Substation inspection performance evaluation method and device, storage medium and computer equipment

Abstract

According to the substation inspection performance evaluation method and device, the storage medium and the computer equipment provided by the invention, the inspection data of the inspection task is collected, and the inspection coverage rate, the fault detection accuracy rate, the inspection time and the inspection cost are respectively calculated by using the inspection data. The inspection performance is comprehensively evaluated through multiple dimensions, and the comprehensiveness and reliability of performance evaluation are improved. Then, respectively determining a membership function corresponding to each index according to historical inspection data; and generating a membership score of each index on each evaluation grade based on each determined membership function to form a membership matrix. And finally, generating a comprehensive evaluation vector according to the membership matrix and the weight matrix, and defuzzifying the comprehensive evaluation vector to obtain a comprehensive score of the inspection task. By establishing the membership function of each index, inspection indexes of different dimensions can be converted into a unified fuzzy evaluation standard, so that the evaluation result is more objective and reasonable. Therefore, the accuracy and reliability of the inspection performance evaluation method are improved.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and in particular to a substation inspection performance evaluation method, device, storage medium and computer equipment. Background Art

[0002] As power systems transition toward intelligent and digital technologies, traditional manual substation inspections are no longer able to meet the demands of efficient, accurate, and safe operation. To adapt to this shift, intelligent inspection terminals such as drones and inspection robots are becoming increasingly common in substations. These intelligent terminals leverage artificial intelligence and data fusion technologies to enable real-time monitoring of equipment status, significantly improving the efficiency and reliability of power systems.

[0003] However, existing technologies still have limitations when it comes to comprehensively evaluating the performance of inspection terminals. Current evaluation methods often focus on a single metric and rely on qualitative analysis or static weighting. These shortcomings make existing inspection performance evaluation methods inaccurate and unreliable, making them difficult to meet practical needs. Summary of the Invention

[0004] The present application aims to address at least one of the aforementioned technical deficiencies, particularly the fact that existing technologies often focus on a single metric and rely on qualitative analysis or static weighting. These deficiencies result in existing inspection performance evaluation methods being inaccurate and unreliable to meet practical needs.

[0005] In a first aspect, the present application provides a substation inspection performance evaluation method, the method comprising:

[0006] Collect inspection data for this inspection task, and use the inspection data to calculate inspection coverage, fault detection accuracy, inspection time, and inspection cost;

[0007] Obtaining historical inspection data, and determining membership functions corresponding to the inspection coverage rate, the fault detection accuracy rate, the inspection time, and the inspection cost respectively based on the historical inspection data;

[0008] Generating membership scores of the inspection coverage, the fault detection accuracy, the inspection time, and the inspection cost at each evaluation level based on each determined membership function to form a membership matrix;

[0009] A weight matrix is ​​determined, and a comprehensive evaluation vector is generated according to the membership matrix and the weight matrix, and the comprehensive evaluation vector is defuzzified to obtain a comprehensive score for this inspection task.

[0010] In one embodiment, when the inspection task adopts a single device inspection, the inspection coverage, fault detection accuracy, inspection time and inspection cost are calculated respectively using the inspection data, including:

[0011] Determine the number of substation devices inspected by the inspection equipment from the inspection data, and determine the proportion of the number in the preset target inspection number as the inspection coverage rate;

[0012] Analyze the number of fault false alarms in this inspection task based on the inspection data, and calculate the fault detection accuracy rate based on the number of false alarms;

[0013] Obtaining the path planning time, navigation movement time, data collection time, and data analysis time of the inspection equipment from the inspection data, and summing the determined times to obtain the inspection time;

[0014] The energy consumption cost, equipment depreciation cost, labor cost and data storage cost of the inspection task are determined based on the inspection data, and the determined costs are summed to obtain the inspection cost.

[0015] In one embodiment, when the inspection task adopts multi-device collaborative inspection, the inspection coverage, fault detection accuracy, inspection time and inspection cost are calculated using the inspection data, including:

[0016] Determine the substation equipment inspected by each inspection device from the inspection data, remove duplicate substation equipment inspected by each inspection device, and count the number of substation equipment after deduplication, and determine the proportion of this number in the preset target inspection number as the inspection coverage rate;

[0017] Analyze the number of fault false alarms in this inspection task based on the inspection data, and calculate the fault detection accuracy rate based on the number of false alarms;

[0018] Obtaining the path planning time, navigation movement time, data collection time, and data analysis time of each inspection device from the inspection data, summing the determined times of each inspection device to obtain the working time of each inspection device, and selecting the maximum value among the working times of each inspection device as the inspection time;

[0019] Based on the inspection data, the energy consumption cost, equipment depreciation cost, labor cost and data storage cost of each inspection device are determined, and the various costs of each inspection device determined are summed up to obtain the working cost of each inspection device. Then, the working cost of each inspection device is summed up to obtain the inspection cost.

[0020] In one embodiment, the acquiring of historical inspection data and determining, based on the historical inspection data, the membership functions corresponding to the inspection coverage, the fault detection accuracy, the inspection time, and the inspection cost, respectively, include:

[0021] Obtain historical inspection data;

[0022] Perform cluster analysis on the four categories of inspection coverage, fault detection accuracy, inspection time, and inspection cost according to corresponding data in the historical inspection data to obtain corresponding cluster centers;

[0023] Gaussian membership functions are constructed based on the cluster centers of each category, and multi-objective optimization correction is performed on each Gaussian membership function to obtain the membership function corresponding to each category, so as to determine the membership function of the inspection coverage, the fault detection accuracy, the inspection time and the inspection cost.

[0024] In one embodiment, the multi-objective optimization correction of each Gaussian membership function includes:

[0025] With the minimum fitting error, smooth function shape and membership monotonicity as the goals, a multi-objective genetic algorithm is used to optimize and correct each Gaussian membership function.

[0026] In one embodiment, generating the membership scores of the inspection coverage, the fault detection accuracy, the inspection time, and the inspection cost at each evaluation level based on the respective determined membership functions to form a membership matrix includes:

[0027] Substituting the inspection coverage rate, the fault detection accuracy rate, the inspection time, and the inspection cost into their corresponding membership functions respectively to obtain the membership scores of the inspection coverage rate, the fault detection accuracy rate, the inspection time, and the inspection cost at each evaluation level;

[0028] A membership matrix is ​​generated according to the membership scores of the inspection coverage, the fault detection accuracy, the inspection time, and the inspection cost at each evaluation level.

[0029] In one embodiment, the determining of the weight matrix, generating a comprehensive evaluation vector based on the membership matrix and the weight matrix, and defuzzifying the comprehensive evaluation vector to obtain a comprehensive score for the inspection task include:

[0030] Using the hierarchical analysis method to determine the weights corresponding to the inspection coverage rate, the fault detection accuracy rate, the inspection time, and the inspection cost to form a weight matrix;

[0031] The weight matrix is ​​multiplied by the membership matrix to obtain a comprehensive evaluation vector, and the comprehensive evaluation vector is defuzzified to obtain a comprehensive score for this inspection task.

[0032] In a second aspect, the present application provides a substation inspection performance evaluation device, the device comprising:

[0033] The data acquisition module is used to collect the inspection data of this inspection task and use the inspection data to calculate the inspection coverage rate, fault detection accuracy rate, inspection time and inspection cost;

[0034] A function determination module is used to obtain historical inspection data and determine the membership functions corresponding to the inspection coverage rate, the fault detection accuracy rate, the inspection time and the inspection cost according to the historical inspection data;

[0035] A membership determination module, configured to generate membership scores for the inspection coverage, the fault detection accuracy, the inspection time, and the inspection cost at each evaluation level based on the determined membership functions, so as to form a membership matrix;

[0036] The performance evaluation module is used to determine the weight matrix, generate a comprehensive evaluation vector based on the membership matrix and the weight matrix, defuzzify the vector, and obtain a comprehensive score for this inspection task.

[0037] In a third aspect, the present application provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the substation inspection performance evaluation method as described in any of the above embodiments.

[0038] In a fourth aspect, the present application provides a computer device, comprising: one or more processors, and a memory;

[0039] The memory stores computer-readable instructions, and when the one or more processors execute the computer-readable instructions, the steps of the substation inspection performance evaluation method as described in any one of the above embodiments are performed.

[0040] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0041] The substation inspection performance evaluation method, device, storage medium, and computer equipment provided in this application collect inspection data for this inspection task after the inspection task results are obtained, and use the inspection data to calculate the inspection coverage, fault detection accuracy, inspection time, and inspection cost. Inspection performance is comprehensively evaluated using these four dimensions, improving the comprehensiveness and reliability of the performance evaluation. Historical inspection data is then obtained, and membership functions corresponding to inspection coverage, fault detection accuracy, inspection time, and inspection cost are determined based on the historical inspection data. Based on each of the determined membership functions, membership scores for inspection coverage, fault detection accuracy, inspection time, and inspection cost at each evaluation level are generated to form a membership matrix. Finally, a weight matrix is ​​determined, and a comprehensive evaluation vector is generated based on the membership matrix and the weight matrix. This vector is then defuzzified to obtain a comprehensive score for the inspection task. By establishing membership functions for each indicator, inspection indicators of different dimensions can be converted into a unified fuzzy evaluation standard, making the evaluation results more objective and reasonable. This improves the accuracy and reliability of the inspection performance evaluation method. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 A flowchart of a substation inspection performance evaluation method provided in an embodiment of the present application;

[0044] Figure 2 One of the example flow charts for calculating inspection coverage, fault detection accuracy, inspection time, and inspection cost using inspection data provided in an embodiment of the present application;

[0045] Figure 3 Figure 2 of an example process for calculating inspection coverage, fault detection accuracy, inspection time, and inspection cost using inspection data provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of the structure of a substation inspection performance evaluation device provided in an embodiment of the present application;

[0047] Figure 5 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0049] In one embodiment, this application provides a method for evaluating substation inspection performance. The following embodiments illustrate this method as applied to a server. It is understood that the substation inspection performance evaluation method can be executed by a single server or a server cluster consisting of multiple servers, and this application does not impose specific limitations on this.

[0050] like Figure 1 As shown, the present application provides a substation inspection performance evaluation method, the method comprising:

[0051] S101: Collect inspection data of this inspection task, and use the inspection data to calculate the inspection coverage, fault detection accuracy, inspection time and inspection cost.

[0052] Inspection data refers to various data generated during the execution of inspection tasks, such as the substation inspected, the time spent inspecting a specific device, and the inspection results. Inspection coverage measures the percentage of devices or areas actually inspected during an inspection task compared to the total number of devices or areas that should be inspected, reflecting the comprehensiveness of the inspection. Fault detection accuracy refers to the ratio of the number of devices correctly identified as faulty during the inspection to the total number of devices identified as faulty during the inspection. Inspection time refers to the time required to complete an inspection task, including path planning time, navigation movement time, data collection time, data analysis time, etc. Inspection cost refers to the cost of executing a single inspection task.

[0053] In this step, intelligent terminals such as drones, inspection robots, or inspection cameras are deployed to automatically collect inspection data for this inspection mission. This data includes not only images of equipment operating status and potential defects, but also detailed time records and resource consumption of inspection operations. Using this inspection data, key performance indicators such as inspection coverage, fault detection accuracy, inspection time, and inspection cost can be calculated.

[0054] In one example, by comparing the inspection plan with the actual list of devices inspected, the inspection coverage rate can be calculated; by comparing the inspection results with subsequent verification results, the fault detection accuracy rate can be obtained; the total duration from the start to the end of the task can be recorded to obtain the inspection time; and by summarizing the consumption and expenses of all relevant resources, the inspection cost can be calculated. This application does not impose specific restrictions on this.

[0055] Specifically, calculating inspection coverage and fault detection accuracy helps assess the comprehensiveness and accuracy of inspections, ensuring the safe operation of the power system. Recording and analyzing inspection time can identify bottlenecks and delays during the inspection process, thereby optimizing the inspection process and improving efficiency. Calculating and controlling inspection costs helps power companies rationally allocate resources and reduce operating costs. By calculating indicators across multiple dimensions, the performance of inspection tasks can be comprehensively and comprehensively evaluated, providing decision support for subsequent optimization and adjustment.

[0056] S102: Obtain historical inspection data, and determine membership functions corresponding to inspection coverage, fault detection accuracy, inspection time, and inspection cost based on the historical inspection data.

[0057] Among them, historical inspection data refers to the inspection data collected and recorded during the inspection tasks in the past. The membership function is used to define the degree to which the corresponding indicator belongs to each fuzzy set.

[0058] In this step, historical inspection data must first be obtained. This data may include detailed information about all inspection tasks performed over the past few years. By analyzing this historical inspection data, the distribution and trend of each key performance indicator (KPI), such as inspection coverage, fault detection accuracy, inspection time, and inspection cost, can be determined. Based on this historical inspection data, a corresponding membership function can be determined for each performance indicator. Specifically, the membership function quantifies the performance of each indicator across different inspection tasks, assigning each indicator a membership value between 0 and 1.

[0059] S103: Generate membership scores of inspection coverage, fault detection accuracy, inspection time and inspection cost at each evaluation level based on the determined membership functions to form a membership matrix.

[0060] The evaluation level is used to measure the performance of the corresponding indicator for this inspection task. The number of scoring levels can be set when the membership function is determined. The membership score represents the degree of membership of the indicator to the corresponding evaluation level.

[0061] In this step, when determining the membership function, evaluation levels can be defined for key performance indicators such as inspection coverage, fault detection accuracy, inspection time, and inspection cost. These evaluation levels can be "excellent", "good", "general", "poor", etc., depending on the application scenario and requirements. This application does not impose specific restrictions on this. Then, using these membership functions, a membership score is generated for each indicator at each evaluation level. The membership scores of all indicators are organized into a matrix, namely a membership matrix, in which each row represents an indicator and each column represents an evaluation level. Such a membership matrix can comprehensively reflect the performance of the inspection task in each evaluation dimension.

[0062] In one example, for the fault detection accuracy , its membership function can be expressed as follows:

[0063] when When ≥ 90%, the degree of membership in “excellent” is high;

[0064] When 80%≤ When ≤90%, it is classified as “good”;

[0065] When 70%≤ When ≤80%, the classification is “medium”;

[0066] when When <80%, it is classified as “poor”.

[0067] Similarly, for inspection time and inspection cost, since the goal is to be as short as possible and as low as possible, their membership functions can adopt the reverse membership function, and finally the membership scores of each indicator are combined into a membership matrix , which can be expressed as:

[0068]

[0069] Where, It represents the membership score of the inspection coverage rate at the first evaluation level. It represents the inspection coverage rate’s membership score at the second evaluation level. represents the membership score of the fault detection accuracy on the first evaluation level, Indicates the inspection time's membership score on the first evaluation level. Indicates the inspection cost's score at the first evaluation level.

[0070] S104: Determine the weight matrix, generate a comprehensive evaluation vector based on the membership matrix and the weight matrix, defuzzify the vector, and obtain a comprehensive score for this inspection task.

[0071] The weight matrix includes the weight values ​​corresponding to inspection coverage, fault detection accuracy, inspection time and inspection cost.

[0072] In this step, when determining the weight matrix, the importance of each metric (inspection coverage, fault detection accuracy, inspection time, and inspection cost) can be quantified. This can be done using historical inspection data or based on specific business requirements. For example, if fault detection accuracy is critical to the safe operation of the power system, it may be given a higher weight in the weight matrix. Once the weight matrix is ​​determined, it is combined with the membership matrix to generate a comprehensive evaluation vector. This comprehensive evaluation vector is then converted into a specific score through defuzzification, or a comprehensive score. This comprehensive score measures the overall performance of the inspection task across all metrics.

[0073] In the above embodiment, after the inspection task results are obtained, the inspection data for this inspection task is collected, and the inspection data is used to calculate the inspection coverage, fault detection accuracy, inspection time, and inspection cost. Inspection performance is comprehensively evaluated using these four dimensions, improving the comprehensiveness and reliability of the performance evaluation. Historical inspection data is then obtained, and the membership functions corresponding to the inspection coverage, fault detection accuracy, inspection time, and inspection cost are determined based on the historical inspection data. Based on each of the determined membership functions, the membership scores for the inspection coverage, fault detection accuracy, inspection time, and inspection cost at each evaluation level are generated to form a membership matrix. Finally, a weight matrix is ​​determined, and a comprehensive evaluation vector is generated based on the membership matrix and the weight matrix. This vector is then defuzzified to obtain a comprehensive score for this inspection task. By establishing membership functions for each indicator, inspection indicators of different dimensions can be converted into a unified fuzzy evaluation standard, making the evaluation results more objective and reasonable. This improves the accuracy and reliability of the inspection performance evaluation method.

[0074] like Figure 2 As shown, in one embodiment, when the inspection task adopts single-device inspection, the inspection coverage, fault detection accuracy, inspection time and inspection cost are calculated respectively using the inspection data, including:

[0075] S201: Determine the number of substation equipment inspected by the inspection equipment from the inspection data, and determine the proportion of the number in the preset target inspection number as the inspection coverage rate.

[0076] S202: Analyze the number of fault false alarms in this inspection task based on the inspection data, and calculate the fault detection accuracy rate based on the number.

[0077] S203: Obtaining the path planning time, navigation movement time, data collection time, and data analysis time of the inspection equipment from the inspection data, and summing up the determined times to obtain the inspection time.

[0078] S204: Determine the energy consumption cost, equipment depreciation cost, labor cost, and data storage cost of the inspection task based on the inspection data, and sum up the determined costs to obtain the inspection cost.

[0079] The target inspection quantity is the total number of devices within the substation that require inspection. Path planning time refers to the time required for the inspection equipment to plan the inspection route. Navigation movement time refers to the time required for the inspection equipment to move to each inspection point according to the inspection route. Data collection time refers to the time required for the inspection equipment to collect image, temperature, point cloud, and other data at the inspection point. Data analysis time refers to the time required for the inspection equipment to process, analyze, and upload data. Energy consumption cost refers to the cost of electricity or fuel consumed by the inspection equipment during the inspection process. Equipment depreciation cost refers to the cost of wear and tear and maintenance of the inspection equipment. Labor cost refers to the cost of operators and data analysts. Data storage cost refers to the cost of data storage services.

[0080] In this embodiment, when a single-device inspection is performed during this inspection task, the number of substation devices actually inspected by the inspection equipment is first determined from the inspection data. This number is then compared with the preset target number of inspections to calculate the inspection coverage rate. This ratio reflects the degree of completion of the inspection task. Next, based on the inspection data, the number of false fault alarms during this inspection task is analyzed. This, combined with the number of detected faults, yields the fault detection accuracy rate.

[0081] Furthermore, the inspection data captures the path planning time, navigation movement time, data collection time, and data analysis time of the inspection equipment during the task. The sum of these times is the inspection time. This metric reflects the efficiency of the inspection task. Finally, based on the inspection data, the energy consumption cost, equipment depreciation cost, labor cost, and data storage cost of the inspection task are determined. The sum of these costs is the inspection cost. This helps power companies allocate resources more rationally and reduce operating costs.

[0082] In an example, the formula for calculating the inspection coverage can be expressed as:

[0083]

[0084] Where, Indicates the inspection coverage rate of a single device. Indicates the number of substation equipment inspected by the inspection equipment. Indicates the target inspection quantity.

[0085] The formula for calculating the fault detection accuracy can be expressed as:

[0086]

[0087] Where, represents the fault detection accuracy, represents the true positives, i.e. the number of faults correctly detected, Indicates the number of false fault alarms.

[0088] The formula for calculating the inspection time can be expressed as:

[0089]

[0090] Where, Indicates the inspection time of a single device. represents the path planning time, Indicates navigation movement time, Indicates the data collection time, Indicates the data analysis time.

[0091] The formula for calculating inspection costs can be expressed as:

[0092]

[0093] Where, Indicates the inspection cost of a single device. represents the energy consumption cost, represents the equipment depreciation cost, Represents labor cost, Indicates the data storage cost.

[0094] like Figure 3 As shown, in one embodiment, when the inspection task adopts multi-device collaborative inspection, the inspection coverage, fault detection accuracy, inspection time and inspection cost are calculated using the inspection data, including:

[0095] S301: Determine the substation equipment inspected by each inspection device from the inspection data, deduplicate the substation equipment inspected by each inspection device, and count the number of substation equipment after deduplication, and determine the proportion of this number in the preset target inspection number as the inspection coverage rate.

[0096] S302: Analyze the number of fault false alarms in this inspection task based on the inspection data, and calculate the fault detection accuracy rate based on the number.

[0097] S303: Obtain the path planning time, navigation movement time, data collection time and data analysis time of each inspection device in the inspection data, and sum up the various times of each determined inspection device to obtain the working time of each inspection device, and then select the maximum value among the working times of each inspection device as the inspection time.

[0098] S304: Based on the inspection data, determine the energy consumption cost, equipment depreciation cost, labor cost and data storage cost of each inspection device, and sum up the various costs of each inspection device to obtain the working cost of each inspection device. Then, sum up the working costs of each inspection device to obtain the inspection cost.

[0099] For the relevant descriptions in this embodiment, reference can be made to the descriptions in the previous embodiment. Since the scenario of this embodiment is multi-device collaborative inspection, adaptive adjustments are made to the inspection coverage, inspection time, and inspection cost.

[0100] For example, when calculating the inspection coverage, the formula can be expressed as:

[0101]

[0102] Where, Indicates the inspection coverage of multiple devices. Indicates the total number of deduplicated devices among all inspected devices. Indicates the target inspection quantity.

[0103] When calculating the inspection time, the formula can be expressed as:

[0104]

[0105] Where, Indicates the inspection time of multiple devices. Indicates the working time of the drone, Indicates the robot's working time, Indicates the working time of the camera. 、 、 You can refer to the calculation method of inspection time for a single device to calculate it one by one.

[0106] When calculating the inspection cost, the formula can be expressed as:

[0107]

[0108] Where, Indicates the inspection cost of multiple devices, N indicates the number of devices, The working cost of device i can be calculated by referring to the inspection cost of a single device.

[0109] In one embodiment, historical inspection data is obtained, and membership functions corresponding to inspection coverage, fault detection accuracy, inspection time, and inspection cost are determined based on the historical inspection data, including:

[0110] S1: Get historical inspection data.

[0111] S2: Perform cluster analysis on the four categories of inspection coverage, fault detection accuracy, inspection time, and inspection cost based on the corresponding data in the historical inspection data to obtain the corresponding cluster centers.

[0112] S3: Based on the cluster center of each category, Gaussian membership functions are constructed respectively, and multi-objective optimization correction is performed on each Gaussian membership function to obtain the membership function corresponding to each category to determine the membership function of inspection coverage, fault detection accuracy, inspection time and inspection cost.

[0113] In this embodiment, historical inspection data is first obtained and classified according to indicator categories, and then cluster analysis is performed on each type of data to identify typical patterns or cluster centers of different performance indicators. Cluster analysis can help us understand the distribution of different inspection tasks on various performance indicators, thereby providing a basis for constructing membership functions. Then, based on the cluster centers of each category, Gaussian membership functions are constructed respectively. The shape and parameters of the Gaussian membership function can be adjusted according to the characteristics of the cluster centers to ensure that the membership function can accurately reflect the distribution of each performance indicator. For example, for inspection coverage, if historical inspection data shows that the coverage of most inspection tasks is concentrated between 80% and 90%, then a Gaussian membership function centered at 85% can be constructed to reflect this concentration trend.

[0114] Next, a multi-objective optimization calibration is performed on each Gaussian membership function to ensure that it meets specific optimization objectives, such as maximizing the discrimination of the membership function or minimizing the fitting error of the membership function. This results in an optimized membership function for each category, which can more accurately quantify the performance of this inspection task across various performance indicators.

[0115] Furthermore, when historical inspection data is obtained, in order to ensure the reliability of subsequent processing, some of the historical inspection data can be preprocessed first. For example, continuous value indicators (such as fault detection accuracy) can be normalized.

[0116] In one example, for the indicator , its Gaussian membership function can be expressed as:

[0117]

[0118] Where, represents the Gaussian membership function, Indicator For the membership score of evaluation level j, represents the cluster center, represents the standard deviation of the membership function.

[0119] It's clear that cluster analysis and the construction of Gaussian membership functions make the evaluation process more quantitative and objective, reducing the influence of subjective judgment. Furthermore, multi-objective optimization ensures that the membership function meets specific optimization goals, thereby improving the discrimination and accuracy of the evaluation results. Furthermore, this approach can help identify strengths and weaknesses in the inspection process, providing a basis for continuous improvement and promoting the optimization of inspection work.

[0120] In one embodiment, performing multi-objective optimization correction on each Gaussian membership function includes:

[0121] With the minimum fitting error, smooth function shape and membership monotonicity as the goals, a multi-objective genetic algorithm is used to optimize and correct each Gaussian membership function.

[0122] Fitting error refers to the difference between the membership function and the expert evaluation, function shape refers to the geometric form of the membership function, and membership monotonicity refers to the tendency of the membership value to increase or decrease as the input variable changes. In fuzzy logic systems, membership monotonicity typically requires that the membership value either monotonically increase or decrease as the input variable increases to ensure logical consistency.

[0123] In this embodiment, the initial parameters of each Gaussian membership function, such as center, width, etc., can be determined. Then, with the goals of minimizing fitting error, smoothing function shape, and ensuring membership monotonicity, a multi-objective genetic algorithm is used to optimize and correct these membership functions. Specifically, the multi-objective genetic algorithm is a search algorithm that simulates natural selection and genetic mechanisms. It continuously iterates the solution to the optimization problem through operations such as selection, crossover, and mutation. During the optimization and correction process, the algorithm simultaneously considers multiple objectives, such as minimizing fitting error, maintaining smooth function shape, and ensuring membership monotonicity. In this way, the algorithm can find a balance point between multiple objectives and obtain a set of optimized membership function parameters.

[0124] For example, during the optimization process, the algorithm may adjust the center and width parameters of the Gaussian membership function to reduce fitting error while maintaining the smoothness of the function shape. Furthermore, the algorithm ensures the monotonicity of the membership function to ensure logical consistency. Through optimization using a multi-objective genetic algorithm, a set of membership functions can be obtained that accurately fit the data while also exhibiting a good shape and monotonicity. This improves the accuracy and reliability of the inspection performance evaluation method.

[0125] In one embodiment, membership scores of inspection coverage, fault detection accuracy, inspection time, and inspection cost at each evaluation level are generated based on the determined membership functions to form a membership matrix, including:

[0126] S1: Substitute the inspection coverage, fault detection accuracy, inspection time, and inspection cost into their corresponding membership functions to obtain the membership scores of inspection coverage, fault detection accuracy, inspection time, and inspection cost at each evaluation level.

[0127] S2: Generate a membership matrix based on the membership scores of inspection coverage, fault detection accuracy, inspection time and inspection cost at each evaluation level.

[0128] In this embodiment, the calculated values ​​of each indicator are input into the membership function of the corresponding indicator to obtain the membership score of each indicator at each evaluation level. The membership scores of each indicator at multiple evaluation levels are then arranged into a matrix to obtain a membership matrix.

[0129] In one embodiment, a weight matrix is ​​determined, and a comprehensive evaluation vector is generated based on the membership matrix and the weight matrix, and then defuzzified to obtain a comprehensive score for the inspection task, including:

[0130] S1: Use the analytic hierarchy process to determine the weights corresponding to inspection coverage, fault detection accuracy, inspection time, and inspection cost to form a weight matrix.

[0131] S2: Multiply the weight matrix and the membership matrix to obtain a comprehensive evaluation vector, and defuzzify the comprehensive evaluation vector to obtain a comprehensive score for this inspection task.

[0132] In this embodiment, weights are determined using the Analytic Hierarchy Process (AHP) to ensure that the importance of each indicator is properly reflected during the evaluation process. Multiplying the weight matrix by the membership matrix yields a comprehensive evaluation vector. This step integrates the evaluation results of each indicator, making the comprehensive evaluation more comprehensive. Finally, through defuzzification, the comprehensive evaluation vector is converted into a specific score, making the evaluation results more intuitive and easier to understand.

[0133] In other embodiments, methods such as deep learning may be used to determine the weights corresponding to inspection coverage, fault detection accuracy, inspection time, and inspection cost. This application does not impose any specific restrictions on this.

[0134] In one example, the centroid method can be used for defuzzification, and its expression can be expressed as:

[0135]

[0136] Where, Indicates the comprehensive score, represents the jth element in the comprehensive evaluation vector, Represents the value of the j-th indicator.

[0137] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0138] The substation inspection performance evaluation device provided in an embodiment of the present application is described below. The substation inspection performance evaluation device described below and the substation inspection performance evaluation method described above can be referenced to each other.

[0139] like Figure 4 As shown, the present application provides a substation inspection performance evaluation device 400, which includes:

[0140] The data collection module 401 is used to collect the inspection data of this inspection task and use the inspection data to calculate the inspection coverage rate, fault detection accuracy rate, inspection time and inspection cost;

[0141] Function determination module 402, for obtaining historical inspection data and determining membership functions corresponding to inspection coverage, fault detection accuracy, inspection time, and inspection cost based on the historical inspection data;

[0142] A membership determination module 403 is configured to generate membership scores for inspection coverage, fault detection accuracy, inspection time, and inspection cost at each evaluation level based on each determined membership function to form a membership matrix;

[0143] The performance evaluation module 404 is used to determine the weight matrix, generate a comprehensive evaluation vector based on the membership matrix and the weight matrix, and defuzzify the comprehensive evaluation vector to obtain a comprehensive score for this inspection task.

[0144] In the above embodiment, after the inspection task results are obtained, the inspection data for this inspection task is collected, and the inspection data is used to calculate the inspection coverage, fault detection accuracy, inspection time, and inspection cost. Inspection performance is comprehensively evaluated using these four dimensions, improving the comprehensiveness and reliability of the performance evaluation. Historical inspection data is then obtained, and the membership functions corresponding to the inspection coverage, fault detection accuracy, inspection time, and inspection cost are determined based on the historical inspection data. Based on each of the determined membership functions, the membership scores for the inspection coverage, fault detection accuracy, inspection time, and inspection cost at each evaluation level are generated to form a membership matrix. Finally, a weight matrix is ​​determined, and a comprehensive evaluation vector is generated based on the membership matrix and the weight matrix. This vector is then defuzzified to obtain a comprehensive score for this inspection task. By establishing membership functions for each indicator, inspection indicators of different dimensions can be converted into a unified fuzzy evaluation standard, making the evaluation results more objective and reasonable. This improves the accuracy and reliability of the inspection performance evaluation method.

[0145] In one embodiment, the data acquisition module includes:

[0146] The first determination submodule is configured to determine the number of substation devices inspected by the inspection equipment from the inspection data, and determine the proportion of the number in the preset target inspection number as the inspection coverage rate;

[0147] The second determination submodule is used to analyze the number of fault false alarms in this inspection task based on the inspection data, and calculate the fault detection accuracy based on the number;

[0148] The third determination submodule is used to obtain the path planning time, navigation movement time, data collection time and data analysis time of the inspection equipment from the inspection data, and sum up the determined times to obtain the inspection time;

[0149] The fourth determination submodule is used to determine the energy consumption cost, equipment depreciation cost, labor cost and data storage cost of this inspection task based on the inspection data, and sum up the determined costs to obtain the inspection cost.

[0150] In one embodiment, the data acquisition module includes:

[0151] The fifth determination submodule is used to determine the substation equipment inspected by each inspection device from the inspection data, remove duplicate substation equipment inspected by each inspection device, and count the number of substation equipment after deduplication, and determine the proportion of this number in the preset target inspection number as the inspection coverage rate;

[0152] A sixth determination submodule is configured to analyze the number of fault false alarms in this inspection task based on the inspection data, and calculate the fault detection accuracy rate based on the number of false alarms;

[0153] The seventh determination submodule is used to obtain the path planning time, navigation movement time, data collection time, and data analysis time of each inspection device in the inspection data, and sum the various times of each inspection device determined to obtain the working time of each inspection device, and then select the maximum value among the working times of each inspection device as the inspection time;

[0154] The eighth determination submodule is used to determine the energy consumption cost, equipment depreciation cost, labor cost and data storage cost of each inspection device based on the inspection data, and sum up the various costs of each determined inspection device to obtain the working cost of each inspection device, and then sum up the working cost of each inspection device to obtain the inspection cost.

[0155] In one embodiment, the function determination module includes:

[0156] Data acquisition submodule, used to obtain historical inspection data;

[0157] The cluster analysis submodule is used to perform cluster analysis on the four categories of inspection coverage, fault detection accuracy, inspection time and inspection cost according to the corresponding data in the historical inspection data, and obtain the corresponding cluster centers;

[0158] The function construction submodule is used to construct Gaussian membership functions based on the cluster centers of each category, and perform multi-objective optimization correction on each Gaussian membership function to obtain the membership function corresponding to each category, so as to determine the membership function of inspection coverage, fault detection accuracy, inspection time and inspection cost.

[0159] In one embodiment, the function construction submodule includes:

[0160] The optimization correction unit is used to optimize and correct each Gaussian membership function by taking the minimum fitting error, smooth function shape and membership monotonicity as the goals, and adopting a multi-objective genetic algorithm to optimize and correct each Gaussian membership function.

[0161] In one embodiment, the membership determination module includes:

[0162] The score determination submodule is used to substitute the inspection coverage rate, fault detection accuracy rate, inspection time and inspection cost into their corresponding membership functions to obtain the membership scores of the inspection coverage rate, fault detection accuracy rate, inspection time and inspection cost at each evaluation level;

[0163] The matrix determination submodule is used to generate a membership matrix according to the membership scores of inspection coverage, fault detection accuracy, inspection time and inspection cost at each evaluation level.

[0164] In one embodiment, the performance evaluation module includes:

[0165] The matrix determination submodule is used to determine the weights corresponding to the inspection coverage, fault detection accuracy, inspection time and inspection cost using the hierarchical analysis method to form a weight matrix;

[0166] The performance evaluation submodule is used to multiply the weight matrix and the membership matrix to obtain a comprehensive evaluation vector, and defuzzify the comprehensive evaluation vector to obtain a comprehensive score for this inspection task.

[0167] The division of the various modules in the above-mentioned substation inspection performance evaluation device is for illustrative purposes only. In other embodiments, the substation inspection performance evaluation device can be divided into different modules as needed to complete all or part of the functions of the above-mentioned substation inspection performance evaluation device. The various modules in the above-mentioned substation inspection performance evaluation device can be implemented in whole or in part through software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of the above-mentioned modules.

[0168] In one embodiment, the present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the substation inspection performance evaluation method as described in any of the above embodiments.

[0169] In one embodiment, the present application also provides a computer device having computer-readable instructions stored therein. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the substation inspection performance evaluation method as described in any one of the above embodiments.

[0170] Schematically, as Figure 5 As shown, Figure 5 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 500 can be provided as a server. Figure 5 Computer device 500 includes a processing component 502, which further includes one or more processors, and memory resources represented by memory 501 for storing instructions executable by processing component 502, such as application programs. The application programs stored in memory 501 may include one or more modules, each corresponding to a set of instructions. Furthermore, processing component 502 is configured to execute the instructions to perform the substation inspection performance evaluation method according to any of the above-described embodiments.

[0171] The computer device 500 may further include a power supply component 503 configured to perform power management of the computer device 500, a wired or wireless network interface 504 configured to connect the computer device 500 to a network, and an input / output (I / O) interface 505. The computer device 500 may operate based on an operating system stored in the memory 501, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or the like.

[0172] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0173] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment comprising a series of elements not only include those elements, but also include other elements not clearly listed, or also include elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements limited by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or equipment comprising the elements. Herein, the singular forms "one", "an" and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" etc. specify the existence of stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the existence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof. At the same time, the term "and / or" used in this specification includes any and all combinations of the relevant listed items.

[0174] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referenced to each other.

[0175] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A substation inspection performance evaluation method, characterized in that: The method comprises: Collect inspection data for this inspection task, and use the inspection data to calculate inspection coverage, fault detection accuracy, inspection time, and inspection cost; Obtaining historical inspection data, and determining membership functions corresponding to the inspection coverage rate, the fault detection accuracy rate, the inspection time, and the inspection cost respectively based on the historical inspection data; Generating membership scores of the inspection coverage, the fault detection accuracy, the inspection time, and the inspection cost at each evaluation level based on each determined membership function to form a membership matrix; A weight matrix is ​​determined, and a comprehensive evaluation vector is generated according to the membership matrix and the weight matrix, and the comprehensive evaluation vector is defuzzified to obtain a comprehensive score for this inspection task.

2. The substation inspection performance evaluation method according to claim 1, characterized in that: When the inspection task adopts single-device inspection, the inspection coverage, fault detection accuracy, inspection time and inspection cost are calculated respectively using the inspection data, including: Determine the number of substation devices inspected by the inspection equipment from the inspection data, and determine the proportion of the number in the preset target inspection number as the inspection coverage rate; Analyze the number of fault false alarms in this inspection task based on the inspection data, and calculate the fault detection accuracy rate based on the number of false alarms; Obtaining the path planning time, navigation movement time, data collection time, and data analysis time of the inspection equipment from the inspection data, and summing the determined times to obtain the inspection time; The energy consumption cost, equipment depreciation cost, labor cost and data storage cost of the inspection task are determined based on the inspection data, and the determined costs are summed to obtain the inspection cost.

3. The substation inspection performance evaluation method according to claim 1, characterized in that: When the inspection task adopts multi-device collaborative inspection, the inspection coverage, fault detection accuracy, inspection time and inspection cost are calculated respectively using the inspection data, including: Determine the substation equipment inspected by each inspection device from the inspection data, remove duplicate substation equipment inspected by each inspection device, and count the number of substation equipment after deduplication, and determine the proportion of this number in the preset target inspection number as the inspection coverage rate; Analyze the number of fault false alarms in this inspection task based on the inspection data, and calculate the fault detection accuracy rate based on the number of false alarms; Obtaining the path planning time, navigation movement time, data collection time, and data analysis time of each inspection device from the inspection data, summing the determined times of each inspection device to obtain the working time of each inspection device, and selecting the maximum value among the working times of each inspection device as the inspection time; Based on the inspection data, the energy consumption cost, equipment depreciation cost, labor cost and data storage cost of each inspection device are determined, and the various costs of each inspection device determined are summed up to obtain the working cost of each inspection device. Then, the working cost of each inspection device is summed up to obtain the inspection cost.

4. The substation inspection performance evaluation method according to claim 1, characterized in that: The acquiring of historical inspection data and determining, based on the historical inspection data, the membership functions corresponding to the inspection coverage rate, the fault detection accuracy rate, the inspection time, and the inspection cost respectively include: Obtain historical inspection data; Perform cluster analysis on the four categories of inspection coverage, fault detection accuracy, inspection time, and inspection cost according to corresponding data in the historical inspection data to obtain corresponding cluster centers; Gaussian membership functions are constructed based on the cluster centers of each category, and multi-objective optimization correction is performed on each Gaussian membership function to obtain the membership function corresponding to each category, so as to determine the membership function of the inspection coverage, the fault detection accuracy, the inspection time and the inspection cost.

5. The substation inspection performance evaluation method according to claim 4, characterized in that: The multi-objective optimization correction of each Gaussian membership function includes: With the minimum fitting error, smooth function shape and membership monotonicity as the goals, a multi-objective genetic algorithm is used to optimize and correct each Gaussian membership function.

6. The substation inspection performance evaluation method according to claim 1, characterized in that: The generating of the membership scores of the inspection coverage, the fault detection accuracy, the inspection time, and the inspection cost at each evaluation level based on the respective determined membership functions to form a membership matrix includes: Substituting the inspection coverage rate, the fault detection accuracy rate, the inspection time, and the inspection cost into their corresponding membership functions respectively to obtain the membership scores of the inspection coverage rate, the fault detection accuracy rate, the inspection time, and the inspection cost at each evaluation level; A membership matrix is ​​generated according to the membership scores of the inspection coverage, the fault detection accuracy, the inspection time, and the inspection cost at each evaluation level.

7. The substation inspection performance evaluation method according to claim 1, characterized in that: The weight matrix is ​​determined, and a comprehensive evaluation vector is generated according to the membership matrix and the weight matrix, and the comprehensive evaluation vector is defuzzified to obtain a comprehensive score for the inspection task, including: Using the hierarchical analysis method to determine the weights corresponding to the inspection coverage rate, the fault detection accuracy rate, the inspection time, and the inspection cost to form a weight matrix; The weight matrix is ​​multiplied by the membership matrix to obtain a comprehensive evaluation vector, and the comprehensive evaluation vector is defuzzified to obtain a comprehensive score for this inspection task.

8. A substation inspection performance evaluation device, characterized in that: The device comprises: The data acquisition module is used to collect the inspection data of this inspection task and use the inspection data to calculate the inspection coverage rate, fault detection accuracy rate, inspection time and inspection cost; A function determination module is used to obtain historical inspection data and determine the membership functions corresponding to the inspection coverage rate, the fault detection accuracy rate, the inspection time and the inspection cost according to the historical inspection data; A membership determination module, configured to generate membership scores for the inspection coverage, the fault detection accuracy, the inspection time, and the inspection cost at each evaluation level based on the determined membership functions, so as to form a membership matrix; The performance evaluation module is used to determine the weight matrix, generate a comprehensive evaluation vector based on the membership matrix and the weight matrix, defuzzify the vector, and obtain a comprehensive score for this inspection task.

9. A storage medium, characterized in that: The storage medium stores computer-readable instructions, which, when executed by one or more processors, enable the one or more processors to execute the steps of the substation inspection performance evaluation method according to any one of claims 1 to 7.

10. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the substation inspection performance evaluation method according to any one of claims 1 to 7 are executed.

Images