Closed-loop management method, system and equipment for reliability of power transmission and transformation loop, and medium

Abstract

The invention discloses a closed-loop management method, system and equipment for power transmission and transformation loop reliability and a medium, and belongs to the technical field of reliability evaluation and power transmission and transformation management, and the method comprises the steps: respectively constructing a two-dimensional evaluation system of technical reliability and management efficiency based on the loop operation state and the equipment full life cycle management efficiency; secondly, integrating the two types of indexes by adopting a self-adaptive weighted fusion algorithm, and generating a comprehensive reliability score; a data-driven attribution analysis technology is utilized to accurately position reliability bottleneck and management defects, and the contribution degree of each factor is quantified; and finally, based on an analysis result, reversely driving maintenance strategy optimization and resource configuration. According to the method, a two-dimensional evaluation system of a loop-level reliability index and an equipment management index is constructed, comprehensive evaluation is performed by using a weighted scoring model, loop weak links and management defects are intelligently diagnosed based on a decision tree algorithm, and finally maintenance strategy optimization and accurate resource configuration are driven.

Description

Technical Field

[0001] This invention relates to the field of reliability assessment and power transmission and transformation management technology, specifically to a closed-loop management method, system, equipment, and medium for the reliability of power transmission and transformation circuits. Background Technology

[0002] Power grid reliability is the cornerstone of the safe and stable operation of the power system. Traditional reliability assessments of power transmission and transformation projects often focus on the availability indicators of individual devices (such as transformers and circuit breakers), lacking a systematic evaluation of complete electrical circuits based on functionality. This "equipment island" evaluation model cannot accurately reflect the actual operational reliability and weaknesses of the power grid.

[0003] The existing evaluation system has failed to effectively drive the optimization of front-end planning, design, procurement, and operation and maintenance strategies. Management aspects (such as plan execution, talent development, and process control) are often disconnected from technical reliability indicators, failing to form a continuous improvement management loop and hindering further improvement in the level of lean management of power grid reliability. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention provides a closed-loop management method, system, device and medium for the reliability of power transmission and transformation circuits.

[0005] Therefore, the technical problem solved by this invention is to overcome the limitations of the "equipment island" model in the existing power transmission and transformation reliability evaluation, that is, the traditional method only focuses on the availability index of a single equipment and lacks a systematic evaluation of the complete electrical circuit, which makes it difficult to truly reflect the actual reliability and weak links of the power grid operation; at the same time, it solves the problem of the disconnect between the existing evaluation system and the management link, which cannot effectively form an "evaluation-optimization" closed loop, and thus cannot drive the continuous optimization of front-end strategies such as planning, design, operation and maintenance.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a closed-loop management method for the reliability of power transmission and transformation circuits, comprising, The reliability evaluation index of the power transmission and transformation circuit is calculated based on the reliability measurement and comprehensive evaluation of the circuit operation status; the comprehensive management evaluation index of equipment and facilities is calculated based on the management efficiency of the entire equipment life cycle, and the scores of each index are calculated based on the completion rate results and the preset scoring rules; a comprehensive scoring model is constructed, and the reliability index of the power transmission and transformation circuit is integrated with the management evaluation index of equipment and facilities through an adaptive weighted fusion method to output a comprehensive reliability score; based on the comprehensive reliability score results, data-driven attribution analysis is used to locate the links with insufficient reliability margin and management defects, and to quantify the contribution of each attribution factor; based on the attribution analysis results, the maintenance strategy is adjusted in reverse to achieve closed-loop management of power grid reliability.

[0007] As a preferred embodiment of the closed-loop management method for power transmission and transformation circuit reliability described in this invention, the reliability evaluation index of the power transmission and transformation circuit based on the reliability measurement and comprehensive evaluation of the circuit operating status includes: By integrating the operating status data of key circuits under multiple voltage levels, a comprehensive reliability index is calculated.

[0008] By benchmarking the comprehensive reliability index against the preset target, and quantifying it into a standardized score according to the first rule.

[0009] As a preferred embodiment of the closed-loop management method for power transmission and transformation circuit reliability described in this invention, the comprehensive reliability index calculated by integrating the operating status data of key circuits under multiple voltage levels includes: Based on the circuit's operating status data, the availability factor and forced outage rate of the circuit at a specific voltage level are calculated respectively.

[0010] By integrating multi-dimensional indicators, the indicator values ​​of different voltage levels are combined to obtain the comprehensive availability coefficient and comprehensive forced outage rate of each circuit under the same condition.

[0011] The process of benchmarking the comprehensive reliability index against a preset target and quantifying it into a standardized score according to the first rule includes: The calculated comprehensive index value is compared with the preset target value to obtain the target index completion rate of availability coefficient and forced shutdown rate, respectively.

[0012] Based on the scoring rules, the final score of each loop reliability index is calculated according to the target index completion rate.

[0013] As a preferred embodiment of the closed-loop management method for power transmission and transformation circuit reliability described in this invention, the method involves calculating comprehensive management evaluation indicators for equipment and facilities based on the equipment's full life-cycle management efficiency, and calculating scores for each indicator based on completion rate results and preset scoring rules. Select key aspects of equipment lifecycle management.

[0014] The effectiveness of equipment management is quantified by calculating the completion rate and on-time performance of key processes.

[0015] Based on preset rules, points are deducted for key steps, resulting in reward and punishment scores.

[0016] By combining the quantitative results of key aspects with reward and penalty scores, the final score of the comprehensive management evaluation index for equipment and facilities is calculated.

[0017] As a preferred embodiment of the closed-loop management method for power transmission and transformation circuit reliability described in this invention, the step of constructing a comprehensive scoring model integrates power transmission and transformation circuit reliability indicators with equipment and facility management evaluation indicators through an adaptive weighted fusion method, and outputs a comprehensive reliability score including... Establish a weighting framework for the evaluation system and assign basic weights to the two dimensions of power transmission and transformation circuit reliability and equipment and facility management.

[0018] Within each dimension, contribution weights are dynamically allocated to each sub-indicator based on historical data analysis.

[0019] An adaptive weighted fusion algorithm is used to integrate the scores of each indicator in the two dimensions with their corresponding weights for calculation.

[0020] The beneficial effect of this preferred technical solution is that by constructing a two-layer weighting framework that includes basic weights and dynamic contribution weights, and by using an adaptive weighted fusion algorithm for integrated calculation, it effectively overcomes the limitations of subjectively setting weights in traditional evaluation.

[0021] As a preferred embodiment of the closed-loop management method for power transmission and transformation circuit reliability described in this invention, the step of using data-driven attribution analysis based on comprehensive reliability scoring results to locate links with insufficient reliability margins and management deficiencies, and to quantify the contribution of each attribution factor, includes... Based on comprehensive reliability scores and sub-indicator data, key equipment and management factors affecting reliability are automatically identified through interpretable machine learning models.

[0022] By quantifying the contribution of each factor to the scoring results, the root cause of the decline in reliability can be identified.

[0023] The beneficial effect of this preferred technical solution is that by introducing an interpretable machine learning model for data-driven attribution analysis, it achieves accurate tracing from macro-level scoring to micro-level factors, effectively overcoming the subjectivity and limitations of traditional manual analysis.

[0024] As a preferred embodiment of the closed-loop management method for power transmission and transformation circuit reliability described in this invention, the step of automatically identifying key equipment and management factors affecting reliability based on comprehensive reliability scores and sub-indicator data through an interpretable machine learning model includes: By constructing and analyzing a dataset, collecting historical comprehensive scores and sub-indicators to build a training set, setting scoring rules, and learning through decision trees, the machine learning model can automatically extract the core rules that affect the score classification.

[0025] The method of quantifying the contribution of each factor to the scoring results to pinpoint the root causes of the decline in reliability includes: Based on the path backtracking mechanism of the interpretable machine learning model, specific loop types and indicators are located, and the direct impact weight on the total score is quantified by feature importance.

[0026] The beneficial effect of this preferred technical solution is that by constructing an analysis dataset containing historical comprehensive scores and sub-indicators, and by utilizing the path backtracking mechanism and feature importance quantification function of decision trees, multi-level accurate tracing of reliability issues is achieved.

[0027] This invention provides a closed-loop management system for the reliability of power transmission and transformation circuits.

[0028] To address the aforementioned technical problems, this invention provides the following technical solution: a closed-loop management system for the reliability of power transmission and transformation circuits, comprising: a data acquisition and preprocessing module, a multi-dimensional index calculation and scoring module, a comprehensive evaluation and fusion analysis module, a strategy generation and decision support module, and a closed-loop feedback and optimization module.

[0029] The data acquisition and preprocessing module calculates the reliability evaluation index of the power transmission and transformation circuit based on the reliability measurement and comprehensive evaluation of the circuit operation status.

[0030] The multi-dimensional indicator calculation and scoring module calculates comprehensive management evaluation indicators for equipment and facilities based on the efficiency of equipment life cycle management, and calculates the scores of each indicator based on the completion rate results and preset scoring rules.

[0031] The comprehensive evaluation and fusion analysis module constructs a comprehensive scoring model, which integrates the reliability indicators of power transmission and transformation circuits with the evaluation indicators of equipment and facility management through an adaptive weighted fusion method, and outputs a comprehensive reliability score.

[0032] The strategy generation and decision support module, based on the comprehensive reliability score, uses data-driven attribution analysis to locate links with insufficient reliability margins and management deficiencies, and quantifies the contribution of each attribution factor.

[0033] The closed-loop feedback and optimization module, based on the attribution analysis results, drives the adjustment of maintenance strategies in reverse, thereby realizing closed-loop management of power grid reliability.

[0034] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the closed-loop management method for reliability of power transmission and transformation circuits.

[0035] The present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the closed-loop management method for reliability of power transmission and transformation circuits.

[0036] The beneficial effects of this invention are as follows: This invention constructs a two-dimensional evaluation system of loop-level reliability indicators and equipment management indicators, uses a weighted scoring model for comprehensive evaluation, and intelligently diagnoses loop weaknesses and management defects based on decision tree algorithms. Ultimately, it drives the optimization of maintenance strategies and the precise allocation of resources, forming a closed loop of "evaluation-analysis-optimization". This realizes the transformation from single equipment management to system loop management, and comprehensively improves the refinement and systematization of power grid reliability. Attached Figure Description

[0037] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating a closed-loop management method for the reliability of power transmission and transformation circuits, as provided in one embodiment of the present invention.

[0039] Figure 2 This is a block diagram of a closed-loop management system for power transmission and transformation circuit reliability provided in one embodiment of the present invention. Detailed Implementation

[0040] To make the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0041] Example 1, referring to Figure 1 This is one embodiment of the present invention, which provides a closed-loop management method for the reliability of power transmission and transformation circuits, including: S1. Calculate the reliability evaluation index of power transmission and transformation circuits based on the reliability measurement and comprehensive evaluation of circuit operation status.

[0042] S2. Calculate the comprehensive management evaluation indicators of equipment facilities based on the efficiency of equipment life cycle management, and calculate the scores of each indicator based on the completion rate results and the preset scoring rules.

[0043] S3. Construct a comprehensive scoring model, and integrate the reliability indicators of power transmission and transformation circuits with the evaluation indicators of equipment and facility management through an adaptive weighted fusion method to output a comprehensive reliability score.

[0044] S4. Based on the comprehensive reliability score results, data-driven attribution analysis is used to locate the links with insufficient reliability margin and management deficiencies, and to quantify the contribution of each attribution factor.

[0045] S5. Based on the attribution analysis results, reverse-drive the adjustment of maintenance strategies to achieve closed-loop management of power grid reliability.

[0046] By constructing a two-dimensional evaluation system covering loop-level reliability measurement and equipment lifecycle management effectiveness, and using an adaptive weighted fusion algorithm to generate a comprehensive reliability score, a systematic and accurate characterization of power grid reliability has been achieved for the first time. Furthermore, by utilizing data-driven attribution analysis technology, the system automatically locates links with insufficient reliability margins and management defects, and quantifies the contribution of each factor, forming a closed-loop management mechanism of "evaluation-attribution-optimization". This effectively overcomes the limitations of traditional isolated equipment evaluation and provides a scientific basis for adjusting maintenance strategies and accurately allocating resources.

[0047] Example 2, an embodiment of the present invention, provides a closed-loop management method for the reliability of power transmission and transformation circuits based on the previous embodiment, including: In the embodiments of this application, the reliability measurement and comprehensive evaluation of the circuit operation status in S1 is to calculate the availability coefficient and forced outage rate of the three types of circuits, namely the main transformer, bus and outgoing line, under different voltage levels, and to integrate their weight ratio and target completion rate. Specifically, this includes collecting data such as maintenance plans and work orders, and after data cleaning, transformation and fusion, obtaining the operation status data of each circuit, including fields such as circuit category, circuit name, voltage level, power outage start time, power outage end time, and outage nature.

[0048] Based on the formula for calculating the forced outage rate: Forced Outage Rate = Number of Forced Outages / Number of Statistical Circuits per Year, the forced outage rates for 110kV and 220kV and above circuits of the main transformer circuit, outgoing line circuit, and busbar circuit are calculated separately. Furthermore, the forced outage rate for 110kV and above circuits is calculated for each circuit according to the weighted ratio of the forced outage rates for 110kV and 220kV and above circuits.

[0049] The completion rate of the forced outage rate target is calculated as: Forced Outage Rate / Forced Outage Rate Target Value. A score is calculated based on the completion rate of the forced outage rate target. If the completion rate is greater than or equal to the target value, the score is multiplied by the weight. If the completion rate is less than the target value, 120 points are awarded.

[0050] In one optional implementation, the reliability measurement and comprehensive evaluation of the loop's operating status can be achieved by introducing a reliability correction coefficient based on the operating load rate. Specifically, this includes the following: when calculating the loop availability coefficient, the average load rate data of the loop during the statistical period is collected simultaneously; when the average load rate of the loop continuously exceeds a preset threshold (e.g., 80%) of its rated capacity, a load rate penalty coefficient is introduced to correct the equivalent available hours, i.e.: corrected equivalent available hours = original equivalent available hours × (1 - load rate penalty coefficient).

[0051] In another optional implementation, the reliability measurement and comprehensive evaluation of the loop operation status can also be achieved using a weighted forced outage rate based on the severity of the fault consequences. Specifically, based on the calculation of the forced outage rate, a severity weight is further assigned to each outage event according to the load loss caused by each forced outage, the user's importance level, or the system's operational risk level; the weighted forced outage rate = (Severity weight of each forced shutdown) / Statistical loop · year.

[0052] Furthermore, the reliability measurement and comprehensive evaluation calculation of transmission and transformation circuit reliability evaluation indicators based on circuit operating status in S1 includes steps A1-A2: A1. By integrating the operating status data of key circuits under multiple voltage levels, a comprehensive reliability index is calculated.

[0053] A2. By benchmarking the comprehensive reliability index against the preset target, and quantifying it into a standardized score according to the first rule.

[0054] In the embodiments of this application, the first rule in A2 is to calculate the availability factor of each circuit at 110kV and above.

[0055] The completion rate of the loop availability coefficient target indicator is calculated as: Loop Availability Coefficient / Loop Availability Coefficient Target Value. A score is calculated based on the completion rate of the loop availability coefficient target indicator; a score greater than or equal to the target value is 120 points, while a score less than the target value is calculated by multiplying the score rate by a weight.

[0056] The forced outage rate of 110kV and above circuits was calculated.

[0057] The completion rate of the forced outage rate target is calculated as: Forced Outage Rate / Forced Outage Rate Target Value. A score is calculated based on the completion rate of the forced outage rate target. If the completion rate is greater than or equal to the target value, the score is multiplied by the weight. If the completion rate is less than the target value, 120 points are awarded.

[0058] In one alternative implementation, the first rule can be a dynamic scoring mechanism using piecewise linear interpolation. Specifically, this includes setting a target value for the available coefficient / forced shutdown rate as a benchmark, while simultaneously setting an industry-optimal value as the full score; when the indicator value is better than the target value, a score is calculated using linear interpolation between the target value and the optimal value (up to 150 points); when the indicator value is lower than the target value, another linear interpolation is used to calculate the score between the minimum allowable value and the target value.

[0059] In another alternative implementation, the first rule can also be to introduce an incentive coefficient based on the magnitude of indicator improvement. Specifically, this includes simultaneously comparing the improvement of the loop indicator value with that of the same period last year when calculating the current score; when the improvement exceeds a preset threshold, multiplying the base score by an incentive coefficient greater than 1 (e.g., 1.1-1.3); and multiplying a regressive indicator by a corresponding penalty coefficient.

[0060] Furthermore, in A1, by integrating the operating status data of critical circuits under multiple voltage levels, the comprehensive reliability index is calculated, including steps A11-A12: A11. Based on the circuit's operating status data, calculate the circuit's availability factor and forced outage rate at specific voltage levels.

[0061] The circuit includes three types: main transformer, busbar, and outgoing line.

[0062] A12. By integrating multi-dimensional indicators, the indicator values ​​of different voltage levels are combined to obtain the comprehensive availability coefficient and comprehensive forced outage rate of each circuit under the same condition.

[0063] One type of situation refers to the comprehensive availability factor and comprehensive forced outage rate of each circuit at 110kV and above.

[0064] In this embodiment of the application, the multi-dimensional index fusion, i.e., the weighting method in A12, specifically includes calculating the reliability indices of three types of circuits—main transformer, busbar, and outgoing line—based on the preprocessed data. According to the circuit availability coefficient calculation formula: Circuit availability coefficient = Circuit equivalent available hours / Statistical period hours, the availability coefficients for 110kV and 220kV and above circuits of the main transformer circuit, outgoing line circuit, and busbar circuit are calculated respectively. Further, the availability coefficients of 110kV and above circuits are calculated according to the weighting ratio of the 110kV and 220kV and above circuit availability coefficients to obtain the availability coefficients of each 110kV and above circuit.

[0065] In one alternative implementation, the multi-dimensional index fusion can employ a dynamic weighting method based on network topology importance. Specifically, firstly, the electrical centrality index of each voltage level circuit in the system is calculated using a power grid topology analysis algorithm; then, weights are dynamically allocated according to the centrality index, with higher electrical centrality voltage levels receiving higher weights; finally, the availability coefficients of 110kV and 220kV and above circuits are weighted using these dynamic weights to obtain a comprehensive availability coefficient that better reflects the actual structural characteristics of the power grid.

[0066] In another alternative implementation, the fusion of multi-dimensional indicators can also be achieved by applying a fuzzy comprehensive evaluation method based on reliability correlation. Specifically, a fuzzy evaluation set of reliability indicators for circuits at each voltage level is established, and the correlation matrix between different voltage levels is determined through expert evaluation. Then, a fuzzy synthesis operator is used to fuse the availability coefficients of 110kV and 220kV and above circuits to obtain a comprehensive availability coefficient evaluation value that takes into account both technical parameters and empirical judgment.

[0067] Furthermore, in A2, the comprehensive reliability index is benchmarked against a preset target and quantified into a standardized score according to the first rule, including steps A21-A22: A21. Compare the calculated comprehensive index value with the preset target value to obtain the target index completion rate of availability coefficient and forced shutdown rate respectively.

[0068] A22. Based on the scoring rules, calculate the final score of each loop reliability index according to the target index completion rate.

[0069] Furthermore, in S2, the comprehensive management evaluation indicators for equipment facilities are calculated based on the efficiency of equipment lifecycle management, and the scores for each indicator are calculated based on the completion rate results and the preset scoring rules, including steps B1-B4: B1. Select the key aspects of equipment lifecycle management.

[0070] B2. Quantify the effectiveness of equipment management by calculating the completion rate and on-time performance of key processes.

[0071] B3. Based on the preset rules, points are deducted from key links to obtain reward and punishment points.

[0072] B4. Based on the quantitative results of key aspects and the reward and penalty scores, the final score of the comprehensive management evaluation index for equipment and facilities is calculated.

[0073] Specifically, the comprehensive evaluation indicators for equipment and facility management include five indicators: completion rate of pre-test and maintenance plans, timely elimination rate of emergency major defects, completion rate of substation equipment operation plans, cumulative completion rate of countermeasures, and completion rate of mandatory tasks.

[0074] The comprehensive evaluation of equipment and facility management is a refined assessment of the hardware infrastructure and management system that ensures power grid reliability. This evaluation focuses on the quality and execution of equipment lifecycle management, not only on the quantity of planned completions but also on using a strict scoring mechanism to constrain overdue and missed inspections, ensuring the timeliness and effectiveness of operation and maintenance work. Simultaneously, bonus points incentivize autonomous maintenance and technical capability improvement, guiding a shift from "passive defect elimination" to "proactive prevention." The calculation of various comprehensive evaluation indicators and their scores is as follows: The completion rate of the pre-test and maintenance plan = the number of pre-test and maintenance plans completed in the current year / the number of pre-test and maintenance plans that should be completed in the current year × 100%; a completion rate of 100% earns 120 points. For 110kV pre-test and maintenance plans that are not completed on time, 1 point will be deducted per instance per month; for 220kV pre-test and maintenance plans, 2 points will be deducted per instance per month; and for 500kV pre-test and maintenance plans, 3 points will be deducted per instance per month.

[0075] The timeliness rate of eliminating critical and urgent defects = number of critical and urgent defects eliminated in a timely manner / number of critical and urgent defects. A 100% timeliness rate of eliminating critical and urgent defects earns 120 points. For critical and urgent defects that are not eliminated in a timely manner, 1 point will be deducted from the score for each defect.

[0076] The completion rate of the power equipment operation plan = (number of risk control tasks completed in the current year / number of risk control tasks to be completed in the current year) × 100%; a completion rate of 100% earns 120 points. For each instance of failure to complete the task on time, 2 points will be deducted per month. For each instance of falsification of completion information, 2 points will be deducted per instance. For any "mandatory" task not completed, 5 points will be deducted per instance per month.

[0077] Cumulative completion rate of countermeasures = Cumulative number of countermeasures completed / Annual number of countermeasures to be completed × 100%. A completion rate of 100% earns 120 points. Based on the score for achieving the target completion, if a countermeasure is found to be eliminated beyond the deadline, 2 points will be deducted per item per instance (with a maximum deduction of 10 points). Based on the score for achieving the target completion, if the company's inspection finds any unreported countermeasures, 2 points will be deducted per item per instance (with a maximum deduction of 10 points).

[0078] The completion rate of mandatory tasks = number of completed governance tasks / (number of additional tasks in equipment operation plan + number of tasks involving thorough governance risks in the annual new equipment risk warning list). Based on the indicator completion score, if the completion rate of mandatory tasks is ≥50%, 1.5 points are awarded; for every 10% increase in the completion rate, 0.1 points are awarded.

[0079] Furthermore, in S3, a comprehensive scoring model is constructed. Through an adaptive weighted fusion method, the reliability indicators of transmission and transformation circuits are integrated with equipment and facility management evaluation indicators to output a comprehensive reliability score, comprising steps C1-C3: C1. Establish the weight framework of the evaluation system and allocate the basic weights to the two dimensions of the reliability of the power transmission and transformation loop and the management of equipment and facilities.

[0080] The model first establishes the weight system framework. Set the basic weight of the "evaluation index of the reliability of the power transmission and transformation loop" dimension as W1, and set the basic weight of the "evaluation index of the comprehensive management of equipment and facilities" dimension as W2, and satisfy the normalization constraint condition W1 < W2 and W1 + W2 = 1.

[0081] C2. Within each dimension, dynamically allocate the contribution weights to each sub-index based on historical data analysis.

[0082] The contribution weights of the sub-indexes within the dimension. Within each dimension, based on historical data regression analysis (identifying the correlation strength between each index and the system reliability result), dynamically allocate the contribution weight of each sub-index (such as the availability factor of the main transformer loop, the completion rate of the preliminary test and maintenance plan, etc.) within this dimension.

[0083] C3. Adopt an adaptive weighted fusion algorithm to integrate and calculate the scores of each index in the two dimensions and their corresponding weights.

[0084] After the weight system is determined, the model executes the weighted fusion algorithm. Its calculation formula is: Comprehensive total score = (The scores of each index in the first dimension × their contribution weights) × W1 + (The scores of each index in the second dimension × their contribution weights) × W2. Through this calculation, the comprehensive reliability score is finally output, and this score is used as the core basis for the subsequent root cause analysis.

[0085] In the embodiment of the present application, in S4, through data-driven attribution analysis, the links with insufficient reliability margin and management defects are located, that is, the decision tree algorithm is used for cause analysis. By constructing a data set with the comprehensive score and sub-indexes as features and setting a low score label, the core rules affecting score classification are extracted, the links with insufficient margin at the loop level and the defects in the management process are located, and the contribution ratio of each attribution factor to the total score is quantified. Specifically, the decision tree algorithm is used to analyze the comprehensive score generated in S3, trace back from the low score phenomenon to the root cause, and accurately locate the weak links at the loop level and the defects in the management process.

[0086] First, construct an analysis data set. Use the comprehensive scores and sub-indexes of each power supply bureau in the past two years (including the availability factor, forced outage rate of the main transformer / bus / line loop, and equipment management indicators) to construct a training set, and set "score < 110" as the low score label (the full score is 120). Through decision tree learning, the model automatically extracts the core rules affecting score classification.

[0087] The path backtracking mechanism based on the decision tree model first identifies specific circuit types (such as main transformer / bus circuits) and their low indicators (such as low availability coefficient, high forced outage rate, etc.), and quantifies their direct impact weight on the total score through feature importance; secondly, the management identifies process loopholes (such as the disconnect between countermeasure plans and maintenance cycles), and analyzes how management factors lower the total score.

[0088] The contribution ratio of each attribution level to the total score was calculated, clarifying the relative weights of factors such as management deficiencies, equipment aging, and execution deviations. Through simulation and analysis, the main reasons for the low total score of a power supply bureau were identified, providing data support for developing targeted improvement strategies.

[0089] In one alternative implementation, data-driven attribution analysis can be used to locate links with insufficient reliability margins and management deficiencies. This can be achieved by employing a feature contribution analysis method based on SHAP values. Specifically, based on the decision tree model, the SHAP values ​​of each feature (including loop indicators and management indicators) are further calculated to quantify the positive and negative contributions of each feature to the low-scoring prediction results of a single power supply bureau. By analyzing the SHAP value distribution of high-weight features, not only can key factors affecting reliability be identified, but also the direction of their influence can be determined.

[0090] In another alternative implementation, data-driven attribution analysis can be used to pinpoint insufficient reliability margins and management deficiencies by applying a combined model of association rule mining and causal discovery. Specifically, this involves first using association rule algorithms such as Apriori to mine frequently occurring "loop indicator-management deficiency" combinations from low-scoring samples (e.g., "low bus availability coefficient" often occurs simultaneously with "overdue pre-test maintenance"); then, combining this with causal discovery algorithms to construct a causal graph, distinguishing between correlated and causal factors, ultimately identifying the root cause chain of reliability problems rather than isolated factors.

[0091] Furthermore, S5, based on the attribution analysis results, reverse-drives the adjustment of maintenance strategies to achieve closed-loop management of power grid reliability, including: Based on the root cause analysis results of S4, precise adjustments to maintenance strategies and continuous optimization of resource allocation can be effectively driven, providing a basis for decision-making to improve power grid reliability. By identifying weak links and management deficiencies in the circuit, the analysis results can guide the formulation of differentiated maintenance strategies and the scientific allocation of operation and maintenance resources, ensuring that limited resources are invested in the most critical areas. The analysis conclusions provide directional support for carrying out root cause governance, promoting the resolution of systemic hidden dangers from the source levels such as technical standards and management processes, and ultimately achieving closed-loop management and continuous improvement of power grid reliability.

[0092] Example 3, referring to Figure 2This is one embodiment of the present invention, which provides a closed-loop management system for the reliability of power transmission and transformation circuits, including: a data acquisition and preprocessing module, a multi-dimensional index calculation and scoring module, a comprehensive evaluation and fusion analysis module, a strategy generation and decision support module, and a closed-loop feedback and optimization module.

[0093] The data acquisition and preprocessing module calculates reliability evaluation indicators for power transmission and transformation circuits based on reliability measurement and comprehensive evaluation of circuit operating status.

[0094] The multi-dimensional indicator calculation and scoring module calculates comprehensive management evaluation indicators for equipment and facilities based on the efficiency of equipment life cycle management, and calculates the scores of each indicator based on the completion rate results and preset scoring rules.

[0095] The comprehensive evaluation and fusion analysis module constructs a comprehensive scoring model. Through an adaptive weighted fusion method, it integrates the reliability indicators of power transmission and transformation circuits with the evaluation indicators of equipment and facility management, and outputs a comprehensive reliability score.

[0096] The strategy generation and decision support module, based on the comprehensive reliability score, uses data-driven attribution analysis to locate areas with insufficient reliability margins and management deficiencies, and quantifies the contribution of each attribution factor.

[0097] The closed-loop feedback and optimization module, based on the attribution analysis results, drives the adjustment of maintenance strategies in reverse, thereby achieving closed-loop management of power grid reliability.

[0098] This embodiment also provides an electronic device applicable to a closed-loop management method for the reliability of power transmission and transformation circuits, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the closed-loop management method for the reliability of power transmission and transformation circuits proposed in the above embodiment.

[0099] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements a closed-loop management method for the reliability of power transmission and transformation circuits as proposed in the above embodiments.

[0100] The storage medium proposed in this embodiment belongs to the same inventive concept as the closed-loop management method for power transmission and transformation circuit reliability proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0101] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0102] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A closed-loop management method for power transmission and distribution circuit reliability, characterized by: The method comprises the following steps: Based on the reliability measurement and comprehensive evaluation of the circuit operation state, the reliability evaluation index of the power transmission and transformation circuit is calculated. Based on the management efficiency of the equipment full life cycle, the comprehensive management evaluation index of the equipment and facility is calculated, and the final score of each index is calculated based on the completion rate result and the preset scoring rule. A comprehensive scoring model is constructed, and the power transmission and transformation circuit reliability index and the equipment and facility management evaluation index are integrated through an adaptive weighted fusion method to output the comprehensive reliability score. Based on the comprehensive reliability score result, the data-driven attribution analysis is performed to locate the reliability margin insufficient link and management defects, and the contribution of each attribution factor is quantified. According to the attribution analysis result, the maintenance strategy adjustment is driven in reverse to realize the closed-loop management of the power grid reliability.

2. The closed-loop management method for power transmission and transformation circuit reliability according to claim 1, characterized in that: The reliability measurement and comprehensive evaluation based on the circuit operation state include: By integrating the operation state data of the key circuit under multiple voltage levels, the comprehensive reliability index is calculated. By comparing the comprehensive reliability index with the preset target, and quantifying it into a standardized score according to the first rule.

3. The closed-loop management method for reliability of power transmission and distribution circuits according to claim 2, characterized in that: The comprehensive reliability index is calculated by integrating the operation state data of the circuit under multiple voltage levels. Based on the operation state data of the circuit, the availability coefficient and forced outage rate of the circuit under a specific voltage level are calculated. By multi-dimensional index fusion, the index values of different voltage levels are integrated to obtain the comprehensive availability coefficient and comprehensive forced outage rate under each circuit condition. The comprehensive reliability index is compared with the preset target value to obtain the target index completion rate of the availability coefficient and the forced outage rate. According to the scoring rule, the final score of each circuit reliability index is calculated according to the target index completion rate. The key links of the equipment full life cycle management are selected.

4. The closed-loop management method for reliability of power transmission and distribution circuits according to claim 3, characterized in that: The execution effect of equipment management is quantified by calculating the planned completion rate and task timeliness rate of the key links. According to the preset rule, the key links are deducted to obtain the reward and punishment scores. The final score of the equipment and facility comprehensive management evaluation index is calculated by integrating the quantification results of the key links and the reward and punishment scores. The comprehensive scoring model is constructed, and the power transmission and transformation circuit reliability index and the equipment and facility management evaluation index are integrated through an adaptive weighted fusion method to output the comprehensive reliability score. The weight framework of the evaluation system is established, and the basic weights of the power transmission and transformation circuit reliability and the equipment and facility management are allocated.

5. The closed-loop management method for reliability of power transmission and distribution circuits according to claim 4, characterized in that: Based on historical data analysis, the contribution weights of each subdivided index are dynamically allocated within each dimension. The adaptive weighted fusion algorithm is adopted to integrate and calculate the index scores of the two dimensions and their corresponding weights. Based on the comprehensive reliability score result, the data-driven attribution analysis is performed to locate the reliability margin insufficient link and management defects, and the contribution of each attribution factor is quantified. ​ 6. The closed-loop management method for reliability of power transmission and distribution circuits according to claim 4, characterized in that: ​ Based on the comprehensive reliability score and the sub-index data, the key equipment factors and management factors affecting reliability are automatically identified by an interpretable machine learning model; By quantifying the contribution of each factor to the score result, the root cause of the decline in reliability level is located.

7. The closed-loop management method for reliability of power transmission and distribution circuits according to claim 4, characterized in that: The automatic identification of the key equipment factors and management factors affecting reliability based on the comprehensive reliability score and the sub-index data by the interpretable machine learning model comprises, An analysis data set is constructed, historical comprehensive scores and sub-indexes are collected to construct a training set, score rules are set, and the interpretable machine learning model automatically extracts the core rules affecting score classification through decision tree learning; The root cause of the decline in reliability level is located by quantifying the contribution of each factor to the score result, which comprises, Based on the path backtracking mechanism of the interpretable machine learning model, the specific loop type and index are located, and the direct impact weight of the total score is quantified through feature importance.

8. A closed-loop management system for power transmission and transformation circuit reliability, applying the closed-loop management method for power transmission and transformation circuit reliability according to any one of claims 1-7, characterized in that, It comprises: a data acquisition and preprocessing module, a multi-dimensional index calculation and scoring module, a comprehensive evaluation and fusion analysis module, a strategy generation and decision support module, and a closed-loop feedback and optimization module; The data acquisition and preprocessing module is based on the reliability measurement and comprehensive evaluation of the loop operation state to calculate the reliability evaluation index of the power transmission and transformation loop; The multi-dimensional index calculation and scoring module calculates the comprehensive management evaluation index of the equipment and facilities based on the equipment full life cycle management efficiency, and calculates the score of each index based on the completion rate result and the preset score rule; The comprehensive evaluation and fusion analysis module constructs a comprehensive scoring model, integrates the power transmission and transformation loop reliability index and the equipment and facility management evaluation index through a self-adaptive weighted fusion method, and outputs the comprehensive reliability score; The strategy generation and decision support module is based on the comprehensive reliability score result, and through data-driven attribution analysis, the reliability margin deficiency link and management defects are located, and the contribution of each attribution factor is quantified; The closed-loop feedback and optimization module reversely drives the maintenance strategy adjustment according to the attribution analysis result, and realizes the closed-loop management of power grid reliability. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the closed-loop management method for the power transmission and transformation loop reliability in any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the closed-loop management method for the power transmission and transformation loop reliability in any one of claims 1 to 7.

Images