Heavy haul railway transportation optimization method, device, equipment, medium and product

Abstract

The invention relates to the technical field of heavy haul railway transportation optimization, in particular to a heavy haul railway transportation optimization method and device, equipment, a medium and a product, and the method comprises the steps: obtaining a unit train access marshalling form and an access moment; establishing a multi-objective optimization model based on a unit train access marshalling form and an access moment; solving the multi-objective optimization model by adopting an improved genetic algorithm; and outputting the solved heavy haul railway transportation collaborative optimization scheme. And the heavy haul railway transportation efficiency can be improved.

Description

Technical Field

[0001] This invention relates to the field of railway traffic management technology, and in particular to a method, apparatus, equipment, medium and product for optimizing heavy-haul railway transportation. Background Technology

[0002] Relying on traditional capacity expansion methods, the transport capacity of heavy-haul railways has reached its limit. Group operation mode, through vehicle-to-vehicle communication self-organizing network coordination, can significantly shorten the tracking interval between vehicles, representing a new direction for the capacity expansion and upgrading of heavy-haul railways. However, related optimization methods do not consider group operation mode, making it difficult to fully leverage its advantages and improve the efficiency of heavy-haul railway transport and the utilization rate of station arrival and departure track resources. There are technical problems in this field regarding how to improve the efficiency of heavy-haul railway transport. Summary of the Invention

[0003] This invention provides a method, apparatus, equipment, medium, and product for optimizing heavy-haul railway transportation, solving the technical problem of how to improve the efficiency of heavy-haul railway transportation.

[0004] In a first aspect, the present invention provides a method for optimizing heavy-haul railway transportation, comprising: step S01, obtaining the unit train access formation and access time; step S02, establishing a multi-objective optimization model based on the unit train access formation and access time; step S03, solving the multi-objective optimization model using an improved genetic algorithm; and step S04, outputting the solved heavy-haul railway transportation collaborative optimization scheme. Step S02, the step of establishing a multi-objective optimization model based on the unit train access formation and access time, includes: step S21, determining the objective function of the model as the shortest total travel time and the shortest sum of arrival and departure time on the occupied tracks; and step S22, determining the constraints of the model, including constraints on unit train group capacity, loading quantity, combined train parking decomposition, station arrival and departure track conflict, train running interval time, and train departure time.

[0005] In some embodiments, the unit train group capacity constraint includes: the number of unit trains included in the group train does not exceed a preset group number threshold, wherein the group train is a train formed by virtually connecting two or more unit trains.

[0006] In some embodiments, step S03, which uses an improved genetic algorithm to solve the multi-objective optimization model, includes: step S31, generating an initial solution using chromosome encoding; and step S32, performing an iterative optimization operation to solve the initial solution through evolution. The iterative optimization operation includes: decoding chromosome deduction run lines and arrival / departure line occupancy, calculating fitness, non-dominated sorting, calculating distance to the reference point, population selection, and crossover mutation.

[0007] In some embodiments, step S31, the step of generating an initial solution using chromosome encoding, includes: step S311, determining the variables of the first stage of chromosome as the arrival and departure lines and blocks accessed by the unit train; step S312, determining the variables of the second stage of chromosome as whether the unit train is grouped and the grouping form; step S313, determining the variables of the third stage of chromosome as the destination, departure time and decomposed station of the unit train.

[0008] In some embodiments, step S32, the step of iteratively optimizing the initial solution through evolutionary solutions, includes: step S321, decoding chromosomes to deduce the train's operating line information and arrival / departure line occupancy information; step S322, calculating the fitness value of each solution based on the operating line information and arrival / departure line occupancy information; step S323, performing non-dominated sorting on the solutions in the population to determine the dominance level of each solution; step S324, calculating the distance between each solution and a preset reference point to evaluate the uniformity of solution distribution; step S325, performing population selection based on dominance level and reference point distance to retain high-quality solutions; and step S326, performing crossover and mutation operations on the selected high-quality solutions to generate the next generation of evolutionary population.

[0009] In some embodiments, step S04, the step of outputting the solved heavy-haul railway transportation collaborative optimization scheme, includes: step S41, outputting the frontier solution set from the multi-objective optimization model; step S42, parsing the scheme of the frontier solution set into train group plan and operation diagram, arrival and departure line occupancy diagram, to obtain the heavy-haul railway transportation collaborative optimization scheme.

[0010] Secondly, the present invention provides a heavy-haul railway transportation optimization device, comprising: a data collection module for acquiring the unit train access formation and access time; a model building module for establishing a multi-objective optimization model based on the unit train access formation and access time; a model solving module for solving the multi-objective optimization model using an improved genetic algorithm; and a display module for outputting the obtained heavy-haul railway transportation collaborative optimization scheme.

[0011] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method of any of the above aspects.

[0012] Fourthly, the present invention provides an electronic device including a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the method of any of the above aspects.

[0013] Fifthly, the present invention provides a computer program product, including a computer program that, when executed by a processor, implements a method for any of the above aspects.

[0014] This invention provides a method, apparatus, equipment, medium, and product for optimizing heavy-haul railway transportation. The method includes: step S01, obtaining the unit train access formation and access time; step S02, establishing a multi-objective optimization model based on the unit train access formation and access time; step S03, solving the multi-objective optimization model using an improved genetic algorithm; and step S04, outputting the obtained collaborative optimization scheme for heavy-haul railway transportation. This invention can solve the technical problem of how to improve the efficiency of heavy-haul railway transportation. Attached Figure Description

[0015] The invention will now be described in more detail with reference to embodiments and the accompanying drawings: Figure 1 A flowchart illustrating a method for optimizing heavy-haul railway transportation according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a heavy-haul railway transportation optimization device provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the overall encoding form of a solution provided in an embodiment of the present invention; Figure 4 A train group planning and operation diagram provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the occupancy of arrival and departure tracks at a section originating technical station, provided as an embodiment of the present invention.

[0016] In the accompanying drawings, the same parts are referred to by the same reference numerals, and the drawings are not drawn to scale. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present invention and to fully understand and implement the process of how the present invention uses technical means to solve technical problems and achieve corresponding technical effects, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. The embodiments of the present invention and the various features therein can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0019] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0020] Relying on traditional capacity expansion methods, the transport capacity of heavy-haul railways has reached its limit. Group operation mode, through vehicle-to-vehicle communication self-organizing network coordination, can significantly shorten the tracking interval between vehicles, representing a new direction for the capacity expansion and upgrading of heavy-haul railways. However, related optimization methods do not consider group operation mode, making it difficult to fully leverage its advantages and improve the efficiency of heavy-haul railway transport and the utilization rate of station arrival and departure track resources. There are technical problems in this field regarding how to improve the efficiency of heavy-haul railway transport.

[0021] To address the aforementioned technical problem of improving the efficiency of heavy-haul railway transportation, this invention proposes a method, apparatus, equipment, medium, and product for optimizing heavy-haul railway transportation. The implementation details of this invention are described below. The following content is provided for ease of understanding and is not essential for implementing this solution.

[0022] Example 1 Figure 1 This is a flowchart illustrating a method for optimizing heavy-haul railway transportation provided in an embodiment of this application, as shown below. Figure 1 As shown, in the technical solution of this embodiment, a method for optimizing heavy-haul railway transportation is provided, including: step S01, obtaining the unit train access formation and access time; step S02, establishing a multi-objective optimization model based on the unit train access formation and access time; step S03, solving the multi-objective optimization model using an improved genetic algorithm; and step S04, outputting the obtained collaborative optimization scheme for heavy-haul railway transportation.

[0023] Traditional transportation planning fails to adequately consider the utilization of arrival and departure tracks, resulting in long train waiting times and limited track capacity. With increasing freight volume, the conflict between transportation planning and arrival / departure track utilization becomes more pronounced, necessitating a method of deep collaborative optimization to improve transportation efficiency and the utilization rate of arrival / departure track resources, thereby achieving efficient operation of heavy-haul railway transportation. Under group operation mode, heavy-haul railway transportation faces problems such as poor coordination of transportation planning, low transportation efficiency, and low utilization rate of arrival / departure track resources.

[0024] In this embodiment, the technical solution first obtains information such as the unit train's access formation and access time. Then, a multi-objective optimization model is established, with the shortest total travel time and the shortest sum of arrival / departure track usage time as the objective function. An improved genetic algorithm is then used to solve the model, employing a global search based on the algorithm's mechanical energy to find the optimal solution. Finally, a collaborative optimization scheme for heavy-haul railway transportation is output. Here, "unit train" is a general term for various heavy-haul train types on heavy-haul railways. By processing unit train information and constructing an optimization model, the coordination between transportation planning and arrival / departure track utilization is achieved.

[0025] The technical solution in this embodiment achieves deep coordination of transportation planning by establishing a multi-objective optimization model and using an improved genetic algorithm for solving the problem. Taking a heavy-haul railway as an example, after implementing this solution, the total travel time is significantly shortened, train turnover is accelerated, and line capacity is improved. At the same time, the time spent on arrival and departure tracks is reduced, improving the utilization rate of station arrival and departure track resources and releasing station operational capacity. This solution also outputs multiple optimization schemes, providing decision-makers with more choices and allowing for flexible decision-making based on different operational priorities, thus enhancing the flexibility and adaptability of transportation organization.

[0026] Example 2 Based on the above embodiments, step S02, which is the step of establishing a multi-objective optimization model based on the unit train access grouping form and access time, includes: step S21, determining the objective function of the model as the shortest total travel time and the shortest sum of arrival and departure time occupied; step S22, determining the constraints of the model, including unit train group capacity constraints, loading quantity constraints, combined train parking decomposition constraints, station arrival and departure line conflict constraints, train running interval time constraints, and train departure time constraints.

[0027] The unit train group capacity constraint includes: the number of unit trains in a group of trains does not exceed a preset group number threshold, wherein a group of trains is formed by virtually connecting two or more unit trains. The group number threshold is determined, for example, by the effective parking length of a single track on the station's arrival / departure lines and the length of the unit trains.

[0028] Existing models often fail to comprehensively cover all factors in transportation, such as constraints like train group capacity, loading quantity, and station arrival / departure line conflicts. This leads to a disconnect between the model and actual transportation conditions, hindering the optimization of transportation plans. In real-world heavy-haul railway transportation scenarios, these factors are interrelated and significantly impact transportation efficiency and resource utilization, necessitating the construction of a collaborative optimization model that comprehensively considers multiple factors. The technical problem this embodiment aims to solve is how to construct a multi-objective collaborative optimization model in heavy-haul railway transportation that fully considers the utilization of departure lines.

[0029] In this embodiment, the objective functions of the multi-objective optimization model are defined as minimizing the total travel time and minimizing the sum of arrival and departure track usage time. These two objectives are directly related to transportation efficiency and the utilization of arrival and departure track resources. Constraints are defined, including unit train group capacity constraints to ensure reasonable group size; loading quantity constraints to ensure that transportation tasks match actual loading capacity; combined train stopping decomposition constraints to standardize train operation procedures; station arrival and departure track conflict constraints to avoid conflicts in track usage; and train running interval time constraints and train departure time constraints to ensure train operation safety and order. By clarifying these objective functions and constraints, a comprehensive and effective multi-objective collaborative optimization model is constructed.

[0030] The technical solution in this embodiment provides a computer system based on a specific computational model by constructing a multi-objective collaborative optimization model that considers multiple factors, thereby achieving refined transportation planning. In practical applications, this model can effectively coordinate various aspects of transportation, reducing train waiting time and arrival / departure line conflicts. Taking a certain station as an example, after applying this model, the number of arrival / departure line conflicts was significantly reduced, the average train waiting time was shortened, and station operational efficiency and line throughput capacity were improved.

[0031] Example 3 Based on the above embodiments, step S03, which uses an improved genetic algorithm to solve the multi-objective optimization model, includes: step S31, generating an initial solution using chromosome encoding; step S32, performing evolutionary optimization on the initial solution through iterative optimization operations, including: decoding chromosome deduction run lines and arrival / departure line occupancy, calculating fitness, non-dominated sorting, calculating distance to reference point, population selection, and crossover mutation.

[0032] Traditional solution methods are prone to getting trapped in local optima when dealing with complex models, and their low efficiency fails to meet the real-time and high-efficiency requirements of heavy-haul railway transportation. Faced with large amounts of transportation data and complex constraints, traditional algorithms struggle to find the optimal solution quickly and accurately, resulting in lengthy transportation planning times and an inability to adapt to changes in transportation demand. The technical problem this embodiment aims to solve is how to efficiently solve a multi-objective model of co-optimization of group planning and transportation planning using an improved genetic algorithm.

[0033] In this embodiment, the initial solution is generated using chromosome encoding. The solution is encoded as a chromosome, with its segments corresponding to variables in three decision-making stages, including unit train access to arrival / departure tracks and blocks, whether to form a train formation and its formation format, departure time, and decomposed stations. The initial solution is then iteratively optimized through operations such as decoding the chromosome to deduce the operating lines and arrival / departure track occupancy, calculating fitness, non-dominated sorting, calculating distance to the reference point, population selection, and crossover mutation, continuously evolving the population to find a better solution.

[0034] The technical solution in this embodiment improves the efficiency and accuracy of the solution by employing an improved genetic algorithm. In practical applications, it can quickly generate high-quality transportation collaborative optimization schemes and reduce solution time. Taking a heavy-haul railway transportation system as an example, the improved algorithm significantly shortens the solution time and yields a more uniformly distributed Pareto front solution set, providing decision-makers with more high-quality options and effectively enhancing the solution performance and reliability of the heavy-haul railway transportation collaborative optimization scheme.

[0035] Example 4 Based on the above embodiments, step S31, which uses chromosome encoding to generate an initial solution, includes: step S311, determining the variables of the first stage of chromosome as the arrival and departure lines and blocks accessed by the unit train; step S312, determining the variables of the second stage of chromosome as whether the unit train is grouped and the grouping form; and step S313, determining the variables of the third stage of chromosome as the destination, departure time, and decomposed stations of the unit train.

[0036] In heavy-haul railway transportation, group planning and transportation planning involve multiple complex decision-making stages, such as the access, marshalling, and destination of unit trains. Related encoding methods often fail to accurately reflect these decision variables and their interrelationships, causing genetic algorithms to be unable to effectively search for the optimal solution during the solution process, thus affecting the optimization effect of the transportation plan. The technical problem to be solved in this embodiment is how to design chromosome-encoded decision variables to accurately map the multi-stage decision-making process of co-optimization of group planning and transportation planning.

[0037] In this embodiment, the variables for the first stage of the chromosome analysis are the arrival / departure tracks and blocks where the unit train connects. These variables determine the initial stopping position of the unit train at the station, affecting subsequent operational processes. The variables for the second stage are whether the unit train is grouped and its grouping format. The grouping decision directly affects the train's transport capacity and efficiency. The variables for the third stage are the unit train's destination, departure time, and decomposed stations. These variables determine the train's transport path and final state. By designing decision variables for these three stages, the multi-stage decision-making process is accurately mapped.

[0038] The technical solution in this embodiment, by designing chromosome-encoded decision variables, enables the genetic algorithm to better understand and handle the collaborative optimization problem of group planning and transportation planning. This improves the algorithm's search efficiency and accuracy, allowing it to find better transportation planning solutions more quickly. Taking a heavy-haul railway as an example, after adopting this encoding method, the overall efficiency of the transportation plan is improved, the utilization of arrival and departure track resources is more rational, train waiting time and conflicts are reduced, and transportation efficiency is improved.

[0039] Example 5 Based on the above embodiments, step S32, which involves iteratively optimizing the initial solution through evolutionary optimization, includes: step S321, decoding chromosomes to deduce the train's operating line information and arrival / departure line occupancy information; step S322, calculating the fitness value of each solution based on the operating line information and arrival / departure line occupancy information; step S323, performing non-dominated sorting on the solutions in the population to determine the dominance level of each solution; step S324, calculating the distance between each solution and a preset reference point to evaluate the uniformity of solution distribution; step S325, combining the dominance level and the distance to the reference point to select population and retain high-quality solutions; and step S326, performing crossover and mutation operations on the selected high-quality solutions to generate the next generation of evolutionary population.

[0040] The technical problem this embodiment aims to solve is how to improve the iterative optimization of genetic algorithms to ensure that the solution process can efficiently generate a uniformly distributed and high-quality Pareto front solution set, thereby improving the solution effect and reliability of the heavy-haul railway transportation collaborative optimization scheme. Traditional genetic algorithms are prone to problems such as loss of population diversity and premature convergence during the iterative process, resulting in the inability to obtain a uniformly distributed Pareto front solution set. This leads to a lack of diversity and adaptability in the final transportation collaborative optimization scheme, failing to meet different operational needs.

[0041] In this embodiment, the technical solution first decodes the chromosomes to deduce the train's operating line information and arrival / departure line occupancy information. Based on this, the fitness value of each solution is calculated to evaluate its quality. The solutions in the population are then sorted using non-dominated methods to determine their dominance level, distinguishing between high-quality and low-quality solutions. The distance between each solution and a preset reference point is calculated to assess the uniformity of solution distribution and avoid concentrated distribution. Population selection is performed based on dominance level and reference point distance, retaining high-quality solutions. Crossover and mutation operations are performed on the selected high-quality solutions to introduce new genes, generating the next generation of the evolutionary population and continuously optimizing the population.

[0042] The technical solution in this embodiment effectively avoids the shortcomings of traditional genetic algorithms through iterative optimization. In practical applications, it can efficiently generate uniformly distributed and high-quality Pareto front solution sets. Taking a heavy-haul railway transportation scenario as an example, after adopting this iterative optimization method, the number of transportation collaborative optimization schemes obtained not only increases, but also covers schemes with different focuses. Decision-makers can flexibly choose according to actual operational needs, greatly improving the solution effect and reliability of heavy-haul railway transportation collaborative optimization schemes and enhancing the flexibility of transportation organization.

[0043] Example 6 Based on the above embodiments, step S04, which outputs the solution obtained for the collaborative optimization scheme of heavy-haul railway transportation, includes: step S41, outputting the frontier solution set from the multi-objective optimization model; step S42, parsing the scheme of the frontier solution set into train group plans and operation diagrams, and arrival and departure line occupancy diagrams, to obtain the collaborative optimization scheme of heavy-haul railway transportation.

[0044] If the results of heavy-haul railway transportation plan optimization are not presented clearly and intuitively to decision-makers, it will be difficult for them to understand and apply the optimization scheme. Traditional result output methods often simply list data without visualization, making it impossible for decision-makers to quickly grasp key information of the transportation plan, such as train group plans and operation status, arrival and departure track occupancy, etc., which is not conducive to decision-making and implementation. The technical problem to be solved in this embodiment is how to output and intuitively display the collaborative optimization results.

[0045] In this embodiment, the technical solution first outputs a leading edge solution set from the multi-objective optimization model. This solution set contains multiple feasible collaborative optimization schemes. The schemes in the leading edge solution set are then parsed into a train group schedule and operation diagram, and an arrival / departure track occupancy diagram. The train group schedule and operation diagram graphically displays information such as train schedules, routes, and train formations; the arrival / departure track occupancy diagram clearly shows the usage of each arrival / departure track at different time periods. These two diagrams transform the abstract optimization results into an intuitive and easy-to-understand form.

[0046] The technical solution in this embodiment improves decision-making efficiency by interpreting the results of collaborative optimization into intuitive charts. Decision-makers can quickly understand the overall transportation plan and accurately grasp the train operation and arrival / departure track usage through train group plans and operation diagrams and arrival / departure track occupancy diagrams.

[0047] Example 7 Figure 2 This is a schematic diagram of the structure of a heavy-haul railway transportation optimization device provided in an embodiment of this application, as shown below. Figure 2 As shown in the technical solution of this embodiment, a heavy-haul railway transportation optimization device is provided, including: a data collection module for acquiring the unit train access formation and access time; a model building module for establishing a multi-objective optimization model based on the unit train access formation and access time; a model solving module for solving the multi-objective optimization model using an improved genetic algorithm; and a display module for outputting the obtained heavy-haul railway transportation collaborative optimization scheme.

[0048] Traditional transportation planning fails to adequately consider the utilization of arrival and departure tracks, resulting in long train waiting times and limited track capacity. With increasing freight volume, the conflict between transportation planning and arrival / departure track utilization becomes more pronounced, necessitating a method of deep collaborative optimization to improve transportation efficiency and the utilization rate of arrival / departure track resources, thereby achieving efficient operation of heavy-haul railway transportation. Under group operation mode, heavy-haul railway transportation faces problems such as poor coordination of transportation planning, low transportation efficiency, and low utilization rate of arrival / departure track resources.

[0049] In this embodiment, the technical solution first obtains information such as the unit train's access formation and access time. Then, a multi-objective optimization model is established, with the shortest total travel time and the shortest sum of arrival / departure track usage time as the objective function. An improved genetic algorithm is then used to solve the model, employing a global search based on the algorithm's mechanical energy to find the optimal solution. Finally, a collaborative optimization scheme for heavy-haul railway transportation is output. Here, "unit train" is a general term for various heavy-haul train types on heavy-haul railways. By processing unit train information and constructing an optimization model, the coordination between transportation planning and arrival / departure track utilization is achieved.

[0050] The technical solution in this embodiment achieves deep coordination of transportation planning by establishing a multi-objective optimization model and using an improved genetic algorithm for solving the problem. Taking a heavy-haul railway as an example, after implementing this solution, the total travel time is significantly shortened, train turnover is accelerated, and line capacity is improved. At the same time, the time spent on arrival and departure tracks is reduced, improving the utilization rate of station arrival and departure track resources and releasing station operational capacity. This solution also outputs multiple optimization schemes, providing decision-makers with more choices and allowing for flexible decision-making based on different operational priorities, thus enhancing the flexibility and adaptability of transportation organization.

[0051] Other technical features of this embodiment correspond to those of the above embodiments, and will not be repeated here.

[0052] Example 8 In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the method of any one of the above embodiments, including: Step S01: Obtain the unit train access formation and access time; Step S02: Establish a multi-objective optimization model based on the unit train access formation and access time; Step S03: Solve the multi-objective optimization model using an improved genetic algorithm; Step S04: Output the obtained heavy-haul railway transportation collaborative optimization scheme.

[0053] In some embodiments, step S02, the step of establishing a multi-objective optimization model based on the unit train access grouping form and access time, includes: step S21, determining the objective function of the model as the shortest total travel time and the shortest sum of arrival and departure time occupied; step S22, determining the constraints of the model, including unit train group capacity constraints, loading quantity constraints, combined train parking decomposition constraints, station arrival and departure line conflict constraints, train running interval time constraints, and train departure time constraints.

[0054] In some embodiments, step S03, which uses an improved genetic algorithm to solve the multi-objective optimization model, includes: step S31, generating an initial solution using chromosome encoding; and step S32, performing an iterative optimization operation to solve the initial solution through evolution. The iterative optimization operation includes: decoding chromosome deduction run lines and arrival / departure line occupancy, calculating fitness, non-dominated sorting, calculating distance to the reference point, population selection, and crossover mutation.

[0055] In some embodiments, step S31, the step of generating an initial solution using chromosome encoding, includes: step S311, determining the variables of the first stage of chromosome as the arrival and departure lines and blocks accessed by the unit train; step S312, determining the variables of the second stage of chromosome as whether the unit train is grouped and the grouping form; step S313, determining the variables of the third stage of chromosome as the destination, departure time and decomposed station of the unit train.

[0056] In some embodiments, step S32, the step of iteratively optimizing the initial solution through evolutionary solutions, includes: step S321, decoding chromosomes to deduce the train's operating line information and arrival / departure line occupancy information; step S322, calculating the fitness value of each solution based on the operating line information and arrival / departure line occupancy information; step S323, performing non-dominated sorting on the solutions in the population to determine the dominance level of each solution; step S324, calculating the distance between each solution and a preset reference point to evaluate the uniformity of solution distribution; step S325, performing population selection based on dominance level and reference point distance to retain high-quality solutions; and step S326, performing crossover and mutation operations on the selected high-quality solutions to generate the next generation of evolutionary population.

[0057] In some embodiments, step S04, the step of outputting the solved heavy-haul railway transportation collaborative optimization scheme, includes: step S41, outputting the frontier solution set from the multi-objective optimization model; step S42, parsing the scheme of the frontier solution set into train group plan and operation diagram, arrival and departure line occupancy diagram, to obtain the heavy-haul railway transportation collaborative optimization scheme.

[0058] In the technical solution of this embodiment, an electronic device is provided, including a processor and a memory. The memory stores a computer program, and the processor executes the computer program to implement the method of any of the above embodiments.

[0059] In the technical solution of this embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0060] The processor may include, but is not limited to, one or more processors or microprocessors. Each processor may be implemented as an Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor, or other electronic component, for performing the methods in the above embodiments. The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, and may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0061] Computer-readable storage media may also store at least one computer-executable program / instruction, such as computer-readable instructions. Computer-readable storage media include, but are not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Computer-readable storage media may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device executes the computer-readable instructions stored on the computer-readable storage medium, the various methods described above can be performed.

[0062] In addition, the computer device may also include (but is not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (e.g., a keyboard, mouse, speakers, etc.). The processor can communicate with external devices via the I / O bus through a wired or wireless network. In one embodiment, the at least one computer-executable instruction may also be compiled into or comprise a software product / computer program product, wherein one or more computer-executable instructions, when executed by the processor, perform the steps of the various functions and / or methods in the embodiments described herein.

[0063] Example 9 Based on the above embodiments, this embodiment provides an application example.

[0064] This application example and solution pertain to the field of heavy-haul railway transportation planning. Currently, relying on traditional capacity expansion methods, the transportation capacity of heavy-haul railways is approaching its bottleneck. Group operation mode, through car-to-car communication self-organizing network collaboration, can significantly shorten the tracking interval between cars, representing a new direction for capacity expansion and upgrading of heavy-haul railways and other railways. Therefore, researching and proposing a method that can deeply collaboratively optimize group planning and operation plans, while comprehensively considering the constraints of departure line resources, is of great significance.

[0065] Currently, there are two main approaches to related technologies. The first approach is to optimize the use of arrival and departure lines individually: This type of method usually optimizes the use of arrival and departure lines locally under the premise that the train operation plan has been determined, but it fails to achieve coordination between plans from the root. The second approach is to coordinate optimization in the context of a single train: Although this type of method considers coordination, its model and constraints are based on the traditional single-train operation mode, and it lacks the ability to characterize the holistic constraints unique to group operation (such as grouping / ungrouping order, group size, and parking order of unit trains on arrival and departure lines).

[0066] Although existing technologies exist for planning heavy-haul railway transportation, the group operation mode is relatively new, and most existing methods do not take it into consideration. Furthermore, they do not consider the use of departure lines in the group operation mode when planning heavy-haul railway transportation. Therefore, it is difficult to fully leverage the advantages of the group operation mode, which limits the efficiency of heavy-haul railway transportation and the utilization rate of station arrival and departure line resources.

[0067] The purpose of this solution is to address how to achieve deep collaborative optimization of heavy-haul railway group planning and transportation planning under the group operation mode, taking into account the use of departure lines, in order to improve transportation efficiency and the utilization rate of arrival and departure line resources.

[0068] Figure 3 This is a schematic diagram of the overall encoding form of a solution provided in an embodiment of the present invention; Figure 4 A train group planning and operation diagram provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the occupancy of arrival and departure tracks at a section originating technical station, provided as an embodiment of the present invention.

[0069] This scheme constructs a multi-objective optimization model with the objectives of minimizing the total travel time and the sum of arrival and departure times. An improved genetic algorithm (R-NSGA-II) is used to solve the model, outputting a Pareto front solution set. This yields multiple collaborative optimization schemes that comprehensively consider the utilization of departure lines, combining group planning and operational planning, providing decision-makers with options. The specific steps are as follows: S1: Data Input. Input the various parameters required for the unit train connection, such as train formation, timetable, and algorithm. S2: Establish a multi-objective optimization model. The objective function of the model is to minimize the total travel time and the sum of the time spent on arrival and departure tracks; the constraints include the capacity of unit train combinations or groups, the number of cars loaded, the decomposition of combined train stops, station arrival and departure track conflicts, train running intervals, and train departure times.

[0070] S3: Model Solving. The model is solved using a non-dominated sorting genetic algorithm (R-NSGA-II) with an elitist preservation strategy and reference point guidance. This includes encoding and initial solution, and iterative optimization steps. S31: Encoding and Initial Solution. Encode the solution as a chromosome (e.g., ...). Figure 3 As shown), the fragments correspond to variables in the three decision-making stages: The decision variables in the first stage are which arrival / departure line and which block the unit train will connect to; The decision variables for the second stage are whether the unit trains are grouped together and the grouping format; The decision variables for the third stage are the destination, departure time, and breakdown station of the unit train.

[0071] S32: Iterative optimization. The population continuously evolves through operations such as decoding chromosome deduction of run lines and arrival / departure line occupancy, calculating fitness, non-dominated sorting, calculating distance to reference point, population selection, and crossover mutation.

[0072] S4: Output Results. The algorithm ultimately outputs a Pareto front solution set, where each solution represents a feasible co-optimization scheme. Decision-makers can select the final scheme based on actual needs. The final scheme can be visually represented as a train group plan and operation diagram (e.g., Figure 4 (as shown) and arrival / departure line occupancy diagram (as shown) Figure 5 (As shown).

[0073] The beneficial effects of this plan include at least the following: ① Deep collaboration was achieved. The three core elements of group planning, operation planning, and arrival / departure lines were uniformly coupled and optimized in the model, breaking the limitations of individual optimization.

[0074] ② Improved transportation efficiency. By minimizing total travel time, it accelerated vehicle turnaround and increased route capacity.

[0075] ③ Improved resource utilization. By minimizing the time spent on arrival and departure tracks, this key resource of the station can be used more efficiently, freeing up station operational capacity.

[0076] ④ It provides decision-making flexibility. The output Pareto solution set provides decision-makers with multiple "optimal" trade-offs, which can be flexibly selected according to the operational priorities at different times.

[0077] Key aspects of this plan include: ① Design and coding of three-stage decision variables: The complex transportation organization problem is reasonably decomposed and mapped onto the chromosome structure of the genetic algorithm.

[0078] ② Solution strategy based on improved genetic algorithm (R-NSGA-II): In particular, the non-dominated sorting and reference point guidance mechanism ensure that a uniformly distributed Pareto optimal solution set can be obtained in the end.

[0079] This solution combines group planning, operational planning, and arrival / departure lines into a single model for collaborative optimization.

[0080] This scheme employs a multi-objective optimization model (the objective function is to minimize the total travel time and the sum of arrival and departure times; constraints include unit train combination or group capacity, number of cars loaded, decomposition of combined train stops, station arrival and departure line conflicts, train running interval time, and train departure time, etc.); a specific method for chromosome encoding; specific steps and methods for solving the problem using the improved algorithm (R-NSGA-II); and a computer system for implementing the above methods.

[0081] In addition to using the improved genetic algorithm (R-NSGA-II), other algorithms such as the ε-constraint method and the non-dominated sorting genetic algorithm (NSGA-III) can also be used to solve the model.

[0082] In addition to chromosome coding, other coding methods (such as real number coding and matrix coding) can also be used for coding.

[0083] Furthermore, the objective function can be modified. The invention's purpose of "improving efficiency and resource utilization" remains unchanged, but the objective function can be added to or replaced. For example, "minimizing arrival and departure line occupancy time" can be replaced with "maximum balance of arrival and departure line utilization," or "optimal train arrival and departure route conditions" can be added as a third objective.

[0084] The application scenario can also be changed. This method is not only applicable to heavy-haul railways such as the Shenshuo Railway, but its core idea can also be applied to other railway systems that adopt group operation mode (such as urban rail transit and high-speed railways), simply by adjusting the parameters and constraints in their models.

[0085] Group planning: Through coordinated control and transportation organization technology of train group operation, a plan is proposed to specify key elements such as the grouping and disgrouping stations of group trains, group size, group type of unit trains, parking order of unit trains on arrival and departure lines, and grouping order within group trains.

[0086] Train operation plan: A detailed plan that includes the scheduling of train operations, route planning, station stops, and the rational allocation of related transportation resources.

[0087] Unit train: Currently, this is a general term for various types of heavy-haul trains on heavy-haul railways.

[0088] Train group: A train formed by virtual connection of two or more unit trains through train group operation collaborative control technology.

[0089] Grouping: The process by which unit trains are virtually connected and combined into a group of trains at the station through train group operation collaborative control technology before departing from the station.

[0090] Degrouping: The process by which a group of trains is broken down into individual trains or parts of a group of trains at a station using train group operation coordination control technology.

[0091] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0092] It should be noted that, in this invention, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element limited by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0093] While the embodiments disclosed in this invention are as described above, the above content is merely for the purpose of facilitating understanding of this invention and is not intended to limit the invention. Any person skilled in the art to which this invention pertains may make any modifications and changes in form and detail of the implementation without departing from the spirit and scope disclosed in this invention; however, the scope of patent protection of this invention shall still be determined by the scope defined in the appended claims.

Claims

1. A method for optimizing heavy-haul railway transportation, characterized in that, include: Step S01: Obtain the unit train access formation and access time; Step S02: Establish a multi-objective optimization model based on the unit train access formation and access time; Step S03: Solve the multi-objective optimization model using an improved genetic algorithm; Step S04: Output the cooperative optimization scheme for heavy-haul railway transportation obtained by the solution. Step S02, which involves establishing a multi-objective optimization model based on the unit train access formation and access time, includes: Step S21: Determine the objective function of the model as the shortest total travel time and the shortest sum of arrival and departure times. Step S22: Determine the constraints of the model. The constraints include unit train group capacity constraints, loading quantity constraints, combined train parking decomposition constraints, station arrival and departure line conflict constraints, train running interval time constraints, and train departure time constraints.

2. The method according to claim 1, characterized in that, The capacity constraints of the unit train group include: The number of unit trains included in a group train does not exceed the preset group number threshold, wherein a group train is a train formed by virtually connecting two or more unit trains.

3. The method according to claim 1, characterized in that, Step S03, which involves solving the multi-objective optimization model using an improved genetic algorithm, includes: Step S31: Generate an initial solution using chromosome encoding. Step S32: The initial solution is solved through iterative optimization operations, which include: decoding chromosome deduction run lines and arrival / departure line occupancy, calculating fitness, non-dominated sorting, calculating distance to reference point, population selection, and crossover mutation.

4. The method according to claim 3, characterized in that, Step S31, the step of generating an initial solution using chromosome encoding, includes: Step S311: Determine the variables for the first stage of chromosome analysis as the arrival / departure lines and blocks accessed by the unit train; Step S312: Determine whether the unit trains are grouped and the grouping format as variables in the second stage of chromosome analysis. Step S313: Determine the variables for the third stage of chromosome as the destination, departure time, and decomposition station of the unit train.

5. The method according to claim 3, characterized in that, Step S32, the step of iteratively optimizing the initial solution, includes: Step S321: Decode the chromosome to deduce the running line information and arrival / departure line occupancy information of the unit train; Step S322: Calculate the fitness value of each solution based on the running line information and arrival / departure line occupancy information; Step S323: Perform non-dominated sorting on the solutions in the population to determine the dominance level of each solution; Step S324: Calculate the distance between each solution and the preset reference point, and evaluate the uniformity of solution distribution; Step S325: Combine dominance level and reference point distance to perform population selection and retain high-quality solutions; Step S326: Perform crossover and mutation operations on the selected high-quality solutions to generate the next generation of evolutionary population.

6. The method according to claim 1, characterized in that, Step S04, which involves outputting the solved collaborative optimization scheme for heavy-haul railway transportation, includes: Step S41: Output the frontier solution set from the multi-objective optimization model; Step S42: The scheme of the frontier solution set is parsed into train group plan and operation diagram and arrival and departure line occupancy diagram to obtain the heavy-haul railway transportation collaborative optimization scheme.

7. A heavy-haul railway transportation optimization device, characterized in that, include: The data collection module is used to obtain the unit train access formation and access time; The model building module is used to build a multi-objective optimization model based on the unit train access formation and access time. The model solving module is used to solve the multi-objective optimization model using an improved genetic algorithm; The display module is used to output the collaborative optimization scheme for heavy-haul railway transportation obtained by the solution.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

9. An electronic device comprising a processor and a memory, characterized in that, The memory stores a computer program, and the processor executes the computer program to implement the method of any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images