Intelligent scheduling method for emergency repair of gas pipe network and related device

Abstract

The invention discloses an intelligent scheduling method for emergency repair of a gas pipe network and a related device. The method comprises the following steps: generating a plurality of first-aid repair schemes based on acquired emergency tasks and first-aid repair teams, constructing a multi-objective optimization model for the first-aid repair schemes, and performing multi-objective solution for each first-aid repair scheme; taking a plurality of first-aid repair schemes as populations, performing population initialization by adopting a mode of combining a heuristic rule and random generation, and executing genetic operation; performing non-dominated sorting based on a Pareto dominated relationship, calculating a congestion degree distance of the first-aid repair scheme, and performing local search optimization until an optimal first-aid repair scheme set is output; and based on man-machine collaborative decision, selecting a matched target first-aid repair scheme from the optimal first-aid repair scheme set to perform intelligent scheduling. According to the method, a group of Pareto optimal scheduling schemes can be automatically generated, man-machine collaborative decision making is supported, conversion from experience scheduling to intelligent and accurate scheduling is realized, and the timeliness, accuracy and economical efficiency of emergency response are remarkably improved.

Description

Technical Field

[0001] This application relates to the field of urban public safety and emergency management technology, specifically to the fields of artificial intelligence, public safety and emergency management intersection, and particularly to an intelligent dispatching method and related device for emergency repair of gas pipeline networks. Background Technology

[0002] Urban gas pipeline networks are vital lifeline projects, and their safe operation is of paramount importance. Sudden incidents such as gas leaks and pipeline ruptures are characterized by their high risk and rapid spread, demanding a swift, precise, and efficient emergency response.

[0003] Currently, emergency dispatching by gas companies mainly relies on the personal experience of dispatchers and adopts simple rules such as assigning tasks based on proximity. However, the decision-making is not scientific enough and is prone to bias. The optimization objectives are singular, lack dynamic adaptability, and cannot quickly carry out global re-dispatch, resulting in rigid responses. Summary of the Invention

[0004] This application provides an intelligent scheduling method and related device for emergency repair of gas pipeline networks. By constructing a refined multi-objective function model and using an improved genetic algorithm to efficiently solve it, it automatically generates a Pareto optimal solution set that achieves the best balance among multiple conflicting objectives, realizing a paradigm shift from manual experience-based scheduling to intelligent and precise scheduling, and comprehensively improving the overall efficiency of emergency response.

[0005] The technical solution is as follows: Firstly, an intelligent scheduling method for emergency repair of gas pipeline networks is provided, including: Acquire information on multiple emergency tasks generated by gas accidents within the target city area, information on multiple available emergency repair teams, and real-time traffic information; Based on the information of the multiple emergency tasks and the information of the multiple available repair teams, multiple repair plans are generated, and the repair teams assigned to each emergency task in each repair plan are different; Based on the multiple emergency repair plans and the real-time road condition information, a multi-objective solution is performed for each emergency repair plan using a constructed multi-objective optimization model and corresponding constraints. The multi-objective optimization model includes: a first objective function representing minimizing the total weighted response time, a second objective function representing minimizing the total mismatch degree, and a third objective function representing minimizing the total resource consumption cost. The multiple emergency repair schemes are treated as a population. The population is initialized using a combination of heuristic rules and random generation, and genetic operations are performed. Based on the Pareto dominance relation, the merged population after the genetic operations is sorted in a non-dominated manner, and the crowding distance of each emergency repair scheme is calculated. Based on probabilistic selection, the top K emergency repair schemes sorted by crowding distance are optimized using an embedded local search method. The genetic operations are repeated until the local optimization operation is completed, until the optimal set of emergency repair schemes that meets the maximum number of generations is output. Based on human-machine collaborative decision-making, a matching target emergency repair plan is selected from the set of optimal emergency repair plans for intelligent scheduling.

[0006] Secondly, an intelligent dispatching device for emergency repair of gas pipeline networks is provided, comprising: The acquisition module is used to acquire information on multiple emergency tasks generated by gas accidents within the target city area, information on multiple available emergency repair teams, and real-time traffic information. The generation module is used to generate multiple emergency repair plans based on the information of the multiple emergency tasks and the information of the multiple available emergency repair teams. Each emergency task in each emergency repair plan is assigned a different emergency repair team. The solution module is used to solve for each emergency repair plan based on the multiple emergency repair plans and the real-time road condition information, through a constructed multi-objective optimization model and corresponding constraints. The multi-objective optimization model includes: a first objective function representing minimizing the total weighted response time, a second objective function representing minimizing the total mismatch degree, and a third objective function representing minimizing the total resource consumption cost. The optimization module is used to treat the multiple emergency repair schemes as a population, initialize the population using a combination of heuristic rules and random generation, and perform genetic operations; based on Pareto dominance, it performs non-dominated sorting on the merged population after the genetic operations and calculates the crowding distance of each emergency repair scheme; based on probabilistic selection, it performs local search optimization on the top K emergency repair schemes sorted by crowding distance using an embedded local search method; it repeats the genetic operations to the local optimization operations until the optimal set of emergency repair schemes that satisfies the maximum number of generations is output; The decision-making module is used to intelligently schedule a matching target emergency repair plan from the set of optimal emergency repair plans based on human-machine collaborative decision-making.

[0007] Thirdly, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods described above and any possible implementations.

[0008] Fourthly, a computer-readable storage medium is provided, wherein at least one instruction is stored therein, the at least one instruction being loaded and executed by a processor to implement the aspects described above and any possible implementation thereof.

[0009] Fifthly, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the aspects and any possible implementations described above.

[0010] The beneficial effects of the technical solution provided in this application include at least the following: As can be seen from the above technical solution, the embodiments of this application construct a multi-objective function based on multiple emergency repair schemes and real-time road condition information, aiming to minimize the total weighted response time, the total resource mismatch, and the total resource consumption cost. This function efficiently solves for each emergency repair scheme. A hybrid probability model combining heuristics and stochastic methods is used to initialize the population determined by multiple emergency repair schemes to improve the quality of the initial solution. An embedded local search operator is designed to enhance the algorithm's local optimization capability. Furthermore, a threshold-based dynamic rescheduling mechanism is established to cope with emergencies. This application can automatically generate a set of Pareto optimal scheduling schemes, supports human-machine collaborative decision-making, and realizes the transformation from experience-based scheduling to intelligent and precise scheduling, significantly improving the timeliness, accuracy, and economy of emergency response.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram illustrating the steps of an intelligent scheduling method for emergency repair of a gas pipeline network provided in an embodiment of this application.

[0014] Figure 2 This is a schematic diagram of the intelligent scheduling process for emergency repair of gas pipeline networks provided in the embodiments of this application.

[0015] Figure 3 This is a structural block diagram of an intelligent dispatching device for emergency repair of gas pipelines provided in one embodiment of this application.

[0016] Figure 4 This is a block diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These embodiments should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0018] Obviously, the described embodiments are only some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0019] It should be noted that the terminal devices involved in the embodiments of this application may include, but are not limited to, smart devices such as mobile phones, personal digital assistants (PDAs), wireless handheld devices, and tablet computers; the display devices may include, but are not limited to, personal computers, televisions, and other devices with display functions.

[0020] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0021] Given the shortcomings of existing emergency repair and dispatch schemes, such as insufficient scientific decision-making leading to biases, singular optimization objectives lacking dynamic adaptability, inability to quickly perform global rescheduling, and rigid responses, this application proposes an intelligent dispatch scheme for emergency repair of gas pipeline networks. The inventive concept involves: constructing a multi-objective function based on multiple repair schemes and real-time road condition information, aiming to minimize the total weighted response time, the total resource mismatch, and the total resource consumption cost; efficiently solving for each repair scheme; initializing the population determined by multiple repair schemes using a hybrid probability model combining heuristics and stochastic methods to improve the quality of initial solutions; designing an embedded local search operator to enhance the algorithm's local optimization capability; and establishing a threshold-based dynamic rescheduling mechanism to cope with emergencies. This application can automatically generate a set of Pareto optimal dispatch schemes, supports human-machine collaborative decision-making, and realizes the transformation from experience-based dispatching to intelligent and precise dispatching, significantly improving the timeliness, accuracy, and economy of emergency response.

[0022] Reference Figure 1 The diagram shown illustrates the steps of an intelligent scheduling method for emergency repair of a gas pipeline network according to an embodiment of this application. The intelligent scheduling method may include the following steps: Step 102: Obtain information on multiple emergency tasks generated by gas accidents within the target city area, information on multiple available repair teams, and real-time traffic information.

[0023] Optionally, in this application's solution, the emergency center platform can collect real-time information on gas accidents in the target city and generate multiple emergency tasks based on these accidents. The information for each emergency task includes at least: accident level, accident description, estimated repair time, and required equipment. Simultaneously, the emergency center platform can also monitor and manage multiple repair teams in real-time, including information on teams currently performing repairs and information on available repair teams; the information on each repair team includes at least: team qualifications, repair costs, current team status, location, and equipment.

[0024] Step 104: Based on the information of the multiple emergency tasks and the information of the multiple available repair teams, generate multiple repair plans, with each emergency task in each repair plan having a different repair team assigned to it.

[0025] After identifying multiple emergency tasks and multiple repair teams, each emergency task can be combined with each repair team to form multiple repair plans. For example, there are emergency tasks T1 and T2; and available repair teams A, B, and C. Combining each emergency task with each repair team yields 6 repair plans. For example: Repair Plan 1: Emergency Task T1 - Repair Team A; Emergency Task T2 - Repair Team B; Repair Plan 2: Emergency Task T1 - Repair Team A; Emergency Task T2 - Repair Team C; Repair Plan 3: Emergency Task T1 - Repair Team B; Emergency Task T2 - Repair Team A; Repair Plan 4: Emergency Task T1 - Repair Team B; Emergency Task T2 - Repair Team C; Repair Plan 5: Emergency Task T1 - Repair Team C; Emergency Task T2 - Repair Team A; Repair Plan 6: Emergency Task T1 - Repair Team C; Emergency Task T2 - Repair Team B.

[0026] Step 106: Based on the multiple emergency repair plans and the real-time road condition information, a multi-objective solution is performed for each emergency repair plan using the constructed multi-objective optimization model and corresponding constraints. The multi-objective optimization model includes: a first objective function representing minimizing the total weighted response time, a second objective function representing minimizing the total mismatch, and a third objective function representing minimizing the total resource consumption cost.

[0027] Optionally, the first objective function representing minimizing the total weighted response time is: in, It is the priority weight of emergency task i; It is the estimated arrival time of the repair team j to the accident site where the emergency task i is located; This is a scheduling scheme that assigns emergency task i to repair team j. The second objective function representing minimizing the total mismatch is: in, It refers to the resource matching degree of the emergency repair team j in handling emergency tasks i; The third objective function representing minimizing the total resource consumption cost is: in, It is an indicator function, indicating that if repair team j is dispatched, then... =1, otherwise =0; To reach the required time, To estimate the repair time upon arrival; It is the unit time cost of the emergency repair team j.

[0028] Furthermore, the second objective function is constructed as follows: based on the information of multiple emergency repair teams, the skills, qualifications, equipment, tools, and experience cases of each emergency repair team are quantified; the skill qualification matching degree, equipment and tool matching degree, and experience case matching degree of the emergency repair teams are calculated; based on the skill qualification matching degree, equipment and tool matching degree, and experience case matching degree, and the skill qualification matching degree weight, equipment and tool matching degree weight, and experience case matching degree weight set for each matching degree, the total mismatch degree is minimized.

[0029] In step 106, a multi-objective optimization model can be constructed based on multiple emergency repair plans and real-time road condition information. Specifically, by combining the industry characteristics of gas accident emergency repair, public safety needs, and resource management realities, the following three core performance indicators can be determined after systematic analysis, and these three indicators can form the multi-objective optimization model.

[0030] (1) Minimize the total weighted response time The purpose of this indicator is to prioritize the fastest response to high-risk gas leak points under limited emergency resources, thereby minimizing public safety risks and potential accident losses. This is achieved by introducing risk weights. This enables scheduling algorithms to have risk perception and priority judgment capabilities, achieving high-risk tasks → high priority → fastest response, that is, prioritizing rapid response to high-priority incidents, and thus shifting from average response to precise response.

[0031] In this application, a matrix is ​​used. This represents the scheduling plan, i.e., each emergency repair plan: Where i={1,2,...,N}: the set of emergency tasks i for sudden accidents, and N is the number of emergency tasks; j={1,2,...,M}: the set of available repair teams, and M is the number of repair teams.

[0032] The minimum total weighted response time is: in, This refers to the priority weight of emergency task i triggered by the accident, for example, Level I = 3; Level II = 2; Level III = 1. It is the estimated arrival time (ETA) of the repair team j to the accident site where emergency task i is located. This ETA is calculated based on real-time traffic conditions.

[0033] (2) Minimize the total mismatch (i.e. maximize the total match) The core purpose of this indicator is to ensure that dispatch decisions shift from "whether it can be handled" to "optimal matching" by quantitatively assessing the compatibility between repair teams and emergency incidents.

[0034] This calculation comprehensively considers three key dimensions: skills and qualifications, equipment and tools, and experience and case studies. Skills matching verifies whether the team possesses the legal qualifications and capability thresholds; equipment matching measures the extent to which its materials and equipment cover the mission requirements; and experience matching assesses the effectiveness and reliability of its handling of similar historical missions. Finally, a weighted composite matching score is synthesized, aiming to minimize the total mismatch cost resulting from all scheduling decisions.

[0035] Skills and aptitude matching : Equipment and tool matching degree : in, It is a collection of key equipment required for handling emergency tasks caused by accidents; It is an indicator function; it is 1 if the j-th repair team is equipped with equipment e, and 0 otherwise.

[0036] Case study matching degree: in, It is the number of emergency tasks similar to those caused by the accident that the repair team j has handled. It represents the total number of tasks handled by the emergency repair team.

[0037] Based on the above, the resource matching degree is obtained. : in: This is the weight of skill qualification matching. For high-risk accidents with high standard requirements (such as high-pressure pipeline leaks), a higher weight should be assigned. The default weight in this application is 0.3. Equipment and tool matching weight: For emergency repairs that rely on special large equipment (such as pipeline replacement), a higher weight should be assigned. The default value in this application is 0.4. This refers to the weighting of experience-based case matching. For complex and unconventional incidents (such as pipeline repairs across rivers), a higher weight should be assigned. This application defaults to 0.3. It should be understood that the weighting coefficient can be adjusted based on actual circumstances.

[0038] Minimize the total mismatch: Where Mij∈[0,1] represents the resource matching degree of the repair team j in handling the emergency task i caused by the accident. It should be noted that more matched resources should be scheduled first.

[0039] (3) Minimize total resource consumption cost: This indicator aims to optimize scheduling plans globally from the perspectives of economy and efficiency. Its core objective is not simply to reduce expenses, but to maximize the efficiency of resource utilization. This indicator comprehensively measures the total economic burden under different scheduling plans by quantifying the unit time cost, travel time, and estimated repair time for each team.

[0040] in, It is an indicator function, indicating that if repair team j is dispatched, then... =1, otherwise =0; To reach the required time, To estimate the repair time upon arrival; It is the unit time cost of the emergency repair team j.

[0041] Meanwhile, the above-mentioned multi-objective optimization algorithm must satisfy the following hard constraints during the solution process: Each emergency task must be assigned and assigned only once: The repair team's skills must meet the mission requirements: The response time must not exceed the specified time limit. .

[0042] Step 108: Treat the multiple emergency repair schemes as a population, initialize the population using a combination of heuristic rules and random generation, and perform genetic operations; perform non-dominated sorting on the merged population after the genetic operations based on Pareto dominance, and calculate the crowding distance of each emergency repair scheme; perform local search optimization on the top K emergency repair schemes sorted by crowding distance based on probability selection, using an embedded local search method; repeat the genetic operations to the local optimization operations until the optimal set of emergency repair schemes that satisfies the maximum number of generations is output.

[0043] Optionally, when performing non-dominated sorting on the merged population after genetic operations based on Pareto dominance and calculating the crowding distance for each repair scheme, the merged population after genetic operations can be specifically sorted non-dominated based on Pareto dominance, dividing the merged population into several non-dominated layers: F = (F1, F2, F3, ..., F...). k ), where F1 is the first non-dominated layer, F kThis is the k-th non-dominated layer; for repair schemes within the same non-dominated layer, calculate their congestion distance: in, It is the value of the b-th emergency repair plan on the m-th objective function; and These are the maximum and minimum values ​​of the m-th objective function in the current population.

[0044] Optionally, when using an embedded local search method to optimize the local search for the top K emergency repair schemes sorted by congestion distance based on probability selection, a new population can be constructed by selecting the top K emergency repair schemes sorted by congestion distance: Based on probabilistic selection, some emergency repair schemes in the new population are optimized using an embedded local search method; and a task is randomly selected and reallocated to perform resource redistribution search.

[0045] In practical implementation, based on the classic NSGA-II algorithm, and addressing the pain points of the emergency scheduling problem, such as complex solution space, strong constraints, intense objective conflicts, and slow convergence speed, in-depth improvements can be made in four dimensions: encoding method, genetic operators, selection mechanism, and constraint handling, forming a high-efficiency and practical multi-objective optimization engine. The algorithm process is as follows: First, heuristic population initialization. A hybrid probability model (a strategy combining heuristic rules and random generation) is adopted to replace completely random initialization, which improves the quality of the initial solution while ensuring population diversity.

[0046] For each gene locus of each individual in the population The probability of its allocation is: in, It is the heuristic selection probability (usually set to 0.8). The cardinality of a set (the number of elements). : Select the top-K teams with the shortest ETA from the feasible set (high-quality candidate set). : Feasible team set.

[0047] Secondly, genetic manipulation ① Selection: A binary tournament selection method is adopted, giving priority to individuals with high non-dominant hierarchy and high crowding. That is, two individuals are randomly selected from the population, and the superior one is selected to enter the mating pool through comparison.

[0048] ② Crossover operation: Randomly select a crossover point from two parent individuals and exchange the gene segments after the crossover point.

[0049] Suppose there are two parent individuals: Randomly select crossover point k to exchange parent gene segments: Generate offspring: Merging populations: For the parent population, This is the offspring population. The size of the merged population Rt is 2N.

[0050] ③ Conflict detection and repair: When conflicts occur, infeasible solutions may arise (the same repair team is assigned multiple emergency tasks at the same time), which requires repair.

[0051] ④ Mutation: Adaptive mutation is used, and the mutation probability decreases as the number of generations increases.

[0052] Then, fast non-dominated sorting and crowding calculation. ① Fast Non-Dominated Sort: Based on Pareto dominance, a fast non-dominated sort is performed on the merged population, dividing it into several non-dominated layers: F = (F1, F2, F3, ..., Fk) F1 is the first non-dominated layer (optimal), F2 is the second non-dominated layer, and so on.

[0053] ② Crowding degree calculation: For individual i in the same non-dominated layer F, the crowding degree distance is calculated as follows: It is the value of individual i on the m-th objective function. and These are the maximum and minimum values ​​of the m-th objective in the current population. The crowding distance of boundary individuals (individuals with extreme objective function values) is set to infinity.

[0054] Next, the elite retains the choice. After performing non-dominated sorting and crowding calculation on the merged population, a new population is filled in from high to low according to the frontier level. If the last level needs to be screened, the population is selected from large to small according to the crowding level, and a new population is constructed by selecting each level.

[0055] Select the first K individuals: Next step: Embedded local search ① Local search: Based on probability, a search is performed on a subset of individuals (repair plans).

[0056] ② Resource reallocation search: Randomly select a task and attempt to reallocate it to optimize the objective.

[0057] For the selected individuals Generate a candidate team set Evaluate the new allocation: for each ; Create a new solution: =copy( ); if Then accept, or accept the non-dominated solution with a certain probability.

[0058] ③ Route optimization: 2-opt optimization of team routes to shorten travel time.

[0059] in For the new path. If Then accept the new path.

[0060] Finally, termination and output. Repeat the genetic operation up to the local search operation until the maximum number of generations is reached. Output the first non-dominated layer F1 as the Pareto optimal solution set.

[0061] Step 110: Based on human-machine collaborative decision-making, select a matching target emergency repair plan from the set of optimal emergency repair plans for intelligent scheduling.

[0062] Optionally, when there are changes in emergency tasks and / or repair teams, the scheduling of the current target repair plan can be suspended, and the optimal target repair plan can be regenerated based on the latest information on multiple emergency tasks and available repair teams, in accordance with the method of claim 1, for scheduling and execution.

[0063] In this application, the emergency tasks and / or repair teams may change. This could be due to the addition of new emergency tasks, modifications to existing emergency tasks, or the cancellation of existing emergency tasks. Alternatively, it could be due to new available repair teams or teams being urgently called upon to perform other emergency tasks.

[0064] like Figure 2 The diagram shown is a schematic of the intelligent scheduling process for emergency repair of gas pipeline networks provided in an embodiment of this application.

[0065] The intelligent dispatching solution for emergency repair of gas pipeline networks can be divided into three parts: a pre-processing layer, an intelligent optimization engine layer, and a post-processing and output layer.

[0066] First, the system receives multi-source data, including accident, resource, and road condition data. A multi-objective optimization function is constructed. Then, a heuristic population is initialized, and genetic operations such as crossover, mutation, and selection are performed. Next, fast non-dominated sorting and crowding calculation are performed, with elite selection. Following this, an embedded local search is conducted, terminating and outputting a Pareto optimal solution set. Finally, a human-machine collaborative decision-making process determines the optimal repair plan.

[0067] Taking emergency dispatch for urban gas pipeline leaks as an example, the scenario is during the evening rush hour, with two gas accidents occurring simultaneously in a city. This allows us to obtain specific information about tasks T1 and T2, as well as the teams (Team A-Team C) responsible for maintenance at the emergency center. Table 1 shows the tasks and their related information. Table 2 shows the teams and their related information. Table 3 shows the combinations of different teams assigned to each task.

[0068] Table 1

[0069] Table 2

[0070] Table 3 Based on the task and team information in Tables 1-3 above, the multi-objective function constructed in this application is used to solve the multi-objective problem. Among them, Table 4 shows the objective of solving multiple emergency repair schemes: minimizing the total weighted response time.

[0071] Table 4 Table 5 shows the solution objective 2 for multiple emergency repair schemes: minimizing the total mismatch.

[0072] Table 5 Table 6 shows the solution objective 3 for multiple emergency repair schemes: minimizing total resource consumption cost.

[0073] Table 6 Table 7 shows the combined three objective function values ​​of multiple emergency repair plans.

[0074] Table 7 Subsequently, based on the results in Table 7, the Pareto optimal solution set was obtained using the improved genetic algorithm, as shown in Table 8.

[0075] Table 8 Subsequently, either Scheme 2 or Scheme 6 can be selected from Table 8 for scheduling and execution based on human-computer interaction.

[0076] Suppose that the dispatch center selects option 2, and after 15 minutes of execution, an emergency occurs: a Level I high-pressure pipeline leak occurs in the new urban area, which generates a new task T3.

[0077] The system monitoring detects the addition of task T3, triggering a rescheduling. The scheduling unit will then start from the current state (Team C is already processing T1, Team B is already processing T2), and consider T3, the idle Team A, and the soon-to-be-idle Team B and Team C as available resources. It will recalculate and provide a new optimal solution. For example, Team B, currently en route, might abandon its original task T2 and immediately switch to the new Level I incident T3 (because Team B is closer to T3 and meets the skill requirements), while simultaneously assigning the soon-to-be-idle Team A to take over and complete task T2. The dispatcher reviews and confirms the new optimal solution, and the system immediately sends change orders to the relevant teams.

[0078] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0079] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0080] Figure 3 This application provides a structural block diagram of an intelligent dispatching device for emergency repair of gas pipeline networks according to one embodiment. Figure 3As shown. The intelligent dispatching device 300 for emergency repair of gas pipeline networks in this embodiment may include an acquisition module 301, a generation module 302, a solution module 303, an optimization module 304, and a decision module 305. The acquisition module 301 is used to acquire information on multiple emergency tasks generated by gas accidents within a target city area, information on multiple available repair teams, and real-time road condition information. The generation module 302 is used to generate multiple repair plans based on the information on the multiple emergency tasks and the information on the multiple available repair teams, with each emergency task in each repair plan having a different repair team assigned to it. The solution module 303 is used to perform multi-objective solutions for each repair plan based on the multiple repair plans and the real-time road condition information, using a constructed multi-objective optimization model and corresponding constraints; the multi-objective optimization model includes: a first objective function representing minimizing the total weighted response time, a second objective function representing minimizing the total mismatch degree, and a third objective function representing minimizing the total resource consumption cost. The optimization module 304 is used to initialize the multiple emergency repair schemes as a population using a combination of heuristic rules and random generation, and then perform genetic operations. Based on Pareto dominance, the merged population after the genetic operations is sorted non-dominated, and the crowding distance of each emergency repair scheme is calculated. Based on probabilistic selection, the top K emergency repair schemes sorted by crowding distance are optimized using an embedded local search method. The genetic operations are repeated until the local optimization operation is completed, outputting the optimal set of emergency repair schemes that satisfies the maximum number of generations. The decision module 305 is used to intelligently schedule a matching target emergency repair scheme from the optimal set of emergency repair schemes based on human-machine collaborative decision-making.

[0081] It should be noted that some or all of the intelligent dispatching device for emergency repair of gas pipeline networks in this embodiment may be an application located on a local terminal, or it may be a plugin or software development kit (SDK) or other functional unit set in the application located on the local terminal, or it may be a processing engine located on the network-side server, or it may be a distributed system located on the network side. This embodiment does not impose any particular limitations on this.

[0082] It is understood that the application can be a native program installed on the local terminal, or it can be a web application of a browser on the local terminal. This embodiment does not limit this.

[0083] Optionally, in one possible implementation of this embodiment, the first objective function representing minimizing the total weighted response time is: in, It is the priority weight of emergency task i; It is the estimated arrival time of the repair team j to the accident site where the emergency task i is located; This is a scheduling scheme that assigns emergency task i to repair team j. The second objective function representing minimizing the total mismatch is: in, It refers to the resource matching degree of the emergency repair team j in handling emergency tasks i; The third objective function representing minimizing the total resource consumption cost is: in, It is an indicator function, indicating that if repair team j is dispatched, then... =1, otherwise =0; To reach the required time, To estimate the repair time upon arrival; It is the unit time cost of the emergency repair team j.

[0084] Optionally, in one possible implementation of this embodiment, when constructing the second objective function, the solving module is specifically used to quantify the skills, qualifications, equipment, tools, and experience cases of each of the multiple emergency repair teams based on the information of multiple emergency repair teams, calculate the skill qualification matching degree, equipment and tool matching degree, and experience case matching degree of the emergency repair teams and the emergency task quality inspection; and calculate the minimum total mismatch degree based on the skill qualification matching degree, equipment and tool matching degree, experience case matching degree, and the skill qualification matching degree weight, equipment and tool matching degree weight, and experience case matching degree weight set for each matching degree.

[0085] Optionally, in one possible implementation of this embodiment, when the optimization module 304 performs non-dominated sorting of the merged population after genetic operations based on Pareto dominance and calculates the congestion distance of each repair scheme, it is specifically used to perform non-dominated sorting of the merged population after genetic operations based on Pareto dominance, dividing the merged population into several non-dominated layers: F = (F1, F2, F3, ..., F...). k ), where F1 is the first non-dominated layer, F k This is the k-th non-dominated layer; for repair schemes within the same non-dominated layer, calculate their congestion distance: in, It is the value of the b-th emergency repair plan on the m-th objective function; and These are the maximum and minimum values ​​of the m-th objective function in the current population.

[0086] Optionally, in one possible implementation of this embodiment, when the optimization module 304 performs local search optimization using an embedded local search method to select the top K emergency repair schemes sorted by congestion distance based on probability, it is specifically used to construct a new population by selecting the top K emergency repair schemes sorted by congestion distance. Based on probabilistic selection, some emergency repair schemes in the new population are optimized using an embedded local search method; and a task is randomly selected and reallocated to perform resource redistribution search.

[0087] Optionally, in one possible implementation of this embodiment, the information of the emergency task includes at least: the accident level, the accident description, the estimated repair time, and the required equipment; the information of the repair team includes at least: the team's qualifications, the repair cost, the team's current status, its location, and the equipment it is equipped with.

[0088] Optionally, in one possible implementation of this embodiment, the device further includes: a re-decision module, used to suspend the scheduling of the current target repair plan when there are changes in emergency tasks and / or repair teams, and trigger the regeneration of the optimal target repair plan for scheduling execution using steps 102-110 based on the latest information on multiple emergency tasks and available repair teams.

[0089] It should be understood that the implementation details of the intelligent scheduling device can be found in [reference needed]. Figure 1 The methods and related content shown will not be elaborated here.

[0090] In this embodiment, a multi-objective function is constructed based on multiple emergency repair plans and real-time road condition information. The function aims to minimize the total weighted response time, the total resource mismatch, and the total resource consumption cost. This function is used to efficiently solve for each emergency repair plan. A hybrid probabilistic model combining heuristics and stochastic methods is used to initialize the population determined by the multiple emergency repair plans to improve the quality of the initial solution. An embedded local search operator is designed to enhance the algorithm's local optimization capability. Furthermore, a threshold-based dynamic rescheduling mechanism is established to handle emergencies. This application can automatically generate a set of Pareto optimal scheduling plans, supports human-machine collaborative decision-making, and realizes the transformation from experience-based scheduling to intelligent and precise scheduling, significantly improving the timeliness, accuracy, and economy of emergency response.

[0091] One embodiment of this application provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the intelligent scheduling method for emergency repair of gas pipeline networks as described above.

[0092] One embodiment of this application provides an electronic device, which includes a processor and a memory. The memory stores at least one instruction, which is loaded and executed by the processor to realize the intelligent scheduling method for emergency repair of gas pipeline networks as described above.

[0093] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0094] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of this application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0095] like Figure 4 As shown, the electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. The RAM 403 may also store various programs and data required for the operation of the electronic device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0096] Multiple components in electronic device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of displays, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows electronic device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0097] The computing unit 401 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the intelligent scheduling method for emergency repair of gas pipeline networks. For example, in some embodiments, the intelligent scheduling method for emergency repair of gas pipeline networks can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the intelligent scheduling method for emergency repair of gas pipeline networks described above can be performed. Alternatively, in other embodiments, the computing unit 401 may be configured by any other suitable means (e.g., by means of firmware) to perform an intelligent scheduling method for emergency repairs of gas pipeline networks.

[0098] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, at least one input device, and at least one output device.

[0099] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0100] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0101] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0102] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0103] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0104] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0105] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. An intelligent dispatching method for emergency repair of gas pipeline networks, characterized in that, include: Acquire information on multiple emergency tasks generated by gas accidents within the target city area, information on multiple available emergency repair teams, and real-time traffic information; Based on the information of the multiple emergency tasks and the information of the multiple available repair teams, multiple repair plans are generated, and the repair teams assigned to each emergency task in each repair plan are different; Based on the multiple emergency repair plans and the real-time road condition information, a multi-objective solution is performed for each emergency repair plan using a constructed multi-objective optimization model and corresponding constraints. The multi-objective optimization model includes: a first objective function representing minimizing the total weighted response time, a second objective function representing minimizing the total mismatch, and a third objective function representing minimizing the total resource consumption cost; The multiple emergency repair schemes are treated as a population. The population is initialized using a combination of heuristic rules and random generation, and genetic operations are performed. Based on the Pareto dominance relation, the merged population after the genetic operations is sorted in a non-dominated manner, and the crowding distance of each emergency repair scheme is calculated. Based on probabilistic selection, the top K emergency repair schemes sorted by crowding distance are optimized using an embedded local search method. The genetic operations are repeated until the local optimization operation is completed, until the optimal set of emergency repair schemes that meets the maximum number of generations is output. Based on human-machine collaborative decision-making, a matching target emergency repair plan is selected from the set of optimal emergency repair plans for intelligent scheduling.

2. The method as described in claim 1, characterized in that, The first objective function representing minimizing the total weighted response time is: in, This is the priority weight of emergency task i; It is the estimated arrival time of the repair team j to the accident site where the emergency task i is located; This is a scheduling scheme that assigns emergency task i to repair team j. The second objective function representing minimizing the total mismatch is: in, It refers to the resource matching degree of the emergency repair team j in handling emergency tasks i; The third objective function representing minimizing the total resource consumption cost is: in, It is an indicator function, indicating that if repair team j is dispatched, then... =1, otherwise =0; To reach the required time, To estimate the repair time upon arrival; It is the unit time cost of the emergency repair team j.

3. The method as described in claim 2, characterized in that, The second objective function is constructed in the following way: Based on the information quantification of multiple emergency repair teams, the skills, qualifications, equipment, tools, and experience cases of each emergency repair team are calculated, and the matching degree of skills and qualifications, equipment and tools, and experience cases of emergency repair teams with the emergency task quality inspection is calculated. Based on the skill qualification matching degree, equipment tool matching degree, experience case matching degree, and the skill qualification matching degree weight, equipment tool matching degree weight, and experience case matching degree weight set for each matching degree, the total mismatch degree is calculated to be minimized.

4. The method as described in claim 1, characterized in that, Based on Pareto dominance, the merged population after genetic operations is non-dominated and ordered, and the crowding distance for each repair scheme is calculated, specifically including: Based on Pareto dominance, the merged population after genetic operations is sorted into several non-dominated layers: F = (F1, F2, F3, ..., F...). k ), where F1 is the first non-dominated layer, F k It is the k-th non-dominated layer; For emergency repair plans within the same non-dominated layer, calculate their congestion distance: in, It is the value of the b-th emergency repair plan on the m-th objective function; and These are the maximum and minimum values ​​of the m-th objective function in the current population.

5. The method as described in claim 1, characterized in that, Based on probabilistic selection, the top K emergency repair schemes sorted by congestion distance are optimized using an embedded local search method, specifically including: The top K repair plans, sorted by congestion distance, are used to construct a new population. Based on probabilistic selection, some emergency repair schemes in the new population are optimized using an embedded local search method; and a task is randomly selected and reallocated to perform resource redistribution search.

6. The method according to any one of claims 1-5, characterized in that, Information for emergency response tasks should include at least: incident level, incident description, estimated repair time, and required equipment; Information about the emergency repair team should include at least: team qualifications, repair costs, current status of the team, location, and equipment.

7. The method according to any one of claims 1-5, characterized in that, When there are changes in emergency tasks and / or repair teams, the method further includes: The current target repair plan is suspended. Based on the latest information on multiple emergency tasks and available repair teams, the optimal target repair plan is regenerated using the method described in claim 1 for scheduling and execution.

8. An intelligent dispatching device for emergency repair of gas pipeline networks, characterized in that, include: The acquisition module is used to acquire information on multiple emergency tasks generated by gas accidents within the target city area, information on multiple available emergency repair teams, and real-time traffic information. The generation module is used to generate multiple emergency repair plans based on the information of the multiple emergency tasks and the information of the multiple available emergency repair teams. Each emergency task in each emergency repair plan is assigned a different emergency repair team. The solution module is used to solve for each emergency repair plan based on the multiple emergency repair plans and the real-time road condition information, through the constructed multi-objective optimization model and corresponding constraints. The multi-objective optimization model includes: a first objective function representing minimizing the total weighted response time, a second objective function representing minimizing the total mismatch, and a third objective function representing minimizing the total resource consumption cost; The optimization module is used to treat the multiple emergency repair schemes as a population, initialize the population using a combination of heuristic rules and random generation, and perform genetic operations; based on Pareto dominance, it performs non-dominated sorting on the merged population after the genetic operations and calculates the crowding distance of each emergency repair scheme; based on probabilistic selection, it performs local search optimization on the top K emergency repair schemes sorted by crowding distance using an embedded local search method; it repeats the genetic operations to the local optimization operations until the optimal set of emergency repair schemes that satisfies the maximum number of generations is output; The decision-making module is used to intelligently schedule a matching target emergency repair plan from the set of optimal emergency repair plans based on human-machine collaborative decision-making.

9. The apparatus as claimed in claim 8, characterized in that, The first objective function representing minimizing the total weighted response time is: in, It is the priority weight of emergency task i; It is the estimated arrival time of the repair team j to the accident site where the emergency task i is located; This is a scheduling scheme that assigns emergency task i to repair team j. The second objective function representing minimizing the total mismatch is: in, It refers to the resource matching degree of the emergency repair team j in handling emergency tasks i; The third objective function representing minimizing the total resource consumption cost is: in, It is an indicator function, indicating that if repair team j is dispatched, then... =1, otherwise =0; To reach the required time, To estimate the repair time upon arrival; It is the unit time cost of the emergency repair team j.

10. The apparatus as claimed in claim 9, characterized in that, When constructing the second objective function, the solution module is specifically used for: Based on the information quantification of multiple emergency repair teams, the skills, qualifications, equipment, tools, and experience cases of each emergency repair team are calculated, and the matching degree of skills and qualifications, equipment and tools, and experience cases of emergency repair teams with the emergency task quality inspection is calculated. Based on the skill qualification matching degree, equipment tool matching degree, experience case matching degree, and the skill qualification matching degree weight, equipment tool matching degree weight, and experience case matching degree weight set for each matching degree, the total mismatch degree is calculated to be minimized.

11. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-7.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-7.

Images