Power equipment maintenance plan intelligent arrangement data model based on optimization solver

Abstract

The invention relates to a power equipment maintenance plan intelligent arrangement data model based on an optimization solver, and the model employs a digital optimization model constructed by the optimization solver, and automatically arranges a maintenance plan through the optimization algorithm of the model, thereby achieving the on-time completion of tasks, the shortest distance, reasonable distribution of key tasks, and efficient utilization of resources. And finally, a detailed scheduling table covering the accurate time sequence of the tasks, personnel allocation, predicted completion time, driving time and minimum rest time is generated, so that the scientificity, rationality and high efficiency of power grid equipment maintenance plan arrangement are effectively improved, and the online operation duty is ensured to accord with regulations and meet the power grid operation requirements.

Description

Technical Field

[0001] The present invention relates to the field of power system maintenance management, and specifically to an intelligent scheduling data model for power equipment maintenance plan based on an optimization solver. The model uses a digital optimization model and a solving algorithm to comprehensively consider multiple complex constraints such as task completion time, maintenance distance, equipment cannot be stopped at the same time, maintenance personnel limit, and maintenance task continuity, so as to achieve automated, intelligent scheduling and optimization of power grid equipment maintenance tasks. Technical Background

[0002] The maintenance of power grid equipment is an important part of ensuring the safe and reliable operation of the power system. However, with the expansion of the scale of power networks and the increase in power grid equipment, the current maintenance of power grid equipment faces many major challenges. In terms of equipment, serious aging, diverse models and standards lead to difficulties in status monitoring and poor compatibility. Traditional inspection methods are difficult to meet the needs and difficult to detect hidden dangers in advance. At the same time, the diversity of equipment increases the difficulty and cost of maintenance. In terms of maintenance technology, traditional technology is backward, the degree of intelligence is low, and the fault diagnosis and processing capabilities are limited. Although the data has increased, the collection and analysis problems are prominent, and it is impossible to effectively assist decision-making. In terms of human resources, there is a shortage of professionals, and the skill update cannot keep up with the development of equipment technology, making it difficult to cope with complex tasks. In terms of safety, the maintenance environment is high-voltage and dangerous, with multiple safety risks and difficult management. From the perspective of external environment and resource allocation, natural and geographical conditions affect equipment operation, and resource allocation and department coordination are difficult in special periods, affecting the progress and quality of maintenance. These challenges restrict the efficient implementation of power grid equipment maintenance.

[0003] According to the search and analysis of the technical team of this study, the current technical research similar to this study at home and abroad includes the following aspects.

[0004] The distribution network control artificial intelligence system of the power supply service command center of the State Grid Zhengzhou Power Supply Company can autonomously analyze the power outage equipment in the maintenance application, intelligently analyze the optimal transfer strategy in combination with the network topology, automatically analyze the distribution network "power outage scope, power grid risk, safety measures", intelligently optimize the operation mode, generate dispatch order tickets with one click, and autonomously carry out "maintenance plan, work ticket, dispatch order ticket" safety verification. The system has greatly solved the problems of discrete power grid resources and reduced operational safety control capabilities, improved efficiency, and increased the accuracy of ticketing to more than 98%. The system and manual safety double audit can be completed in 20 minutes to the execution stage, and the efficiency is improved by more than 60%.

[0005] The AI ​​power supply service command system of State Grid Jiangsu Electric Power Co., Ltd. has functions such as intelligent perception of fault power outages, intelligent arrangement of maintenance plans, and intelligent management of equipment abnormalities. In terms of intelligent arrangement of maintenance plans, the system has 11 intelligent analysis functions, including frequent power outage analysis, large-time household and large-duration calculation, main and distribution network plan coordination, and team carrying capacity calculation. It can deeply integrate fault power outage information with meteorological warning data, realize intelligent tracking of the entire process and time period of the power outage plan, accurately identify frequent power outages and warn of potential risks in advance, and provide support for the scientific and reasonable arrangement of maintenance plans.

[0006] The State Grid Xuzhou Tongshan District Power Supply Company has developed and improved cross-system data interfaces to achieve efficient transmission and sharing of maintenance plan information between OMS and PMS. Medium-voltage power outage maintenance, live operation maintenance, and low-voltage power outage maintenance plans can all be "reported with one click" from the PMS system to the OMS system. The company has also innovatively established a full-cycle rolling compilation and flexible balance system of "year, quarter, month, week, and day" to achieve the "risk rolling verification" function, accurately verify various risks of maintenance plans, reduce repeated power outages, and reduce the number of households during power outages. In addition, the company explored the construction of a "full-volume dispatch information resource pool" system and a "power outage plan execution evaluation" application to enhance the dispatcher's ability to perceive the power outage and restoration of on-site equipment, and encourage reporting units to optimize power outage plans.

[0007] The patent for "A method for intelligent allocation and management of meter box maintenance based on data analysis" applied by China Electric Equipment Shandong Electronics and State Grid Tibet Power Rutog County Power Supply selects preferred faulty meter boxes according to the urgency of the faults of each faulty meter box, matches and selects the various maintenance personnel, and then obtains the recommendation degree of each preferred maintenance personnel based on the straight-line distance between each preferred maintenance personnel and the preferred faulty meter box, the workload of each preferred maintenance personnel, the time matching degree, and the maintenance quality evaluation coefficient, and then selects the preferred maintenance personnel to better match the maintenance personnel's capabilities with the fault types, thereby improving the accuracy and success rate of fault handling.

[0008] The production maintenance model implemented in the United States reflects the diversity and flexibility of maintenance methods. It not only accepts the viewpoints of logistics engineering, but also considers equipment reliability issues and the content of no-maintenance processing; Germany has two maintenance models: intensive and extensive. Intensive maintenance focuses on exerting the potential of equipment and trying to use preventive maintenance methods to increase the service life of power generation equipment; extensive maintenance does not require high requirements for the exertion of equipment potential and the increase of service life, and more post-maintenance methods are used; France stipulates that most equipment is preventive maintenance, and other parts are coordinated maintenance strategies assisted by scheduled maintenance and condition maintenance; Japan uses the total production maintenance model (TPM), which is a comprehensive application of diversified modern management measures in enterprise production. It takes equipment efficiency as the primary goal and ensures preventive maintenance for the normal operation of power generation equipment throughout its life.

[0009] In general, the intelligent scheduling of power equipment maintenance plans is developing in the direction of intelligence, efficiency and precision. By using various technologies and methods, the maintenance plan can be optimized to improve the reliability and economy of power system operation. However, the development levels of different regions and enterprises may vary, and the specific applications and effects may also be different. At the same time, technology is still constantly improving and improving, and more advanced intelligent scheduling systems and methods may appear in the future. In this context, how to reasonably and efficiently schedule maintenance tasks, minimize the impact on the operation of the power system, optimize the maintenance path and shorten the task time, has become an urgent problem to be solved in the power industry. The introduction of optimization algorithms and mathematical models provides new ideas for solving this problem. Among them, the CPLEX optimization solver has become an ideal tool for scheduling maintenance plans due to its excellent performance in handling large-scale and complex constraints. Summary of the invention

[0010] The present invention establishes a digital optimization model for power grid equipment maintenance tasks through an optimization solver, comprehensively considers a variety of complex constraints, sets the objective function, uses the optimization algorithm to automatically arrange the maintenance plan and generate a scheduling table, and optimizes the personnel path based on the geographic information system. It also has the ability to dynamically adjust and establish an evaluation system to solve various technical problems in the intelligent arrangement of power grid equipment maintenance plans.

[0011] A data model for intelligent scheduling of power equipment maintenance plans based on an optimization solver. The data content of this data model includes: establishing a digital optimization model of power grid equipment maintenance tasks through an optimization solver; automatically scheduling maintenance plans through an optimization algorithm; and generating a specific scheduling table for maintenance tasks based on the solution results of the digital optimization model.

[0012] As a preferred technical solution of the present invention, the digital optimization model has an objective function that aims to simultaneously minimize the total distance of the maintenance task and the execution time of the operation ticket, and when constructing the objective function, the travel time of the line operation team from the starting point to each maintenance task location at a certain speed and the idle time required by the line operation team after completing each operation ticket are comprehensively considered.

[0013] As a preferred technical solution of the present invention, specifically, a digital optimization model of power grid equipment maintenance tasks is constructed with the help of an optimization solver, and the model at least includes the following data content: time constraints of maintenance tasks: the task execution time range limited by the planned decommissioning time, planned recommissioning time and on-duty time of the line operation team involved in the operation ticket; location optimization: optimizing task allocation based on the geographical relationship between each maintenance task location and the starting location of the line operation team and the distance relationship between different task locations to reduce travel time; equipment cannot be stopped at the same time constraint: key equipment maintains an uninterrupted continuous operation state during the entire maintenance process; maintenance number limit constraint: ensure that the number of personnel participating in the maintenance work at any time point does not exceed the total amount of human resources that can be deployed; key task allocation constraint: each line operation team can only perform one key task at most to achieve a reasonable allocation of key tasks; continuity of maintenance tasks: reduce the idle time after each operation to ensure the efficiency and continuity of the line operation team's task execution and other complex constraints.

[0014] As a preferred technical solution of the present invention, in the model, the optimization result of the maintenance plan reasonably allocates the maintenance tasks by considering the different working hours of the line operation teams to ensure that each line operation team will not encounter conflicts due to taking on tasks in multiple locations at the same time during the execution of the tasks, and reduce the idle time of the line operation team between each operation task, thereby improving the efficiency of the maintenance work.

[0015] As a preferred technical solution of the present invention, the model is provided with a submodule for dynamically adjusting the scheduling of maintenance tasks in parallel, which can quickly insert emergency tasks into the existing maintenance plan and adjust other related tasks in time when faced with an emergency.

[0016] As a preferred technical solution of the present invention, the model is provided with maintenance personnel path optimization in parallel, which is based on geographic information system data and accurately calculates the shortest path from the starting point to each maintenance task location through geographic information analysis of each maintenance task location and the starting point of the line operation team in the geographic information system data to improve the overall maintenance efficiency.

[0017] As a preferred technical solution of the present invention, the model is provided in parallel with a data measurement submodule that is compatible with the number of decommissioning tickets and recommissioning tickets involved in each maintenance plan. When the number of decommissioning tickets for a maintenance plan exceeds six, a mechanism is automatically started to arrange multiple line operation shifts to participate in the execution of the maintenance plan at the same time to avoid delays in the maintenance plan due to excessive workload.

[0018] As a preferred technical solution of the present invention, the scheduling table includes but is not limited to the specific work content of each maintenance task, clear assignment to the line operation team to perform the task, accurate estimation of the completion time of the task, accurate calculation of the travel time of the line operation team to the task location, and strict regulations on the minimum rest time required for the line operation team after executing the operation ticket. The above regulations ensure that the line operation team complies with the relevant regulations on work and rest while performing tasks.

[0019] As a preferred technical solution of the present invention, a self-assessment module is additionally provided outside the model, and the data content of the module includes: Define the evaluation index system: including but not limited to the task completion timeliness index: used to measure whether the maintenance task is completed within the planned time, and evaluated by calculating the difference between the actual completion time and the planned completion time; resource utilization index: evaluate the utilization of resources, resources include but are not limited to maintenance personnel and equipment; route rationality index: by comparing the degree of proximity between the actual maintenance route and the theoretical shortest route, the effect of the model on task allocation in route optimization is judged; key task execution effect index: examine the priority arrangement and execution of key tasks; Verification using historical data: collect relevant data from past power grid equipment maintenance tasks and input these data into the constructed model, run the model to obtain simulation results, and analyze the performance of the model in actual scenarios by comparing the simulation results with historical actual conditions; Conduct simulation tests: Use the model to generate corresponding maintenance plans by setting different maintenance task scenarios, and analyze the accuracy of the model-generated plans in various scenarios; Through multiple simulation tests, statistically analyze the data of various evaluation indicators of the model in different scenarios to comprehensively evaluate the performance of the model; Introduce expert review: Invite experts in the field of power equipment maintenance to evaluate the model.

[0020] The beneficial effects of adopting the above technical solution are: the adoption of the above solution has produced beneficial effects in many aspects. In terms of maintenance planning, comprehensive consideration of multiple constraints is used to achieve reasonable scheduling, while optimizing the task distance and execution time to improve efficiency and feasibility. In terms of task allocation, the working hours and ticket volume of the line operation team are taken into account, which improves the rationality of task allocation and resource utilization efficiency, and avoids conflicts and delays. In terms of responding to emergencies, the dynamic adjustment function enhances the flexibility of the plan. In terms of personnel work, geographic information is used to optimize the path and reduce travel time. In terms of evaluation and improvement, the evaluation system promotes continuous optimization of the model, improves the scientificity, efficiency, reliability and adaptability of power grid equipment maintenance management, ensures the stable operation of the power grid, and improves economic and social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of the intelligent arrangement of the maintenance plan of the present invention.

[0022] Figure 2 This is an example diagram of the demand description, team situation and rule description when the present invention is applied.

[0023] Figure 3 It is an example data diagram when the present invention is applied.

[0024] Figure 4 It is an example diagram of the solution result when the present invention is applied.

[0025] Figure 5 This is an example diagram of data service description when the present invention is applied.

[0026] Figure 6 This is an example diagram for explaining the solver code when the present invention is applied.

[0027] Figure 7 This is an example diagram of the benefit function when the present invention is applied.

[0028] Figure 8 This is an example diagram of the dynamic programming algorithm when the present invention is applied. DETAILED DESCRIPTION

[0029] The following examples describe the present invention in detail. In the description of the following examples, specific details such as specific system structures, technologies, etc. are proposed for illustration rather than limitation, so as to provide a thorough understanding of the present application embodiments. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, the detailed description of well-known systems, devices and methods is omitted to prevent unnecessary details from hindering the description of the present application.

[0030] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements and components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components. It should also be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the items listed in association and all possible combinations, and includes these combinations. As used in the present specification and the appended claims, the term "if" can be interpreted as "when..." or "once" or "in response to determination" or "in response to detection" according to the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "once it is determined" or "in response to determination" or "once [described condition or event] is detected" or "in response to detection [described condition or event]" according to the context.

[0031] In addition, in the description of the present application specification and the attached claims, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. The reference to "one embodiment" or "some embodiments" described in the present application specification means that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in the different parts of this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0032] Example 1: Establishing a digital optimization model for power grid equipment maintenance tasks through an optimization solver 1. Clarify the objective function The goal is to minimize the total distance S of the maintenance task and the execution time T of the operation ticket. During the construction process, the travel time of the line operator needs to be comprehensively considered. and free time after the operation ticket is completed For example, the line operator's travel speed is set to v (assuming v = 10km / h), and it travels from the starting point (the latitude and longitude of the starting point are known, such as latitude 31.014016, longitude 121.227950) to each maintenance task location. Suppose the total distance of the maintenance task is S, the operation ticket execution time is T, and the line operator's travel time from the starting point to the i-th maintenance task location is , the idle time after completing the i-th operation ticket is , then the objective function can be expressed as: minimizes(S+T+ + ), where n is the total number of maintenance tasks.

[0033] For travel time , according to the distance formula d= (in( , ) is the starting point coordinate, ( , ) is the coordinate of the i-th maintenance task location) calculate the distance , combined with the speed v, we get = . Free time Set according to actual requirements (e.g. at least 15 minutes).

[0034] 2. Set constraints Time Constraints Specify the planned outage time of the operation ticket and planned time of decommissioning , which limits the executable interval of each maintenance task on the timeline.

[0035] At the same time, the working hours of different shifts of the line operation team should be considered, such as 0:00-9:00 for line operation 1 and 2, 9:00-18:00 for line operation 3 and 4, and 18:00-24:00 for line operation 5 and 6. Any maintenance task must be arranged within the working hours of the corresponding line operation team, that is, and (in and is the actual start and end time of the ith maintenance task, and is the start and end time of the j-th line operation class).

[0036] Position optimization constraints Based on the geographical relationship (latitude and longitude information) between each maintenance task location and the starting position of the line operation team and the distance relationship between different task locations, calculate the distance between each task location. Constraints are set in the model so that task allocation follows the distance optimization principle as much as possible and the transfer time of the line operation team between task locations is reduced, that is, the total travel time is minimized.

[0037] Devices cannot be stopped at the same time Analyze the relationship between power grid equipment and identify key equipment. For key equipment k, multiple maintenance tasks involving the equipment cannot be scheduled at the same time. That is, if equipment k is in maintenance status in task i ( =1 means that equipment k is repaired in task i, =0 means not under maintenance), then in other tasks j(j i) The equipment cannot be repaired at the same time. (The total number of maintenance tasks).

[0038] Maintenance personnel limit Determine the total number of maintenance personnel N that can be deployed and the standard number of people in each line operation team M. Set constraints in the model so that the number of people involved in maintenance work at any time does not exceed the total amount of human resources that can be deployed, that is, (in is the number of people who perform the i-th maintenance task), and .

[0039] Key task allocation constraints Mark the key tasks and set each line operation class to perform at most one key task. If task i is a key task ( =1 means task i is a key task, =0 means non-key task), then for each line operation class b, 1(i Indicates that task i is assigned to line operation class b).

[0040] Continuity constraints of maintenance tasks In order to reduce the idle time after each operation, constraints are set in the model to make the connection between adjacent maintenance tasks closer. For example, according to the order of tasks, the time interval between adjacent tasks cannot be too long, that is, - （ is the maximum time interval allowed, set according to actual conditions).

[0041] 3. Select optimization solver and algorithm Select a suitable optimization solver, such as the CPLEX optimization solver, which has powerful computing power and optimization algorithm library, can handle large-scale integer programming and mixed integer programming problems, and is suitable for complex constraints and multivariable optimization in this model. Determine the optimization algorithm applicable to this solver, such as the branch and bound algorithm, cutting plane algorithm, etc., and input the constructed objective function and constraints into the optimization algorithm for calculation.

[0042] 4. Model solution and verification Start the optimization solver, and the algorithm iterates the calculation according to the input objective function and constraints. During the calculation process, the variables such as the distribution and time arrangement of the maintenance task are constantly adjusted to find a solution that satisfies all constraints and makes the objective function optimal. Verify the solution results to check whether all constraints are met, such as time constraints, equipment operation constraints, etc. At the same time, analyze whether the objective function value is reasonable, for example, whether the total distance of the maintenance task and the execution time of the operation ticket achieve the expected optimization effect. If the result does not meet the requirements, check whether the model construction is accurate and the constraints are reasonable, and make adjustments and recalculations if necessary.

[0043] Example 2: Automatically arrange maintenance plans through optimization algorithms 1. Choose the right optimization algorithm Based on the characteristics of the digital optimization model of power grid equipment maintenance tasks, select algorithms that can handle complex constraints and multi-objective optimization problems. For example, algorithms based on integer programming or mixed integer programming, such as branch and bound algorithms and cutting plane algorithms, can be used. These algorithms are often used in optimization solvers and are suitable for solving problems involving multiple constraints and multiple objectives in this scenario.

[0044] Consider the computational efficiency and accuracy of the algorithm to ensure that a better solution can be obtained within a reasonable time. For example, for large-scale maintenance task data, some efficient heuristic algorithms or hybrid algorithms that combine meta-heuristic algorithms with exact algorithms may be more applicable, which can speed up the solution while ensuring a certain degree of accuracy.

[0045] 2. Data preparation and input Collect various data related to the maintenance plan, including but not limited to: equipment information: equipment type, equipment status, relationship between equipment, equipment location; maintenance task information: task content, task priority, operation ticket related time, task estimated time; personnel information: number of maintenance personnel, personnel composition of each line operation team, personnel skill level, line operation team work schedule; geographic information: geographical relationship between each maintenance task location and the starting position of the line operation team, distance relationship between different task locations; organize and input these data in the format required by the optimization algorithm to ensure the accuracy and completeness of the data. For example, convert the equipment non-simultaneous stop relationship into a mathematical constraint expression, and convert the personnel working time limit into a time interval constraint that the algorithm can recognize.

[0046] 3. Algorithm execution and plan generation Start the optimization algorithm, and the algorithm begins to calculate based on the input data; during the calculation process, the algorithm will continuously try different maintenance task allocation schemes, time arrangement combinations, etc., to evaluate the feasibility and pros and cons of each scheme. For example, for a possible maintenance plan arrangement, the algorithm will calculate its total distance, operation ticket execution time, whether it violates the constraint that the equipment cannot be stopped at the same time, whether the personnel allocation is reasonable, and other factors; after multiple iterations and searches, the algorithm gradually finds a maintenance plan that meets all constraints and makes the objective function optimal or close to optimal. This plan will clarify the execution order of each maintenance task, the assigned line operation shift, the start time, the end time and other detailed information, so as to complete the automatic arrangement of the maintenance plan.

[0047] 4. Result processing and adjustment Check and analyze the maintenance plan results generated by the algorithm to see if there are any unreasonable or inconsistent with the actual situation. For example, check whether a line operation team has performed multiple complex tasks in a short period of time, causing fatigue or failure to complete the tasks on time, or whether there are problems such as long time intervals between tasks leading to waste of resources. If problems are found in the results, adjust the algorithm parameters, constraints or data according to the actual situation, and then re-run the algorithm for optimization until a more satisfactory maintenance plan result is obtained. For example, if a constraint is found to be too strict and there is no solution or the solution is unreasonable, the constraint can be appropriately relaxed and calculated again to obtain a more feasible plan. At the same time, the results can also be fine-tuned in combination with manual experience to make the maintenance plan more operational and reasonable.

[0048] Example 3: Generate a specific scheduling table for maintenance tasks based on the solution results 1. Task information organization Extract detailed information of each maintenance task from the solution of the optimization algorithm, including task number, task content, and task location; determine the priority of each maintenance task, which helps to reasonably allocate resources and arrange time during the scheduling process. For example, key tasks may require priority for experienced personnel and tighter time windows.

[0049] 2. Clear staffing allocation According to the line operation team assigned to each task in the solution result, the specific personnel list or personnel number for performing the task shall be listed in detail in the scheduling table. If there is a division of labor within the line operation team, it should also be noted in the scheduling table to ensure that the executors of each task are clear and the responsibilities are clear; considering the skill level and work experience of the personnel, try to assign complex tasks to highly skilled and experienced personnel, while taking into account the balance of personnel workload to avoid overwork of some personnel and affecting work quality and efficiency.

[0050] 3. Schedule confirmation Record the planned start time of each maintenance task and planned end time These two times are directly derived from the solution results, ensuring that the tasks are executed in the optimized time order; calculate and list the estimated time for each task ( = - ), so that staff can understand the workload and time requirements of the task in advance and arrange the work rhythm reasonably; at the same time, clarify the travel time for each line operation team to the next task location after completing a task , and the minimum rest time required after completing each operation ticket (e.g. at least 15 minutes). Such time information helps to control the overall progress of maintenance and ensure that personnel have proper rest during work, in compliance with labor safety regulations.

[0051] 4. Schedule format design and presentation Design a clear and intuitive schedule format. A common format can be a table with the following columns: task number, task content, task location, priority, executor, planned start time, planned end time, estimated time, travel time, rest time, etc. You can use spreadsheet software or professional project management software to create and manage schedules for easy editing, updating and sharing. Present the schedule in a visual way to relevant personnel, such as maintenance personnel, management personnel, etc., to ensure that everyone can clearly understand their task arrangements and the progress of the overall maintenance plan.

[0052] 5. Dynamic update and adjustment mechanism During the maintenance process, if unexpected situations occur and the original plan needs to be adjusted, update the schedule in a timely manner. Re-run the optimization algorithm according to the actual situation or make manual adjustments based on experience and actual constraints to ensure that the schedule always reflects the latest maintenance plan arrangements; establish effective information communication channels to ensure that all relevant personnel can obtain updated information on the schedule in a timely manner to avoid work errors or delays due to poor information flow. For example, relevant personnel can be notified of changes to the schedule in a timely manner through instant messaging tools, workflow systems, or on-site announcements.

[0053] Example 4: Comprehensive evaluation and optimization of intelligent scheduling model for power equipment maintenance plan 1. Define the evaluation indicator system 1. Task completion timeliness indicator Suppose the planned completion time of a maintenance task is The actual completion time is , then the task completion timeliness index = - For example, if a transformer maintenance task is planned to be completed within 5 working days, but it actually takes 6 working days, then =6-5=1 day. The larger the indicator value, the longer the task completion will be. If it actually takes 4 working days, then =4-5=-1 day. The smaller the indicator value, the earlier the task will be completed.

[0054] 2. Resource utilization index (taking maintenance personnel as an example) Statistics show that during a maintenance cycle, the total working time of maintenance personnel is (Assuming that one maintenance worker works 8 hours a day, one cycle is 10 days, and there are 5 maintenance workers, then =8x10x5=400 hours). In actual maintenance work, the maintenance personnel spends (obtained by recording the cumulative working time of each maintenance personnel on each task). Then the maintenance personnel resource utilization index = .like =300 hours, then = =0.75, indicating that the utilization rate of maintenance personnel in this cycle is 75%. For equipment resource utilization, the ratio of the actual operation time of the equipment for maintenance to the total time that the equipment can be used for maintenance can be calculated similarly.

[0055] 3. Route rationality index Assuming that a maintenance involves three task locations, the actual maintenance distance calculated by the model is = 50 km. The theoretical shortest distance to these three mission locations is calculated by the Geographic Information System (GIS) as =45 km, then the distance rationality index = = ≈1.11. The closer this index is to 1, the better the model is at optimizing the distance for task allocation; if the index value is greater than 1 and deviates greatly from 1, it means that the actual distance is much different from the theoretical shortest distance, and there may be room for improvement in the model in terms of distance optimization.

[0056] 4. Key task execution effect indicators For key tasks, record their planned start time and actual start time, as well as planned completion time and actual completion time. Calculate the start time deviation (start time deviation = actual start time - planned start time) and completion time deviation (actual completion time - planned completion time) of key tasks. If the start time deviation = 0 and the completion time deviation = 0, it means that the key tasks are strictly executed according to the plan; if the deviation value is large, it means that the key tasks are not well executed, and the model may need to be adjusted in the priority arrangement of key tasks. At the same time, it can also be examined whether the resource allocation during the execution of key tasks is sufficient, whether the progress of key tasks is hindered due to interference from other tasks, etc.

[0057] 2. Verification using historical data 1. Data collection and organization Obtain maintenance task data for the past year from the power grid equipment management system, including detailed information on each maintenance task, such as task type (equipment maintenance, fault repair, etc.), task location, task start and end time, list of personnel involved in the maintenance, equipment used and its operating status, and distance records during the maintenance process. At the same time, collect historical equipment operation data related to the task, such as operating parameters before equipment failure, failure type and frequency, etc. These data help to more fully understand the background and conditions of the maintenance task.

[0058] 2. Model input and simulation operation The collected historical data is sorted and input in the format required by the model. For example, the task location information is converted into geographic coordinate format for distance calculation, and the personnel and equipment information is matched with the resource constraints in the model. The constructed maintenance plan model is run to obtain the simulated maintenance plan results, including task allocation plan, time arrangement, personnel and equipment usage, etc.

[0059] 3. Results comparison and analysis Compare the simulation results with the historical actual situation. For example, for the timeliness of task completion, check the difference between the task completion time in the simulation results and the historical actual completion time, and calculate the deviation rate of the task completion timeliness indicator ( 00%）。 If the deviation rate is small (e.g. within ±5%), it means that the model has good accuracy in predicting task completion time; if the deviation rate is large, it is necessary to analyze the reasons, which may be that the model does not consider certain constraints accurately enough, or that there are abnormalities in the historical data that affect the accuracy of the model. Similar comparative analysis is also conducted for indicators such as resource utilization and route rationality to find out the aspects where the model performs well and where it is insufficient, providing a basis for model improvement.

[0060] 3. Conduct simulation test 1. Scene Setting Set maintenance task scenarios of different scales, such as small scenarios containing 5-10 maintenance tasks, medium-sized scenarios containing 15-20 tasks, and large scenarios containing more than 30 tasks. At the same time, consider different task distribution situations, including the degree of dispersion of task locations (concentrated in one area or distributed in multiple different areas), the urgency of tasks (some tasks are urgent tasks and need to be arranged first), the diversity of equipment types and fault types (involving different types of power equipment and multiple fault modes), and other factors. For example, scenario one is set as 5 devices in a substation that need to be repaired, the tasks have the same urgency, and the equipment type is relatively single; scenario two is set as 15 devices in different areas of a city that need to be repaired, 3 of which are emergency tasks, and the equipment types include transformers, circuit breakers, transmission lines, and other types.

[0061] 2. Model operation and planning analysis For each set scenario, the model is used to generate a corresponding maintenance plan. The accuracy of the plan generated by the model is analyzed, and the evaluation is conducted from aspects such as the rationality of task allocation (whether tasks are reasonably allocated according to personnel skills and equipment characteristics), the feasibility of time arrangement (whether various time constraints are met and will not cause excessive fatigue of personnel or task delays), and the effectiveness of resource utilization (whether personnel and equipment resources are fully utilized to avoid idle or excessive resource tension). For example, in one scenario, check whether the model assigns complex equipment maintenance tasks to experienced maintenance personnel, whether the time intervals between different tasks are reasonably arranged to avoid personnel working continuously for too long, and whether the existing equipment resources are fully utilized without causing equipment idleness and waste.

[0062] 3. Multiple tests and indicator statistics Conduct multiple simulation tests, using different random seeds or parameter settings for each test (if there are adjustable parameters in the model) to increase the comprehensiveness and reliability of the test. Collect data on various evaluation indicators of the model in different scenarios, such as calculating the average and standard deviation of the task completion timeliness indicator after multiple tests, the maximum, minimum and average values ​​of the resource utilization indicator, and the distribution range of the route rationality indicator. Through these statistical data, comprehensively evaluate the performance of the model in different situations and understand the stability and adaptability of the model. For example, if the standard deviation of the task completion timeliness indicator is small in multiple tests, it means that the model's prediction of task completion time in different scenarios is relatively stable; if the maximum and minimum values ​​of the resource utilization indicator are far apart, it may mean that the model has large fluctuations in resource allocation in certain scenarios and needs further optimization.

[0063] IV. Introducing Expert Review 1. Expert selection and invitation Invite experts in the field of power equipment maintenance, including front-line maintenance engineers with rich practical experience, power system operation and management experts, power equipment R&D experts, etc. These experts come from different professional backgrounds and work fields and can comprehensively evaluate the model from multiple perspectives. For example, invite 5-10 experts, including at least 3 engineers with more than 10 years of maintenance experience, 2 experts in power system operation and management, and 1 power equipment R&D expert.

[0064] 2. Review content and method Provide the experts with a detailed introduction of the model, including the model's objective function, constraints, algorithm principles, evaluation index system, etc. The experts review the model based on their own experience and professional knowledge. The review content includes: Reasonableness of the objective function: Determine whether the model's goal of minimizing the total distance of maintenance tasks and the execution time of operation tickets meets the needs of actual maintenance work, and whether there are other important factors that need to be considered and included in the objective function, such as the impact of equipment service life and comprehensive consideration of maintenance costs.

[0065] Completeness of constraints: Check whether the constraints considered by the model (such as time constraints, equipment cannot be stopped at the same time, and the number of maintenance personnel is limited) are comprehensive, and whether some important constraints commonly seen in actual work are omitted, such as restrictions on maintenance work due to special weather conditions, and specific requirements for the maintenance sequence of different equipment.

[0066] Applicability of the algorithm: Evaluate whether the optimization algorithm used can effectively handle the complex constraints and multi-objective optimization problems in the model, whether there are more suitable algorithms or directions for algorithm improvement, such as whether it can be combined with other emerging algorithms to improve the efficiency and accuracy of the model solution.

[0067] Effectiveness of the evaluation index system: Analyze whether the defined evaluation indicators (task completion timeliness, resource utilization, route rationality, key task execution effect, etc.) can fully and accurately reflect the performance of the model, and whether some indicators need to be supplemented or adjusted to better evaluate the value of the model in practical applications.

[0068] Expert review can be conducted in a variety of ways, such as meeting discussion, written review opinions, online questionnaires, etc. For example, first organize an expert review meeting to let the experts discuss the advantages and disadvantages of the model face to face, then ask the experts to fill in detailed written review opinions, and finally collect experts' suggestions on the direction of model improvement through online questionnaires.

[0069] 3. Improve the model based on review comments Summarize the expert review opinions and improve the model. According to the expert's suggestions for improving the objective function, review and adjust the composition of the objective function; based on the supplementary opinions on the constraints, improve the setting of the constraints in the model; based on the evaluation of the algorithm's applicability, consider using the algorithm recommended by the experts or optimizing the existing algorithm; optimize the evaluation index system according to the adjustment suggestions of the evaluation index system. For example, if the expert suggests adding a maintenance cost factor to the objective function, further research can be conducted on how to quantify the maintenance cost and incorporate it into the objective function; if the expert points out that the model omits a special maintenance sequence constraint for a certain equipment, add the constraint to the model in a timely manner. The improved model is tested and evaluated again to ensure that the model is continuously improved and optimized, and to improve its effectiveness and practicality in the intelligent scheduling of power equipment maintenance plans.

[0070] In various embodiments, the hardware implementation of the technology can directly adopt existing intelligent devices, including but not limited to industrial computers, PCs, smart phones, handheld stand-alone computers, floor-standing stand-alone computers, etc. Its input device preferably adopts a screen keyboard, its data storage and calculation module adopts existing memory, calculator, controller, its internal communication module adopts existing communication ports and protocols, and its remote communication adopts existing GPRS network, World Wide Internet, etc.

[0071] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0072] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0073] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. The intelligent scheduling data model of power equipment maintenance plan based on optimization solver is characterized by: This data model includes: data module A, which establishes a digital optimization model for power grid equipment maintenance tasks through an optimization solver; data module B, which automatically arranges maintenance plans through an optimization algorithm; and data module C, which generates a specific scheduling table for maintenance tasks based on the solution results of the digital optimization model.

2. The intelligent arrangement data model of power equipment maintenance plan based on optimization solver according to claim 1 is characterized in that: In data module A, the digital optimization model has an objective function that aims to minimize the total distance of maintenance tasks and the execution time of operation tickets at the same time, and when constructing the objective function, the travel time of the line operation team from the starting point to each maintenance task location at a certain speed and the idle time required by the line operation team after completing each operation ticket are comprehensively considered.

3. The intelligent arrangement data model of power equipment maintenance plan based on optimization solver according to claim 2 is characterized in that: Specifically, a digital optimization model of power grid equipment maintenance tasks is constructed with the help of an optimization solver, and the model includes at least the following data content: time constraints of maintenance tasks: the task execution time range limited by the planned decommissioning time, planned recommissioning time and on-duty time of the line operation team involved in the operation ticket; location optimization: optimizing task allocation based on the geographical relationship between each maintenance task location and the starting location of the line operation team and the distance relationship between different task locations to reduce travel time; equipment cannot be stopped at the same time constraint: key equipment maintains an uninterrupted continuous operation state during the entire maintenance process; maintenance number limit constraint: ensure that the number of personnel participating in the maintenance work at any time point does not exceed the total amount of human resources that can be deployed; key task allocation constraint: each line operation team can only perform one key task at most to achieve a reasonable allocation of key tasks; continuity of maintenance tasks: reduce the idle time after each operation to ensure the efficiency and continuity of the line operation team's task execution and other complex constraints.

4. The intelligent arrangement data model of power equipment maintenance plan based on optimization solver according to claim 3 is characterized in that: The digital optimization model is provided with a submodule for dynamically adjusting the scheduling of maintenance tasks in parallel, so that when faced with an emergency, emergency tasks can be quickly inserted into the existing maintenance plan and other related tasks can be adjusted in a timely manner.

5. The intelligent arrangement data model of power equipment maintenance plan based on optimization solver according to claim 3 is characterized in that: The digital optimization model is equipped with maintenance personnel path optimization in parallel. Based on geographic information system data, the shortest path from the starting point to each maintenance task location is accurately calculated through geographic information analysis of each maintenance task location and the starting point of the line operation team in the geographic information system data to improve the overall maintenance efficiency.

6. The intelligent arrangement data model of power equipment maintenance plan based on optimization solver according to claim 3 is characterized in that: The digital optimization model is parallelly equipped with a data evaluation submodule that is compatible with the number of decommissioning tickets and recommissioning tickets involved in each maintenance plan. When the number of decommissioning tickets for a maintenance plan exceeds six, the mechanism is automatically activated to arrange multiple line operation teams to participate in the execution of the maintenance plan at the same time to avoid delays in the maintenance plan due to excessive workload.

7. The intelligent arrangement data model of power equipment maintenance plan based on optimization solver according to claim 1 is characterized in that: In data module B, the optimization result of the maintenance plan reasonably allocates the maintenance tasks by considering the different working hours of the line operation teams to ensure that each line operation team will not encounter conflicts when taking on tasks in multiple locations at the same time during the execution of the tasks, and reduce the idle time of the line operation team between each operation task, thereby improving the efficiency of maintenance work.

8. The intelligent arrangement data model of power equipment maintenance plan based on optimization solver according to claim 1 is characterized in that: In data module C, the scheduling table includes but is not limited to the specific work content of each maintenance task, clear assignment to the line operation team to perform the task, accurate estimation of the completion time of the task, accurate calculation of the travel time of the line operation team to the task location, and strict regulations on the minimum rest time required by the line operation team after executing the operation ticket. The above regulations ensure that the line operation team complies with the relevant regulations on work and rest while performing tasks.

9. The intelligent arrangement data model of power equipment maintenance plan based on optimization solver according to claim 1 is characterized in that: The model is additionally provided with a data module D: a self-assessment module, the data content of which includes: Define the evaluation index system: including but not limited to the task completion timeliness index: used to measure whether the maintenance task is completed within the planned time, and evaluated by calculating the difference between the actual completion time and the planned completion time; resource utilization index: evaluate the utilization of resources, resources include but are not limited to maintenance personnel and equipment; route rationality index: by comparing the degree of proximity between the actual maintenance route and the theoretical shortest route, the effect of the model on task allocation in route optimization is judged; key task execution effect index: examine the priority arrangement and execution of key tasks; Verification using historical data: collect relevant data from past power grid equipment maintenance tasks and input these data into the constructed model, run the model to obtain simulation results, and analyze the performance of the model in actual scenarios by comparing the simulation results with historical actual conditions; Conduct simulation tests: Use the model to generate corresponding maintenance plans by setting different maintenance task scenarios, and analyze the accuracy of the model-generated plans in various scenarios; Through multiple simulation tests, statistically analyze the data of various evaluation indicators of the model in different scenarios to comprehensively evaluate the performance of the model; Introduce expert review: Invite experts in the field of power equipment maintenance to evaluate the model.

Images