Large-scale complex road network motor train unit advanced repair productivity layout method and device

Abstract

The invention provides a large-scale complex road network motor train unit advanced repair productivity layout method and equipment, and the method comprises the steps: collecting a motor train unit running route, a motor train unit maintenance record, and the number and type data of running motor train units, and carrying out the preliminary analysis of a collected result; the analysis result is used as the input of a multi-objective optimization model of the vehicle base productivity layout; establishing a multi-objective optimization model of the productivity layout of the vehicle base, including determining an objective function of the productivity layout of the advanced repair vehicle base of the motor train unit based on a set multi-objective optimization objective of the productivity layout of the vehicle base, and setting corresponding constraint conditions based on various limiting conditions in the process of the productivity layout of the advanced repair vehicle base; and solving the multi-objective optimization model based on the vehicle base productivity layout to obtain an advanced repair production capacity layout scheme and outputting the advanced repair production capacity layout scheme.

Description

Technical Field

[0001] The present invention relates to the field of railway transportation, and in particular to a technology for optimizing the layout of productivity of advanced maintenance (advanced repair) of EMUs. Background Art

[0002] With the rapid development of high-speed railway networks, the demand for EMU maintenance is growing. Traditional EMU maintenance capacity layout methods often cannot adapt to the needs of large-scale complex road networks, and there are problems such as low maintenance efficiency and unreasonable resource allocation, including how to efficiently allocate resources, how to optimize maintenance processes to improve maintenance efficiency, and how to reduce maintenance costs. Existing layout methods often cannot adapt to the characteristics of complex road networks, resulting in unreasonable resource allocation, low maintenance efficiency, high costs, and difficulty in ensuring service quality.

[0003] The existing layout of EMU advanced maintenance capacity has the following problems: 1. Irrational layout of EMU maintenance resources: With the gradual improvement of the high-speed railway network and the increase in the number of EMUs, the existing layout of EMU maintenance resources cannot meet the growing maintenance needs, resulting in low maintenance efficiency and extended maintenance cycle.

[0004] 2. Maintenance efficiency and quality are difficult to guarantee: Due to the lack of intelligent and automated maintenance equipment and technology, the maintenance efficiency and quality of EMUs are difficult to be effectively guaranteed, affecting the safe operation of EMUs.

[0005] 3. Waste of maintenance resources and high costs: In the maintenance process of existing EMUs, unreasonable resource allocation leads to waste of resources and high operation and maintenance costs.

[0006] 4. Insufficient management and analysis of maintenance data: The large amount of data generated during the maintenance of EMUs has not been effectively managed and analyzed, and cannot provide a scientific basis for maintenance decisions.

[0007] Therefore, this field urgently needs to propose a technical solution for optimizing the layout of advanced maintenance (advanced repair) productivity of EMUs that is simpler to implement and more applicable. Summary of the invention

[0008] In view of the shortcomings of the prior art, the purpose of the present invention is to propose a method and system for high-level maintenance capacity layout of EMUs in large-scale complex road networks, so as to obtain vertical line deviations with high precision around the clock.

[0009] To achieve the above-mentioned purpose, the technical solution of the present invention provides a method for high-level maintenance capacity layout of EMUs in a large-scale complex road network, including the following processes: Collect data on EMU routes, EMU maintenance records, number and type of EMUs in operation, and conduct preliminary analysis on the collected results, which will be used as input for the multi-objective optimization model of the productivity layout of the vehicle base; Establish a multi-objective optimization model for the layout of vehicle base productivity, including determining the objective function of the layout of EMU advanced maintenance vehicle base productivity based on the multi-objective optimization objectives of the vehicle base productivity layout, and setting corresponding constraints based on various constraints in the layout process of advanced maintenance productivity; The multi-objective optimization model based on the vehicle base productivity layout is solved to obtain the advanced maintenance production capacity layout plan and output it. Moreover, when conducting preliminary analysis of the collected results, random forest or support vector machine methods are used to implement data analysis.

[0010] Furthermore, the multi-objective optimization objectives of the productivity layout of the EMU base include maintenance cycle and time, resource utilization, maintenance cost and EMU maintenance capacity.

[0011] Moreover, various constraints in the advanced repair capacity layout process include physical space limitations of advanced repair facilities, the number and technical level of technicians, working time limitations and economic feasibility limitations.

[0012] Moreover, a hybrid NSGA-II and PSO algorithm is used to solve the multi-objective optimization model based on the productivity layout of vehicle bases.

[0013] Moreover, the advanced maintenance production capacity layout plan includes the location of productivity layout, productivity scale, maintenance time per unit EMU, maintenance process flow line layout, production line configuration plan, maintenance components and spare parts, and effect prediction and evaluation.

[0014] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for advanced maintenance capacity layout of EMUs in large-scale complex road networks as described above is implemented.

[0015] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for advanced maintenance capacity layout of EMUs in a large-scale complex road network.

[0016] On the other hand, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for advanced maintenance capacity layout of EMUs in a large-scale complex road network.

[0017] Compared with the prior art, the present invention can automatically generate a detailed advanced maintenance production capacity layout plan through the above technical scheme, including the productivity layout location, productivity scale and maintenance process flow layout, production line configuration plan, maintenance component spare parts, effect prediction and evaluation, realizing efficient planning and layout of large-scale complex road networks, and effectively improving computing efficiency.

[0018] The solution of the present invention is simple and convenient to implement, has strong practicability, solves the problems of low practicability and inconvenience in actual application existing in the related technology, and has important market value. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The concept, specific structure and technical effects of the present invention will be further described below in conjunction with the accompanying drawings and embodiments, so as to fully understand the purpose, characteristics and effects of the present invention.

[0021] See also Figure 1 In one embodiment of the present invention, a method for advanced maintenance capacity layout of EMUs in a large-scale complex road network is provided, comprising the following processing: Step S1, collecting data such as EMU operation routes, EMU maintenance records, number and type of EMUs in operation, and conducting preliminary analysis of the data to provide comprehensive support for optimizing the layout; Step S2, determining the productivity layout objective function of the EMU advanced maintenance vehicle base, including maintenance cycle and time, resource utilization, maintenance cost, EMU maintenance capacity, etc., to ensure the effectiveness and economy of the plan; Step S3, formulate corresponding constraints, including physical space restrictions of advanced repair facilities, number and technical level of technicians, working time restrictions, economic feasibility restrictions, etc., to ensure that the generated layout plan is practical and feasible; In step S4, a hybrid NSGA-II (Non-dominated Sorting Genetic Algorithm II) and PSO (Particle Swarm Optimization) algorithm is used to solve and generate a detailed advanced maintenance production capacity layout plan, including the location of productivity layout, productivity scale, maintenance time per unit EMU, maintenance process flow layout, production line configuration plan, maintenance component spare parts, effect prediction and evaluation, which realizes efficient planning and layout of large-scale complex road networks and effectively improves calculation efficiency.

[0022] This embodiment establishes a multi-objective optimization model for the vehicle base productivity layout based on S2 and S3, including determining the EMU advanced repair vehicle base productivity layout objective function based on the multi-objective optimization objectives of the vehicle base productivity layout, and setting corresponding constraints based on various restrictions in the advanced repair productivity layout process.

[0023] In one embodiment of the present invention, in step S1, after collecting data such as the EMU operation route, EMU maintenance records, and the number of EMUs in operation, data analysis methods such as random forests or support vector machines are used, and the analysis results are used as input to a multi-objective optimization model to ensure the accuracy and practicality of the layout plan.

[0024] In one embodiment of the present invention, when determining the productivity layout objective function of the EMU advanced vehicle repair base in step S2, it is specifically implemented as follows: Set the multi-objective optimization goals for the layout of vehicle base productivity, including but not limited to maintenance cycle and time, resource utilization, maintenance cost, EMU maintenance capacity, etc. The specific objective function can be expressed as a multi-objective optimization problem as follows: Objective function:

[0025] in: represents the overall objective function; , , They represent the sub-objective functions of maintenance cycle and time, resource utilization, maintenance cost, and EMU maintenance capacity respectively. , , , is the weight coefficient of each sub-objective function, satisfying + + + =1, and >0, used to adjust the relative importance of each objective in the overall objective function.

[0026] 1. Minimize maintenance cycle and time:

[0027] = + + + +

[0028] in, It represents the maintenance time of the i-th EMU under a given configuration. The relevant parameters are defined as follows: 1) Maintenance activity time : Definition: Standard maintenance time for each EMU.

[0029] Calculation method: Estimated based on standard operating manual and historical data.

[0030] 2) Equipment preparation time : Definition: The time it takes for a device to go from standby to ready.

[0031] Calculation method: Determined based on equipment type and preparation process.

[0032] 3) Resource conflict time : Definition: When multiple train sets require the same resource at the same time, it may cause increased waiting time in queues.

[0033] Calculation method: A nonlinear function can be used to calculate the waiting time based on the resource demand and the number of available resources.

[0034] = ( , R) in, represents the resource demand of the i-th EMU, R represents the number of currently available resources, is a nonlinear function used to calculate the waiting time.

[0035]

[0036] Among them, α and β are adjustment parameters used to control the shape of the function.

[0037] 4) Travel time : Definition: The time it takes for a train to reach a productive force layout point within a road network.

[0038] Calculation method: Determined according to the location and mode of transportation of the EMU.

[0039] 5) Testing and verification time : Definition: The time to test and verify after repairs are completed.

[0040] Calculation method: determined according to the test items and standards.

[0041] 2. Maximize resource utilization, including equipment cost, labor cost and other resource utilization;

[0042] in: Indicates i The utilization rate of a resource (such as equipment and manpower). The negative sign indicates maximization.

[0043] 3. Minimize maintenance costs:

[0044] in: Indicates i The cost of a maintenance activity.

[0045] 4. Maximize the maintenance capacity of the EMU and ensure that the maintenance capacity of the EMU is the maximum under a given configuration.

[0046]

[0047] in: Indicates i The maintenance capacity of a train set under a given configuration, with a negative sign indicating maximization.

[0048] In one embodiment of the present invention, corresponding constraints are formulated in step S3, taking into account various constraints in the advanced maintenance capacity layout process, such as physical space limitations, the number and technical level of technicians, working time constraints, economic feasibility, etc., to ensure that the generated layout plan meets the actual feasibility requirements; In the constraint setting stage, various constraints in the point layout process need to be considered, including: Physical space limitations, such as the maximum space allowed by the productivity layout; Restrictions on the number and technical level of technical personnel, such as the number of various types of technical personnel, the technical level of technical personnel, etc.; Restrictions on working time constraints, such as technical personnel working hours, maximum working time of a single device, etc.; Economic feasibility constraints, such as the budget for each maintenance activity.

[0049] These constraints are set to ensure the feasibility and economy of the productivity layout.

[0050] The constraints are set as follows: 1. Physical space limitations

[0051] in, Indicates i The space required for each maintenance station, is the maximum available space.

[0052] 2. Constraints on the number of technical personnel and their technical level

[0053] in, Indicates i The demand for technical personnel It is the maximum number of technicians that can be deployed.

[0054] 3. Working time limit

[0055] in, Indicates i The working time of each maintenance activity, is the maximum allowed working time.

[0056] 4. Limitations of economic feasibility

[0057] in, Indicates i budget for maintenance activities, It is the total budget ceiling.

[0058] S4: A hybrid NSGA-II (Non-dominated Sorting Genetic Algorithm II) and PSO (Particle Swarm Optimization) algorithm is used to solve and generate a detailed productivity layout planning scheme, including layout location, scale and expected effect evaluation, which realizes efficient planning and layout of large-scale complex road networks and effectively improves computing efficiency.

[0059] In one embodiment of the present invention, when performing multi-objective optimization solution on the multi-objective optimization model of the vehicle base productivity layout, a hybrid NSGA-II (Non-dominated Sorting Genetic Algorithm II) and PSO (Particle Swarm Optimization) algorithm is used for solution, thereby realizing efficient planning and optimization of the advanced maintenance productivity layout, effectively improving the computational efficiency, making the planning process faster and more accurate, and being able to find the optimal layout solution while considering multiple objectives.

[0060] For the sake of reference, a specific solution process is provided, including the following steps: Step 1: Initialize the population First generate the initial population: A group of individuals are randomly generated as the initial population. Each individual represents a possible productivity layout scheme.

[0061] At the same time, the velocity vector is initialized for each individual (for subsequent PSO update operations).

[0062] Then define the variable scope: According to the specific requirements of the problem, determine the upper and lower bounds of each decision variable to ensure that the generated solution is within the feasible domain.

[0063] Step 2: Calculate the objective function value The embodiment of the present invention calculates the objective function value of each individual: For each individual, calculate the values ​​of the four sub-objective functions: minimize the maintenance cycle and time , maximize resource utilization , minimize maintenance costs and maximize EMU maintenance capabilities .

[0064] These sub-objective functions are combined into the overall objective function

[0065] in, , , , is the weight coefficient of each sub-objective function Step 3: Non-dominated sorting and crowding distance calculation 1. Non-dominated sorting: Sort the individuals in the population according to the non-dominated relationship to form different fronts. The non-dominated individuals are located in the first front, and the other individuals are arranged in the following fronts.

[0066] 2. Calculate the crowding distance: For each individual in the frontier, calculate its crowding distance to keep the solution distribution on the Pareto front uniform. The larger the crowding distance, the more important the individual is in the frontier.

[0067] Step 4: Select an Action The embodiment of the present invention selects the next generation of individuals based on non-dominated sorting and crowding distance: Individuals located at higher frontiers (with higher non-dominance) are preferred.

[0068] Within the same front, individuals with larger crowding distances are selected to maintain diversity.

[0069] Step 5: PSO Update Operation 1. Update the particle's velocity and position: Use the PSO update formula to update the speed and position of each individual:

[0070]

[0071] in, is the current speed, is the current location, is the best position for an individual. is the global best position, is the inertia weight, and is the learning factor, and is a random number.

[0072] 2. Boundary processing: Make sure that the newly generated individuals are still within the variable range, and those that are out of bounds should be repaired or regenerated.

[0073] Step 6: Crossover and mutation operations 1. Crossover operation: Select two individuals from the current population to perform single-point crossover and multi-point crossover operations to generate new offspring individuals.

[0074] 2. Mutation operation: Perform bit-flip mutation operations on newly generated offspring individuals to increase population diversity.

[0075] Step 7: Update the population 1. Merge parent and child: The parent and offspring individuals are merged to form a new population.

[0076] 2. Select the next generation population: The next generation population is selected from the merged population based on non-dominated sorting and crowding distance.

[0077] Step 8: Adaptive parameter adjustment The embodiment of the present invention dynamically adjusts the crossover probability and mutation probability : According to the different stages of evolution, the crossover probability and mutation probability are dynamically adjusted to meet the needs of different stages. In the early stage, a higher mutation probability is used to increase population diversity, and in the later stage, the mutation probability is reduced to increase the convergence speed.

[0078] Step 9: Local Search Enhancement The embodiment of the present invention introduces a local search algorithm: In each generation, a local search algorithm (such as simulated annealing SA) is introduced to perform local search on some individuals to improve the local search capability. The specific operation includes generating neighborhood solutions and deciding whether to accept the new solution based on the objective function value.

[0079] Step 10: Constraint handling mechanism The embodiment of the present invention provides processing constraints: For individuals that violate constraints, penalty functions or repair mechanisms are used to handle them. For example, for constraints such as physical space limitations, the number and skill level of technicians, working time constraints, and economic feasibility, the feasibility of the solution can be ensured by adding penalty items or directly repairing individuals.

[0080] Step 11: Termination Condition The embodiment of the present invention checks the termination condition: When the maximum number of iterations is reached or the fitness value of the population changes less than a certain threshold, the iteration stops, and the final set of Pareto optimal solutions is output.

[0081] In specific implementation, the method proposed in the technical solution of the present invention can be implemented by technical personnel in this field using computer software technology to realize automatic operation process. System devices for implementing the method, such as computer-readable storage media storing the corresponding computer program of the technical solution of the present invention and computer equipment running the corresponding computer program, should also be within the scope of protection of the present invention.

[0082] The electronic device for high-level maintenance capacity layout of EMUs with large-scale and complex road networks provided by the present invention is described below. The electronic device for high-level maintenance capacity layout of EMUs with large-scale and complex road networks described below and the method for high-level maintenance capacity layout of EMUs with large-scale and complex road networks described above can be referenced to each other.

[0083] The electronic device may include: a processor, a communications interface, a memory, and a communications bus, wherein the processor, the communications interface, and the memory communicate with each other via the communications bus. The processor may call the logic instructions in the memory to execute the advanced maintenance capacity layout method for large-scale complex road network EMUs, which mainly includes the software processing part in the above steps.

[0084] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0085] In another embodiment, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the software processing part of the advanced maintenance capacity layout method for large-scale complex road network EMUs provided by the above-mentioned methods.

[0086] In another embodiment, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the software processing portion of the advanced maintenance capacity layout method for large-scale complex road network EMUs provided by the above-mentioned methods.

[0087] The device embodiments described above are merely illustrative, wherein 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 modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0088] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these 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.

Claims

1. A method for high-level maintenance capacity layout of EMUs in a large-scale complex road network, characterized by: Including the following process, Collect data on EMU routes, EMU maintenance records, number and type of EMUs in operation, and conduct preliminary analysis on the collected results, which will be used as input for the multi-objective optimization model of the productivity layout of the vehicle base; Establish a multi-objective optimization model for the layout of vehicle base productivity, including determining the objective function of the layout of EMU advanced maintenance vehicle base productivity based on the multi-objective optimization objectives of the vehicle base productivity layout, and setting corresponding constraints based on various constraints in the layout process of advanced maintenance productivity; The multi-objective optimization model based on the vehicle base productivity layout is solved to obtain the advanced maintenance production capacity layout plan and output it.

2. According to the large-scale complex network EMU advanced maintenance capacity layout method of claim 1, it is characterized by: When conducting preliminary analysis of the collected results, random forest or support vector machine methods are used to implement data analysis.

3. The method for high-level maintenance capacity layout of EMUs in large-scale complex road networks according to claim 1 is characterized by: The multi-objective optimization objectives of the productivity layout of the EMU base include maintenance cycle and time, resource utilization, maintenance cost and EMU maintenance capacity.

4. According to the large-scale complex network EMU advanced maintenance capacity layout method of claim 1, it is characterized by: The various constraints in the advanced repair capacity layout process include the physical space limitations of advanced repair facilities, the number and technical level of technicians, working time limitations and economic feasibility limitations.

5. The method for high-level maintenance capacity layout of EMUs in large-scale complex road networks according to claim 1 is characterized by: A hybrid NSGA-II and PSO algorithm is used to solve the multi-objective optimization model based on the productivity layout of vehicle bases.

6. The method for high-level maintenance capacity layout of EMUs in large-scale complex road networks according to claim 1 is characterized by: The advanced maintenance production capacity layout plan includes the location of productivity layout, productivity scale, maintenance time per unit EMU, maintenance process flow line layout, production line configuration plan, maintenance components and spare parts, and effect prediction and evaluation.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the advanced maintenance capacity layout method for EMUs in a large-scale complex road network is implemented as described in any one of claims 1 to 6.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the advanced maintenance capacity layout method for EMUs in a large-scale complex road network is implemented as described in any one of claims 1 to 6.

9. A computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the advanced maintenance capacity layout method for EMUs in a large-scale complex road network is implemented as described in any one of claims 1 to 6.

Images