achieved. After integrating these data, the understanding of the behavior of the power system is enhanced by calculating the mean, variance and peak value of the data, and analyzing the spatial distribution of temperature and the frequency characteristics of ground resistance. This data analysis method improves the ability to predict potential risks and the sensitivity of fault detection, effectively avoiding serious equipment failures and service interruptions. This strategy significantly improves the efficiency of preventive maintenance and the operational safety of the system, ensuring real-time and dynamic monitoring, and is more effective than traditional methods.

[0018] In this embodiment, the power parameter acquisition module includes: The electrical signal acquisition submodule is based on the power pipeline. It uses current sensors to connect at each key node to collect real-time current signals and record the current value collected each time. It uses voltage sensors to collect real-time voltage signals and record the voltage value collected each time. It organizes the current and voltage values ​​to generate an electrical signal data set. The temperature and impedance measurement submodule uses a temperature probe to contact at multiple locations, measures the temperature value at each location, records the temperature result at each location, connects at each node through an insulation tester, obtains the insulation impedance value of the node, records the insulation impedance data, uses a ground resistance meter to connect at the grounding point, measures the ground resistance value, records the ground resistance data, organizes the temperature value and ground resistance data, and generates an environmental parameter set; The data aggregation submodule combines the current data, voltage data, temperature data, insulation impedance data and ground resistance data based on the electrical signal data set and the environmental parameter set, organizes them into a unified data format, and generates an electric power parameter set.

[0019] The power parameter set includes current readings at each measuring point of the power pipeline, voltage readings at each measuring point of the power pipeline, temperature data of the power pipeline, insulation resistance measurement results of each node, and ground resistance measurement results of each grounding point.

[0020] Specifically, the electrical signal acquisition submodule uses current sensors to connect at each key node based on the power pipeline. The key nodes need to be determined in combination with field research and the opinions of power engineering experts. They are generally access points equipped with important power equipment such as transformers or circuit breakers, or areas with high requirements for power quality and supply stability. The installation of current sensors and voltage sensors should be strictly in accordance with the standard interface of the power system to ensure accurate signal transmission and high efficiency of acquisition. During the data acquisition process of current and voltage, data verification is implemented to ensure that each data point is accurate and has no abnormal fluctuations. For current data, the detection range is set from 0 to the maximum load current. Readings beyond this range should automatically alarm and record abnormalities. A reasonable detection range is also set for voltage. The detection range of the voltage sensor should cover the normal voltage fluctuation range in the power system. For a system with a rated voltage of 380 volts, the voltage sensor needs to detect a range from 340 volts to 420 volts; for the voltage value of each detection cycle, average processing should be performed to reduce the impact of instantaneous fluctuations. All collected current and voltage data will be further sorted to generate an electrical signal data set. Through the improved data sorting process, the electrical signal data are sorted in time series, and necessary statistical analysis is performed, such as calculating the mean and variance of the current and voltage at each time point, providing a basis for subsequent data processing and analysis.

[0021] The temperature and impedance measurement submodule uses a temperature probe to contact at multiple locations, measures the temperature value at each location, records the temperature results at each location, connects at each node through an insulation tester, obtains the insulation impedance value of the node, records the insulation impedance data, uses a ground resistance meter to connect at the grounding point, measures the ground resistance value, and records the ground resistance data. The temperature probe needs to be calibrated regularly to ensure the accuracy of the temperature reading. During the measurement of insulation resistance and ground resistance, the measuring instruments should be checked and calibrated regularly to ensure the reliability of the data. For the measured temperature and impedance data, data cleaning and outlier processing are implemented to generate an environmental parameter set. This data set will include time series analysis of the temperature and impedance of each node, as well as an assessment of the trend and periodic changes of the data, providing an important reference for the safe operation of the power system.

[0022] The data aggregation submodule combines the current data, voltage data, temperature data, insulation impedance data, and ground resistance data based on the electrical signal data set and the environmental parameter set, organizes them into a unified data format, and generates an electric power parameter set. During the data aggregation process, the network time protocol (NTP) or GPS clock is used to synchronize all sensors and measuring instruments to ensure that each data point has a consistent timestamp, so that data from different sensors and measuring instruments can correspond to the same collection time. Then, data cleaning is performed to remove invalid, erroneous, or abnormal data points, improve the quality and availability of data, ensure that data from different sensors and measuring instruments can accurately correspond, and perform time synchronization. Data compression technology is applied to optimize storage space and improve data transmission efficiency.

[0023] In this embodiment, the signal feature extraction module includes: The statistical feature calculation submodule calculates the mean, variance and peak value of the current data based on the power parameter set, records the calculation results, calculates the mean, variance and peak value of the voltage data, records the calculation results, organizes the statistical features of the current and voltage, and generates a statistical feature set of the electrical signal; The trend analysis submodule analyzes the distribution of temperature data at each location based on the environmental parameter set, identifies the temperature variation pattern, extracts the variation trend of insulation impedance data, calculates the frequency characteristics of ground resistance data, organizes the analysis results, and generates an environmental parameter feature set; The feature integration submodule matches the electrical signal features with the environmental features based on the electrical signal statistical feature set and the environmental parameter feature set, integrates the feature data, forms a complete feature set, and obtains the signal feature set.

[0024] Specifically, the statistical feature calculation submodule calculates the mean, variance and peak value of the current data based on the power parameter set, and records the calculation results. It also calculates the mean, variance and peak value of the voltage data, and records the calculation results. At this stage, in order to ensure the accuracy and efficiency of the calculation, the collected current and voltage data should first pass through a data preprocessing process, including filtering and denoising, to eliminate sensor errors and environmental interference. When calculating the mean, the weighted average method is used, where the weight is determined by the stability of the data within the cycle to improve representativeness and reduce the impact of abnormal data. Variance calculation is used to evaluate the stability and volatility of the data, which is particularly critical for load management and fault prediction of the power grid. Peak detection automatically marks extreme events that exceed the normal working range by setting thresholds. These calculation results will be recorded and used to generate a statistical feature set of electrical signals. For the mean, variance and peak value, a series test will be performed to ensure the continuity and integrity of the data, and any deviations or anomalies will be further detected and corrected through statistical models.

[0025] The trend analysis submodule analyzes the distribution of temperature data at each location based on the set of environmental parameters, identifies the temperature variation pattern, extracts the variation trend of insulation resistance data, and calculates the frequency characteristics of ground resistance data. The distribution analysis of temperature data will rely on geostatistical methods to evaluate the temperature correlation between different locations, and time series analysis to identify long-term trends and periodic changes. The trend extraction of insulation resistance is analyzed through regression analysis to analyze its relationship with environmental factors such as humidity and temperature. The frequency analysis of ground resistance uses Fourier transform to convert time domain signals into frequency domain signals to identify and classify the effects of various frequency components. These analysis results not only provide the dynamic characteristics of environmental parameters, but also help to understand the impact of environmental conditions on the stability of the power system.

[0026] The feature integration submodule matches the electrical signal features with the environmental features based on the electrical signal statistical feature set and the environmental parameter feature set, integrates the feature data, forms a complete feature set, and obtains the signal feature set. In this process, feature matching adopts a model-based approach to ensure the consistency and relevance of the data. Feature integration focuses on the multidimensional analysis of data, using principal component analysis (PCA) and clustering technology to optimize feature representation, reduce redundant data, and improve the efficiency of data processing and the accuracy of the prediction model. The integrated feature set will be stored and managed in a standardized format to ensure compatibility and scalability between different systems and applications. This method can effectively utilize the complex data of the power system and improve the accuracy of monitoring and diagnosis.

[0027] In this embodiment, the weight calculation module includes: The feature statistics submodule counts the value range of each feature based on the signal feature set, calculates the frequency of occurrence of each signal feature, organizes the statistical data, and generates a feature statistics set; The information entropy calculation submodule calculates the information entropy value of each signal feature based on the feature statistical set, records the calculation results, calculates the initial weight according to the information entropy value, and generates an initial weight set; The weight normalization submodule normalizes the initial weights based on the initial weight set, adjusts the proportional relationship of the weight values, makes the sum of the weights equal to one, and generates a feature weight set.

[0028] Specifically, the feature statistics submodule, based on the signal feature set, counts the numerical range of each feature, calculates the frequency of occurrence of each signal feature, organizes the statistical data, and generates a feature statistics set. When executing this step, each feature data in the signal feature set will be analyzed in detail. First, the minimum and maximum values ​​of each feature will be determined, and its numerical range will be established. Subsequently, advanced statistical methods are used to calculate the frequency of occurrence of each feature in the data set to facilitate subsequent weight allocation. During the statistical process, data analysis techniques must also be applied to identify and process any outliers or deviations to ensure the accuracy and reliability of the statistical results. The statistical results will be organized and saved in the feature statistics set, which will include detailed statistical information of each feature, such as the median, mean, standard deviation, and distribution.

[0029] The information entropy calculation submodule calculates the information entropy value of each signal feature based on the feature statistics set, records the calculation results, calculates the initial weight according to the information entropy value, and generates the initial weight set. In the process of calculating the information entropy, the probability of occurrence of each feature value will be considered, and the standard information entropy formula will be used to determine the uncertainty and information content of each feature. The formula is as follows: ,in It is a feature This method can effectively evaluate the contribution of each feature in the data set. Based on the information entropy value obtained, the initial weight of each feature is calculated. This weight represents the importance of the feature in the overall data analysis. The higher the weight, the greater the information content of the feature.

[0030] The weight normalization submodule normalizes the initial weights based on the initial weight set, adjusts the proportional relationship of the weight values, makes the sum of the weights equal to one, and generates a feature weight set. The key to normalization is to ensure that the sum of all feature weights is 1, so that a balance can be maintained in the analysis model where multiple features work together. The mathematical formula for normalization is: ,in It is a feature Through this step, the weight of each feature will be adjusted to a reasonable proportion to ensure the fairness and effectiveness of the model in processing different features. The final feature weight set will include the adjusted weight values ​​of each feature, which are the result of comprehensive consideration under the premise of ensuring data integrity and analysis accuracy.

[0031] In this embodiment, the connectivity assessment module includes: The weighted feature calculation submodule multiplies each feature value in the signal feature set by the corresponding weight based on the feature weight set, calculates the weighted feature value, records the calculation result, and generates a weighted feature set; The total weighted value calculation submodule adds the weighted feature values ​​based on the weighted feature set to obtain the total weighted value, records the total weighted value, and generates the total weighted value result; The continuity judgment submodule compares the total weighted value with the standard threshold based on the total weighted value result; judges the continuity status of the power pipeline, records the judgment result, and obtains the continuity assessment result.

[0032] Specifically, the weighted feature calculation submodule, based on the feature weight set, multiplies each feature value in the signal feature set by the corresponding weight, calculates the weighted feature value, records the calculation result, and generates a weighted feature set. The main operations involved in this process include extracting the value of each feature and multiplying it by its corresponding weight. For example, if the value of a feature is And its weight is , the weighted eigenvalues ​​will be calculated as This calculation step focuses on adjusting the raw data through weights to reflect the actual impact of each feature on the final result. This process is repeated for each feature to ensure that all feature values ​​are weighted. The results are summarized and recorded in the weighted feature set to provide a data basis for the next calculation step.

[0033] The total weighted value calculation submodule adds the weighted feature values ​​based on the weighted feature set to obtain the total weighted value, records the total weighted value, and generates the total weighted value result. In this module, all weighted feature values ​​will be accumulated to form a total weighted value. , where n represents the total number of features. The total weighted value is a key data point in assessing the overall system status because it combines the weighted impact of all features. The calculated total weighted value will be recorded and used in further analysis and evaluation steps.

[0034] The connectivity judgment submodule compares the total weighted value with the standard threshold based on the total weighted value result; judges the connectivity status of the power pipeline, records the judgment result, and obtains the connectivity assessment result. At this stage, the total weighted value S will be compared with the set standard threshold T, for example, by judging S ≥ T to assess whether the power pipeline has good connectivity. If S is greater than or equal to T, it is considered that the power pipeline has good connectivity; conversely, if S is less than T, it is considered that there may be potential problems or obstacles. This method is not only fast and efficient, but can also provide real-time assessment results for maintenance and operation, helping to discover and solve problems in a timely manner.

[0035] In this embodiment, the decision support module includes: The trend analysis submodule, based on the continuity assessment results and combined with the historical data of the power pipeline, arranges the continuity results in chronological order, analyzes the trend of continuity changes, identifies abnormal change points, and generates continuity trend analysis results.

[0036] The risk assessment submodule evaluates the current risk level of the power pipeline based on the results of the continuity trend analysis, identifies potential risk factors, determines the risk level classification, and generates risk assessment results; The suggestion generation submodule formulates corresponding maintenance measures, writes maintenance suggestions, and outputs decision-making suggestions based on the risk assessment results.

[0037] Specifically, the decision support module includes: The trend analysis submodule, based on the continuity assessment results and combined with the historical data of the power pipeline, arranges the continuity results in chronological order, analyzes the trend of continuity changes, identifies abnormal change points, and generates continuity trend analysis results. When executing this process, the continuity assessment results are first integrated with the historical data set, and time series analysis techniques are used to observe and evaluate long-term trends and cyclical patterns. Special attention is paid to the fluctuations and mutations of the continuity results. The weights of historical data are balanced through statistical methods such as moving average and exponential smoothing to improve the accuracy of the prediction. In addition, anomaly detection algorithms, such as threshold-based recognition or machine learning methods, are used to identify mutation points and outliers in the data, which may indicate potential technical problems or external interference. The analysis results will record each identified abnormal point and its possible causes in detail, providing a basis for subsequent risk assessment.

[0038] The risk assessment submodule, based on the results of the continuity trend analysis, evaluates the current risk level of the power pipeline, identifies potential risk factors, determines the risk level classification, and generates risk assessment results; in this step, quantitative and qualitative methods are used to classify risks in combination with the trend analysis results. The basis for the classification of risk levels includes the stability of the continuity results, the frequency of historical abnormal events, and the severity of their impact. The risk matrix method is used to classify risks according to likelihood and impact, so as to determine the priority and response strategy for each risk. This module will integrate multi-faceted data and expert opinions to ensure the comprehensiveness and depth of risk assessment. The final risk assessment results will list in detail various risks and their recommended preventive measures.

[0039] The recommendation generation submodule formulates corresponding maintenance measures, writes maintenance recommendations, and outputs decision recommendations based on the risk assessment results. The key to this module is to convert risk assessment results into specific operation and maintenance recommendations. According to different risk levels, formulate corresponding maintenance strategies, including regular inspections, emergency repairs, equipment upgrades or replacements, and other measures. The maintenance recommendations will combine technical specifications and industry best practices, be specific to each risk point, and provide detailed operation steps and expected results. The final decision recommendations will form a comprehensive report, including recommended measures, implementation schedules, and expected costs, to support management in the rational allocation of funds and resources to improve the reliability and security of the system.

Claims

1. A device for testing the penetration of a power pipeline, characterized in that: include: The power parameter acquisition module is used to collect current signals and voltage signals in the power pipeline, measure temperature values ​​at multiple locations, obtain insulation impedance at each node, measure grounding resistance at multiple grounding points, summarize the measurement data, and generate a power parameter set; A signal feature extraction module, used to calculate the mean, variance and peak value of the current data and the voltage data based on the power parameter set, analyze the spatial distribution characteristics of the temperature value, extract the change trend of the insulation impedance, calculate the frequency characteristics of the ground resistance, and obtain the signal feature set; A weight calculation module, used for counting the value range of each signal feature based on the signal feature set; Calculate the frequency of occurrence of each signal feature; obtain the probability distribution of the signal feature; calculate the information entropy of each signal feature, calculate the weight value based on the information entropy, normalize each signal feature, and generate a feature weight set; A continuity assessment module is used to multiply each feature in the signal feature set by the corresponding weight based on the feature weight set to obtain a weighted feature value; summarize the weighted feature values ​​to obtain a total weighted value, and compare the total weighted value with a standard threshold; determine the continuity of the power pipeline, record the determination result, and obtain a continuity assessment result; The decision support module is used to analyze the continuity change trend based on the continuity assessment results and the historical data of the power pipeline; evaluate the risk level of the power pipeline according to the continuity change trend, generate maintenance suggestions, and output decision suggestions.

2. The device for testing the penetration of a power pipeline according to claim 1, characterized in that: The power parameter acquisition module includes: The electric signal acquisition submodule is used to collect real-time current signals based on power pipelines, connect current sensors at each key node, record the current value collected each time, collect real-time voltage signals using voltage sensors, record the voltage value collected each time, organize current values ​​and voltage values, and generate electric signal data sets; The temperature and impedance measurement submodule is used to use a temperature probe to contact at multiple locations, measure the temperature value at each location, record the temperature result at each location, connect at each node through an insulation tester, obtain the insulation impedance value of the node, record the insulation impedance data, use a ground resistance meter to connect at the grounding point, measure the ground resistance value, record the ground resistance data, organize the temperature value and the ground resistance data, and generate an environmental parameter set; The data aggregation submodule is used to merge the current data, voltage data, temperature data, insulation impedance data and ground resistance data based on the electrical signal data set and the environmental parameter set, organize them into a unified data format, and generate an electric power parameter set.

3. The device for testing the penetration of a power pipeline according to claim 2, characterized in that: The signal feature extraction module comprises: A statistical feature calculation submodule, for calculating the mean, variance and peak value of the current data based on the power parameter set, recording the calculation results, calculating the mean, variance and peak value of the voltage data, recording the calculation results, arranging the statistical features of the current and voltage, and generating a statistical feature set of the electric signal; A trend analysis submodule is used to analyze the distribution of temperature data at each location based on the environmental parameter set, identify the temperature change law, extract the change trend of insulation impedance data, calculate the frequency characteristics of ground resistance data, organize the analysis results, and generate an environmental parameter feature set; The feature integration submodule is used to match the electrical signal features with the environmental features based on the electrical signal statistical feature set and the environmental parameter feature set, integrate the feature data, form a complete feature set, and obtain the signal feature set.

4. The device for testing the penetration of a power pipeline according to claim 1, characterized in that: The weight calculation module includes: A feature statistics submodule is used to count the value range of each feature, calculate the frequency of occurrence of each signal feature, sort the statistical data, and generate a feature statistics set based on the signal feature set; An information entropy calculation submodule is used to calculate the information entropy value of each signal feature based on the feature statistical set, record the calculation result, calculate the initial weight according to the information entropy value, and generate an initial weight set; The weight normalization submodule is used to normalize the initial weights based on the initial weight set, adjust the proportional relationship of the weight values, make the total weight equal to one, and generate a feature weight set.

5. The device for testing the penetration of a power pipeline according to claim 1, characterized in that: The continuity assessment module includes: A weighted feature calculation submodule, for multiplying each feature value in the signal feature set by the corresponding weight based on the feature weight set, calculating the weighted feature value, recording the calculation result, and generating a weighted feature set; A total weighted value calculation submodule is used to add the weighted feature values ​​based on the weighted feature set to obtain a total weighted value, record the total weighted value, and generate a total weighted value result; The continuity judgment submodule is used to compare the total weighted value with the standard threshold based on the total weighted value result; judge the continuity status of the power pipeline, record the judgment result, and obtain the continuity evaluation result.

6. The device for testing the penetration of a power pipeline according to claim 1, characterized in that: The decision support module includes: The trend analysis submodule is used to arrange the continuity results in chronological order based on the continuity assessment results and the historical data of the power pipeline, analyze the trend of continuity changes, identify abnormal change points, and generate continuity trend analysis results.

7. The device for testing the penetration of a power pipeline according to claim 6, characterized in that: The decision support module also includes: A risk assessment submodule, for assessing the current risk level of the power pipeline based on the continuity trend analysis result, identifying potential risk factors, determining the risk level classification, and generating a risk assessment result; The suggestion generation submodule is used to formulate corresponding maintenance measures, write maintenance suggestions, and output decision suggestions based on the risk assessment results.

8. A method for using the device for testing the penetration of a power pipeline according to any one of claims 1 to 7, characterized in that: The following steps are involved: Collect current signals and voltage signals in power pipelines, measure temperature values ​​at multiple locations, obtain insulation impedance at each node, measure grounding resistance at multiple grounding points, summarize measurement data, and generate power parameter sets; Based on the power parameter set, the mean, variance and peak value of the current data and the voltage data are calculated, the spatial distribution characteristics of the temperature value are analyzed, the variation trend of the insulation impedance is extracted, the frequency characteristics of the grounding resistance are calculated, and the signal feature set is obtained; Based on the signal feature set, counting the value range of each signal feature; Calculate the frequency of occurrence of each signal feature; obtain the probability distribution of the signal feature; calculate the information entropy of each signal feature, calculate the weight value based on the information entropy, normalize each signal feature, and generate a feature weight set; Based on the feature weight set, multiply each feature in the signal feature set by the corresponding weight to obtain a weighted feature value; Summarize the weighted characteristic values ​​to obtain the total weighted value, and compare the total weighted value with the standard threshold; judge the continuity of the power pipeline, record the judgment result, and obtain the continuity assessment result; Based on the continuity assessment results, combined with the historical data of the power pipeline, the continuity change trend is analyzed; the risk level of the power pipeline is evaluated according to the continuity change trend, maintenance suggestions are generated, and decision suggestions are output.

Images