Heavy haul railway train operation scheduling method and device, computer equipment and medium

Abstract

The application relates to a heavy-load railway train operation scheduling method and device, computer equipment and a medium. The method comprises the following steps: based on line information, station information and historical traffic OD information in a heavy-load railway system, a train operation scheme target function is constructed; based on historical operation frequencies of each train flow obtained from the historical traffic OD information and a preset traffic fluctuation threshold, traffic fluctuation constraints of each train flow are determined; based on the traffic fluctuation constraints of each train flow and operation capacity constraints of each train flow in the heavy-load railway system, a genetic algorithm is adopted to minimize the function value of the train operation scheme target function as the target, the train operation scheme target function is solved, and a train operation scheme of the heavy-load railway system is obtained; and based on the train operation scheme, the trains of the heavy-load railway system are operated and scheduled. The method can improve the balance between the overall carrying capacity and demand of the heavy-load railway.

Description

Technical Field

[0001] This application relates to the field of heavy-haul railway operation management technology, and in particular to a method, device, computer equipment and medium for scheduling heavy-haul railway train operations. Background Technology

[0002] Heavy-haul railways, as a crucial component of national infrastructure, play an irreplaceable role in ensuring the transportation of energy and raw materials and promoting regional economic development. Train operation plans are a core element of heavy-haul railway transportation organization, and their rationality directly impacts line capacity, transportation cost control, and service level improvement.

[0003] Currently, heavy-haul railway train operation plans are typically formulated on a fixed schedule. This fixed-cycle scheduling of heavy-haul trains can easily lead to a situation where capacity is strained during certain periods while idle capacity is available at other times, resulting in an imbalance between "over-capacity" and "under-capacity." Over-capacity increases equipment wear and energy consumption, and may even affect operational safety; under-capacity leads to wasted transportation resources and reduced transportation revenue, ultimately resulting in a poor balance between overall heavy-haul railway capacity and demand.

[0004] Therefore, how to schedule heavy-haul train operations to improve the balance between overall heavy-haul railway capacity and demand is a problem that needs to be solved. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, device, computer equipment and medium for scheduling heavy-haul railway trains to address the above-mentioned technical problems, so as to improve the balance between the overall transport capacity and demand of heavy-haul railways.

[0006] Firstly, this application provides a method for scheduling heavy-haul railway train operations, including:

[0007] Based on the line information, station information, and historical traffic flow OD information in the heavy-haul railway system, a train operation plan objective function is constructed. The train operation plan objective function includes the total train operation time and the traffic volume balance. The total operation time includes loading and assembly time, travel time, and combination and decomposition operation time. The traffic volume balance is constructed based on the deviation between the total number of train formations under the current traffic volume and the total number of train formations under the historical traffic volume.

[0008] Based on the historical train flow OD information, the historical operating frequency of each train flow is obtained, and the preset traffic volume fluctuation threshold is used to determine the traffic volume fluctuation constraint of each train flow; the historical train flow OD information includes train flow information with the same origin and destination stations.

[0009] Based on the traffic volume fluctuation constraints of each train flow and the operational capacity constraints of each train flow in the heavy-haul railway system, a genetic algorithm is used to solve the objective function of the train operation scheme with the objective of minimizing the function value of the objective function of the train operation scheme, thereby obtaining the train operation scheme of the heavy-haul railway system; wherein, the operational capacity constraints include station throughput capacity constraints, line throughput capacity constraints, combined and decomposed station operational capacity constraints, train flow balancing capacity constraints, and train formation capacity constraints;

[0010] Based on the train operation plan, the trains of the heavy-haul railway system are scheduled for operation.

[0011] In one embodiment, the train operation scheme of the heavy-haul railway system is obtained by solving the objective function of the train operation scheme using a genetic algorithm, with the objective function being to minimize the function value of the objective function of the train operation scheme, based on the traffic volume fluctuation constraints of each train flow and the operating capacity constraints of each train flow in the heavy-haul railway system. The objective function includes:

[0012] Each solution parameter in the objective function of the train operation scheme is mapped to a chromosome with gene structure in the genetic space; each chromosome corresponds to a train operation scheme.

[0013] Based on the multiple operating periods of the heavy-haul railway system, each chromosome is divided into multiple sub-chromosomes. The number of sub-chromosomes corresponding to each chromosome corresponds to the number of operating periods of the heavy-haul railway system. The gene positions of each sub-chromosome include the station identifier of the running path and the operating frequency within the corresponding operating period.

[0014] All train flows in the heavy-haul railway system are sequentially identified as target train flows, and a set of optional train flows for the target train flows is determined. The set of optional train flows includes at least one optional train flow, and each optional train flow corresponds to an optional train operation scheme.

[0015] The pre-selected train flow of the target train flow is determined from the set of optional train flows, and the remaining operational capacity of the heavy-haul railway system is updated based on the pre-selected train flow. The remaining operational capacity includes the remaining station throughput capacity, the remaining line throughput capacity, and the remaining operational capacity of the combined and decomposed stations.

[0016] Based on the remaining operational capacity and the constraints, the initial selectable train flow for the target traffic flow is determined;

[0017] Traverse and determine the initial selectable train flow corresponding to all train flows in the heavy-haul railway system;

[0018] Based on the initial selectable train flows corresponding to all train flows, crossover and mutation operations of a genetic algorithm are performed to obtain the train operation scheme of the heavy-haul railway system.

[0019] In one embodiment, the step of performing crossover and mutation operations using a genetic algorithm on the initial selectable train flows corresponding to all traffic flows to obtain the train operation scheme for the heavy-haul railway system includes:

[0020] Determine the operational capacity of each of the initial optional train flows during each of the operating periods, wherein the operational capacity includes station throughput capacity, line throughput capacity, combined and decomposed station operational capacity, and traffic volume fluctuations;

[0021] If the operational capacity exceeds the corresponding capacity constraint, a penalty value is determined based on the amount by which the operational capacity exceeds the corresponding capacity constraint.

[0022] Based on the objective function of the train operation plan and the penalty value, a fitness function is constructed;

[0023] Based on the fitness function and the initial selectable train flows corresponding to all train flows, the crossover and mutation operations of the genetic algorithm are performed to obtain the train operation scheme of the heavy-haul railway system.

[0024] In one embodiment, the step of performing crossover and mutation operations using a genetic algorithm based on the fitness function and the initial feasible column flows corresponding to all traffic flows to obtain the train operation scheme of the heavy-haul railway system includes:

[0025] The fitness of all the initial optional column streams is determined based on the fitness function;

[0026] Based on the roulette wheel strategy and all the fitness values, the parent selectable column stream of the genetic algorithm is determined from all the initial selectable column streams;

[0027] Based on the intersection of the gene segments corresponding to the parent selectable column streams in the column stream running path, the gene segments of the parent selectable column streams are exchanged to obtain the initial offspring selectable column streams;

[0028] Based on the intersection points of gene segments corresponding to the initial offspring selectable stream in multiple operating periods, the gene segments of the initial offspring selectable stream are exchanged to obtain the offspring selectable stream corresponding to the parent selectable stream;

[0029] The departure frequency of the offspring selectable train flow during the target operating period is mutated to obtain the mutated offspring selectable train flow. The genetic algorithm crossover and mutation operations are then performed on the mutated offspring selectable train flow according to the fitness function until the iteration condition is met to obtain the train operation scheme. The target operating period can be any one of the multiple operating periods, and the mutation operation includes increasing or decreasing the departure frequency.

[0030] In one embodiment, the method further includes:

[0031] The departure frequency of the current child optional queue stream during the target operating period is mutated to obtain the mutated child optional queue stream; the current child optional queue stream is any one of all child optional queue streams;

[0032] If the operational capacity of the mutated sub-generation selectable train flow exceeds the corresponding station operational capacity constraint, the other sub-generation selectable train flows passing through the station within the target operating period are mutated to obtain mutated sub-generation selectable train flows. The step of mutating the sub-generation selectable train flows is executed cyclically, and the train operation scheme of the heavy-haul railway system is obtained based on the mutated sub-generation selectable train flows that satisfy the station operational capacity constraint. The other sub-generation selectable train flows are sub-generation selectable train flows other than the current sub-generation selectable train flow. The fitness of the other sub-generation selectable train flows is lower than that of the current sub-generation selectable train flow. The operational capacity includes station throughput capacity, line throughput capacity, and operations of combined and decomposed stations.

[0033] In one embodiment, the method further includes:

[0034] Based on the fitness function, the column stream corresponding to the current train operation plan is iteratively subjected to crossover and mutation operations of a genetic algorithm until the iteration condition is met; the column stream corresponding to the current train operation plan is the column stream retained after the mutation operation of the genetic algorithm.

[0035] The column streams retained after the mutation operation when the iteration conditions are met are determined as the train operation scheme of the heavy-haul railway system.

[0036] In one embodiment, the objective function of the train operation plan is determined according to the following expression:

[0037] ;

[0038] in, Minimize the objective function of the train operation plan Indicates the loading and assembly time. This indicates that traffic flow k is at station The aggregation parameters, This indicates the column flow that the group passes through arc (i,j). Number of vehicles required The value represents whether traffic flow k passes through arc (i,j) during operating period t. If traffic flow k passes through arc (i,j) during operating period t, then... The value is 1. If traffic flow k does not pass through arc (i,j) during the operating period t, then The value is 0. Indicates travel time. Indicates the section through which traffic flow k passes ( , The runtime of ) The volume of traffic flow k within the operating period t represents the traffic volume of the vehicle flow k. Indicates the time required for combining and decomposing tasks. This indicates that traffic flow k is at station The combined decomposition station operation time. Indicates the operation period t column flow The frequency of train operations, Indicates grouped column flow Number of vehicles required This indicates the train flow of group t during the same historical operating period. Average demand reference value, The parameters represent the balance of transport volume, where K represents the set of all train flows in the heavy-haul railway system, T represents the set of all operating time periods in the heavy-haul railway system, A represents the set of arcs corresponding to all sections in the heavy-haul railway system, and L represents the set of optional train flows generated by the OD of the train flows.

[0039] Secondly, this application also provides a heavy-haul railway train operation scheduling device, comprising:

[0040] The objective function construction module is used to construct an objective function for train operation schemes based on line information, station information, and historical traffic flow OD information in the heavy-haul railway system. The objective function for train operation schemes includes the total train operation time and the transport volume balance. The total operation time includes loading and assembly time, travel time, and combination and decomposition operation time. The transport volume balance is constructed based on the deviation between the total number of train formations in the current transport volume and the total number of train formations in the historical transport volume of the heavy-haul railway system.

[0041] The constraint determination module is used to determine the traffic volume fluctuation constraints of each train flow based on the historical departure frequency of each train flow obtained from the historical traffic flow OD information and a preset traffic volume fluctuation threshold; the historical traffic flow OD information includes multiple train flows with the same origin and destination stations.

[0042] The solution module is used to solve the train operation scheme objective function based on the traffic fluctuation constraints of each train flow and the operational capacity constraints of each train flow in the heavy-haul railway system. The objective function is to minimize the function value of the train operation scheme objective function, thereby obtaining the train operation scheme of the heavy-haul railway system. The operational capacity constraints include station throughput constraints, line throughput constraints, combined decomposition station operation capacity constraints, train flow balancing capacity constraints, and train formation capacity constraints.

[0043] The operation scheduling module is used to schedule the operation of trains in the heavy-haul railway system based on the train operation plan.

[0044] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in any of the above embodiments.

[0045] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in any of the above embodiments.

[0046] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps in any of the above embodiments.

[0047] In the above implementation process, the total train operation time is constructed based on the line information, station information, and historical traffic flow OD information of the heavy-haul railway system. The capacity balance is constructed based on the deviation between the total number of train formations under the current capacity and the total number of train formations under the historical capacity. The objective function of the train operation plan is constructed based on the total train operation time and the capacity balance. Thus, the constructed objective function of the train operation plan considers not only the operation time but also the capacity balance of the heavy-haul railway system. Furthermore, based on the historical train flow OD information, the historical operating frequency of each train flow and the preset capacity fluctuation threshold are determined, and the capacity fluctuation constraints of each train flow are determined. This facilitates the solution of the objective function of the train operation plan based on the capacity fluctuation constraints and the operating capacity constraints. In the solution process, a genetic algorithm is used to minimize the objective function of the train operation plan. Under the joint constraints of operating capacity and capacity fluctuation, the train operation plan is obtained, so that the final train operation plan satisfies the minimum running time and the most balanced capacity. Finally, the trains in the heavy-haul railway system are scheduled according to the determined train operation plan, so that the overall running time of the trains in the heavy-haul railway system is minimized and the balance of capacity in the heavy-haul railway system is improved. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a schematic diagram illustrating the application environment of a train operation plan preparation method provided in an embodiment of this application;

[0050] Figure 2 This is a flowchart illustrating a train operation plan preparation method provided in an embodiment of this application;

[0051] Figure 3 This is a schematic diagram of a transportation service network provided in an embodiment of this application;

[0052] Figure 4 This is a schematic diagram of the running route corresponding to a direct train operation scheme provided in an embodiment of this application;

[0053] Figure 5 This is a schematic diagram of the operating path corresponding to a direct train operation scheme provided in this application embodiment;

[0054] Figure 6 This is a schematic diagram of the running path corresponding to a non-direct train operation scheme provided in an embodiment of this application;

[0055] Figure 7 This is a schematic diagram of a sub-chromosome structure provided in an embodiment of this application;

[0056] Figure 8 This is a schematic diagram of a single-point intersection of a parent selectable column stream provided in an embodiment of this application;

[0057] Figure 9 This is a schematic diagram of a mutation operation provided in an embodiment of this application;

[0058] Figure 10 This is a schematic diagram of the structure of a heavy-haul railway train operation scheduling device provided in an embodiment of this application;

[0059] Figure 11 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0062] The train operation plan compilation method provided in this application embodiment can be applied to, for example, Figure 1 The application environment shown. Figure 1 This is a schematic diagram illustrating the application environment of a train operation plan compilation method provided in this application embodiment, such as... Figure 1 As shown, terminal 102 communicates with server 104 via a network. The data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, and IoT devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart vehicle devices, projection devices, etc. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0063] In one exemplary embodiment, Figure 2 This is a flowchart illustrating a train operation plan formulation method provided in an embodiment of this application, which is applied to... Figure 1 Taking server 104 as an example, this server 104 can be set up in a heavy-haul railway system, such as... Figure 2 As shown, the method may include the following steps:

[0064] Step 201: Based on the line information, station information, and historical traffic flow OD information in the heavy-haul railway system, construct the objective function of the train operation plan.

[0065] The objective function of the train operation plan includes the total train operation time and the load balance. The total operation time includes loading and assembly time, travel time, and combination and decomposition operation time. The load balance is constructed based on the deviation between the total number of train formations under the current load and the total number of train formations under the historical load of the heavy-haul railway system.

[0066] For example, historical train flow origin-destination (OD) information from line information, station information, and historical operating data in a heavy-haul railway system can be obtained. This historical OD information may include train flow information from multiple trains with the same origin and destination stations. Further, the obtained historical OD information is divided into multiple operating periods, and the train flow data for each operating period is analyzed to obtain the average number of train formations for each train flow in each operating period under historical traffic volume. The total number of train formations for all operating periods under historical traffic volume is then determined based on this average. Finally, the traffic volume balance is determined based on the deviation between the total number of train formations for each train flow in all operating periods under the current traffic volume of the heavy-haul railway system and the total number of train formations for all operating periods.

[0067] Furthermore, an objective function for the train operation plan is constructed based on the freight volume balance and the total train operation time in the heavy-haul railway system. As an example, the total train operation time can be calculated based on the loading and assembly time, travel time, and combined operation time constructed from the train operation plan.

[0068] In order to facilitate the parameterization of train operation schemes within the heavy-haul railway system, a transportation service network can be constructed based on the stations within the heavy-haul railway system and the train's operating path between stations.

[0069] Specifically, the physical network within a heavy-haul railway system includes stations and the train's operating paths between stations. To facilitate train operation planning, the physical network can be abstracted into a corresponding transportation service network. Specifically, stations in the physical network can be abstracted as service nodes, and the operating paths between stations can be abstracted as corresponding arcs.

[0070] As an example, the physical network within a heavy-haul railway system can include different types of stations, which can be represented by service nodes with different numbers in the transport service network. The running paths between different stations can be represented by different arcs. If the physical network within the heavy-haul railway system is... Let V be the set of stations in the physical network, with indices v; and E be the set of lines in the physical network, with indices (u, v). Correspondingly, this represents the transportation service network. In N, each element i represents a service node, and a location mapping function is defined. Associating service node i with a site in the physical network Let A be the set of arcs in the physical network. Figure 3 This is a schematic diagram of a transportation service network provided in an embodiment of this application, such as... Figure 3 As shown, the station types in the physical network of a heavy-haul railway system can include loading stations, combining stations, splitting stations, and unloading stations, which correspond to nodes numbered 1, 2, 3, and 4 respectively in the transport service network. Furthermore, the train running paths constitute an arc set, including originating and terminating arcs, running arcs, and transfer arcs. Originating and terminating arcs connect loading / unloading stations with train running path nodes, indicating that the train flow originates from the loading station or terminates at the unloading station; running arcs connect the running path nodes of each train within the same train flow, indicating that the train flow travels from one station to the next without combining or splitting operations along the way, corresponding to physical sections (…). , The section operation process; the transfer arc connects different train operation route nodes within the same station, indicating that a train flow merges into another train flow at that station (combined operation) or is separated from a train flow at that station (decomposed operation), corresponding to the physical station. The internal combination and decomposition process.

[0071] Once the transportation service network is constructed, each train operation plan in the heavy-haul railway system can be represented by the operating path within that network. For example, if the train flow originates from station 1 (loading station) to station 4 (unloading station), the operation plan can include three types: direct from loading point, direct via technical route, and indirect route. Figure 4 This is a schematic diagram of the running route corresponding to a direct train operation scheme provided in an embodiment of this application, such as... Figure 4 As shown, train flow 1 transports goods via stations <1, 2, 3, 4> through a direct route from the loading point; Figure 5 This is a schematic diagram of the operating path corresponding to a direct train operation scheme provided in this application embodiment, such as... Figure 5 As shown, train flow 3 passes through stations <1, 2> via a non-direct route, and is transferred at station 2 to form train flow 2. Then, it is transported via stations <2, 3, 4> via a direct route. Figure 6 This is a schematic diagram of the operating path corresponding to a non-direct train operation scheme provided in an embodiment of this application, such as... Figure 6 As shown, train flow 3 passes through stations <1, 2> via a non-direct route, and transfers at station 2 to form train flow 4. Then it passes through stations <2, 3> via a non-direct route, and transfers at station 3 to form train flow 5. Finally, it passes through stations <3, 4> via a non-direct route for transportation.

[0072] Furthermore, the total train operation time can be constructed based on the transportation service network, and the capacity balance can be constructed based on the deviation between the total number of train formations under the current capacity and the total number of train formations under historical capacity. The objective function of the train operation plan can then be obtained based on the total operation time and the capacity balance.

[0073] Specifically, the total time consumed by trains in a heavy-haul railway system can include the train loading and assembly time T1, the travel time T2, and the assembly and disassembly operation time T3.

[0074] As an example, the loading and assembly time can be determined based on the assembly parameters and the average number of cars required for marshalling flows within the heavy-haul railway system. The travel time can be determined based on the travel time of trains on each line within the heavy-haul railway system and the total number of trains. The combination and decomposition operation time can be determined based on the combination and decomposition time of trains at each station within the heavy-haul railway system and the total number of trains.

[0075] Furthermore, based on the deviation between the total number of train formations under the current traffic volume and the total number of train formations under historical traffic volumes, a traffic volume balance is constructed. And based on the loading and assembly time T1, travel time T2, assembly and disassembly operation time T3, and the balance of transport volume. Construct the objective function of the train operation plan The objective function of the train operation plan can be represented by the following expression. :

[0076] ;

[0077] Step 202: Based on the historical departure frequency of each train flow obtained from the historical traffic flow OD information and the preset traffic volume fluctuation threshold, determine the traffic volume fluctuation constraint for each train flow.

[0078] Historical train flow OD information includes train flow information from multiple stations with the same origin and destination.

[0079] For example, the historical operating frequency of each train flow is obtained from the historical OD information of the heavy-haul railway system. Specifically, the average starting frequency of all train flows in the historical OD information can be determined as the historical starting frequency of each train flow. .

[0080] Furthermore, based on historical operating frequencies and preset passenger volume fluctuation thresholds... This determines the capacity fluctuation range of each flow, thus obtaining the capacity fluctuation constraints for each flow. As an example, the range corresponding to the capacity fluctuation constraints for each flow is: [(1- ) , (1+ ) ].

[0081] Step 203: Based on the traffic volume fluctuation constraints of each train flow and the operating capacity constraints of each train flow in the heavy-haul railway system, a genetic algorithm is used to solve the objective function of the train operation scheme with the goal of minimizing the function value of the objective function of the train operation scheme, so as to obtain the train operation scheme of the heavy-haul railway system.

[0082] Among them, the operational capacity constraints of heavy-haul railway systems include station throughput capacity constraints, line throughput capacity constraints, combined and decomposed station operational capacity constraints, train flow balancing capacity constraints, and train formation capacity constraints.

[0083] For example, the station throughput capacity constraints, line throughput capacity constraints, combined station operation capacity constraints, train flow balancing capacity constraints, and train formation capacity constraints within a heavy-haul railway system are collectively defined as operational capacity constraints. Furthermore, constraint conditions are determined based on these operational capacity constraints and traffic volume fluctuation constraints.

[0084] As another example, constraints can also be determined based on operational capacity constraints, traffic volume fluctuation constraints, and the value constraints of each decision variable.

[0085] Specifically, the station throughput capacity constraint is: the throughput capacity of station v should be greater than or equal to the total number of trains passing through station v. The line throughput capacity constraint is: the throughput capacity of physical segment e should be greater than or equal to the total number of trains passing through physical segment e. The combined / disassembled station operation capacity constraint is: the operation capacity of the combined / disassembled station should be greater than or equal to the total number of trains performing combined operations at that combined / disassembled station. The train flow balancing capacity constraint is: for each station on the line, if the station is a loading station, then the station only dispatches train flow, and the number of train flow is equal to the total number of train flow dispatched to each unloading station; if the station is an unloading station, then the station only receives train flow, and the number of train flow is equal to the total number of train flow dispatched by each loading station; if the station is an intermediate station, the number of train flow dispatched by the station is equal to the number of train flow received. The train formation capacity constraint is: the number of cars in each train formation is less than or equal to the maximum number of cars in a formation.

[0086] Furthermore, based on the constraints of the transport volume fluctuations and the operating capacity of each train flow in the heavy-haul railway system, a genetic algorithm is used to solve the objective function of the train operation scheme with the goal of minimizing the function value of the objective function of the train operation scheme, thereby obtaining the train operation scheme of the heavy-haul railway system.

[0087] Step 204: Based on the train operation plan, schedule the operation of trains in the heavy-haul railway system.

[0088] Furthermore, based on the determined train operation plan, the trains of the heavy-haul railway system are scheduled for operation, thereby enabling the trains of the heavy-haul railway system to operate according to the determined train operation plan.

[0089] In the above implementation process, the total train operation time is constructed based on the line information, station information, and historical traffic flow OD information of the heavy-haul railway system. The capacity balance is constructed based on the deviation between the total number of train formations under the current capacity and the total number of train formations under the historical capacity. The objective function of the train operation plan is constructed based on the total train operation time and the capacity balance. Thus, the constructed objective function of the train operation plan considers not only the operation time but also the capacity balance of the heavy-haul railway system. Furthermore, based on the historical train flow OD information, the historical operating frequency of each train flow and the preset capacity fluctuation threshold are determined, and the capacity fluctuation constraints of each train flow are determined. This facilitates the solution of the objective function of the train operation plan based on the capacity fluctuation constraints and the operating capacity constraints. In the solution process, a genetic algorithm is used to minimize the objective function of the train operation plan. Under the joint constraints of operating capacity and capacity fluctuation, the train operation plan is obtained, so that the overall train operation plan satisfies the minimum running time and the most balanced capacity. Finally, the trains in the heavy-haul railway system are scheduled according to the determined train operation plan, so that the overall running time of the trains in the heavy-haul railway system is minimized and the balance of capacity in the heavy-haul railway system is improved.

[0090] In one embodiment, based on the traffic volume fluctuation constraints of each train flow and the operational capacity constraints of each train flow in the heavy-haul railway system, a genetic algorithm is used to solve the objective function of the train operation scheme with the objective of minimizing the function value of the objective function of the train operation scheme, thereby obtaining the train operation scheme of the heavy-haul railway system. This may include the following steps:

[0091] Step 1: Map each solution parameter in the objective function of the train operation plan to chromosomes with gene structure in the genetic space.

[0092] Each chromosome corresponds to a train operation plan.

[0093] Step 2: Based on the multiple operating periods of the heavy-haul railway system, each chromosome is divided into multiple sub-chromosomes, and the number of sub-chromosomes corresponding to each chromosome corresponds to the number of operating periods of the heavy-haul railway system.

[0094] Each subchromosome's gene locus includes the station identifier of the operating path and the frequency of operation within the corresponding operating period.

[0095] Step 3: Sequentially determine all train flows in the heavy-haul railway system as target train flows, and determine the set of optional train flows for the target train flows. The set of optional train flows includes at least one optional train flow, and each optional train flow corresponds to an optional train operation scheme.

[0096] Step 4: Determine the pre-selected train flow for the target train flow from the set of available train flows, and update the remaining operational capacity of the heavy-haul railway system based on the pre-selected train flow.

[0097] Remaining operational capacity includes remaining station throughput capacity, remaining track throughput capacity, and remaining combined and split-type station operational capacity.

[0098] Step 5: Based on the remaining operational capacity and constraints, determine the initial selectable train flow for the target traffic flow.

[0099] Step 6: Traverse and determine the initial selectable train flows corresponding to all train flows in the heavy-haul railway system.

[0100] Step 7: Perform crossover and mutation operations using a genetic algorithm based on the initial selectable train flows corresponding to all train flows to obtain the train operation scheme for the heavy-haul railway system.

[0101] For example, in the process of solving the objective function of train operation schemes using a genetic algorithm, the solution parameters in the objective function can be mapped to chromosomes with gene structures in the genetic space through encoding. Each chromosome corresponds to a train operation scheme.

[0102] Furthermore, each chromosome is divided into multiple sub-chromosomes based on the multiple operating periods of the heavy-haul railway system, with the number of sub-chromosomes corresponding to the number of operating periods of the heavy-haul railway system. The gene positions of each sub-chromosome include the station identifier and train frequency within the corresponding operating period.

[0103] Specifically, the solution parameters in the objective function of the train operation plan can be encoded as chromosomes of a two-dimensional spatiotemporal matrix. Further, if the heavy-haul railway system includes T operating periods, then each chromosome is divided into T sub-segments, corresponding to T chromosomes. Within each sub-chromosome, the gene positions record the station identifier i traversed by the train flow and the operating frequency of the following flows at each station during that operating period. .

[0104] Figure 7 This is a schematic diagram of a sub-chromosome structure provided in an embodiment of this application, as shown in... Figure 7 The encoding structure shown allows station i to be mapped using the mapping operator. The algorithm points to the corresponding physical station v in real time, so that each mutation in the genetic algorithm can directly correspond to the change in occupancy in the physical layer network.

[0105] Furthermore, to facilitate the construction of the initial feasible solution for the genetic algorithm, all train flows in the heavy-haul railway system can be sequentially identified as the target train flows, and a set of all possible train flows for the target train flows can be determined. Each set of possible train flows includes at least one possible train flow, and each possible train flow corresponds to a possible train operation scheme. Any possible train flow in the set of possible train flows is then identified as a pre-selected train flow for the target train flow, marked as an occupied train flow path, and the remaining operational capacity of the heavy-haul railway system after the pre-selected train flow is occupied is calculated. Specifically, this remaining operational capacity can include parameters such as the remaining station throughput capacity, the remaining line throughput capacity, and the remaining operational capacity of the combined decomposition stations.

[0106] Furthermore, the remaining station throughput capacity is compared with the station throughput capacity, the remaining line throughput capacity is compared with the line throughput capacity, and the remaining combined decomposition station's operational capacity is compared with the combined decomposition station's operational capacity. If any remaining operational capacity exceeds the corresponding capacity constraint, a new train flow is selected as the initial optional train flow for the target train flow from the optional train flows with surplus capacity.

[0107] Furthermore, all train flows are traversed, and steps 3 to 5 above are performed on each train flow to obtain the initial selectable train flow for each train flow. That is, all train flows have an initial operating plan that meets the operational capacity of the heavy-haul railway, thus obtaining the initial feasible solution for the genetic algorithm. Finally, based on the initial selectable train flows corresponding to all train flows, crossover and mutation operations of the genetic algorithm are performed to obtain the train operation plan for the heavy-haul railway system.

[0108] In the above implementation process, the objective function of the train operation plan is mapped to the running path and operation frequency of each train flow in different time periods. A pre-verification mechanism of remaining operational capacity is introduced when the initial population is generated to prioritize the retention of train operation plans that meet the station's capacity, thereby ensuring that the logical train flow operation does not exceed the station's throughput capacity, remaining throughput capacity, and the operational capacity of the combined decomposition station.

[0109] In one embodiment, the train operation scheme of the heavy-haul railway system is obtained by performing crossover and mutation operations of a genetic algorithm based on the initial selectable train flows corresponding to all traffic flows, which may include the following steps:

[0110] Step 1: Determine the operational capacity of each initial optional train flow during each operating period. Operational capacity includes station throughput capacity, line throughput capacity, combined and decomposed station operational capacity, and traffic volume fluctuations.

[0111] Step 2: If the operational capacity exceeds the corresponding capacity constraint, determine the penalty value based on the amount by which the operational capacity exceeds the corresponding capacity constraint.

[0112] Step 3: Construct a fitness function based on the objective function of the train operation plan and the penalty value.

[0113] Step 4: Based on the fitness function and the initial selectable train flow corresponding to all train flows, perform crossover and mutation operations of the genetic algorithm to obtain the train operation scheme of the heavy-haul railway system.

[0114] For example, in order to ensure that the total time consumed by train operation and the deviation of traffic balance are minimized, and in the process of solving the objective function of train operation plan, infeasible solutions may be generated after iteration due to constraints such as station capacity, line capacity, combined decomposition station operation capacity, and traffic fluctuation, a fitness function containing the objective function and constraints can be set by introducing a penalty factor.

[0115] Specifically, the objective function for train operation can be used to determine whether the station throughput capacity, line throughput capacity, combined decomposition station operation capacity, and traffic volume fluctuations of each initial optional train flow exceed the corresponding capacity constraints during each operating period. For example, it can be determined whether the station throughput capacity, line throughput capacity, combined decomposition station operation capacity, and traffic volume fluctuations of each initial optional train flow exceed the station throughput capacity constraints, line throughput capacity, combined decomposition station operation capacity constraints, and traffic volume fluctuation constraints during each operating period. If any operational capacity exceeds the corresponding capacity constraint, the excess amount of all operational capacities will be determined, and the excess amount will be set as a penalty value.

[0116] As an example, if multiple operational capabilities exceed their corresponding capability constraints, the sum of all excesses can be used as the penalty value, or the average of all excesses can be used as the penalty value.

[0117] Furthermore, based on the objective function of the train operation plan and the penalty value, a fitness function is constructed. As an example, the fitness function can be determined by the following expression:

[0118] ;

[0119] Where Fitness is the fitness level and Penalty is the penalty value.

[0120] Furthermore, the fitness function is used to perform crossover and mutation operations on the initial selectable train flows corresponding to all train flows using a genetic algorithm, thereby obtaining the train operation scheme for the heavy-haul railway system.

[0121] In the aforementioned implementation process, during the solution of the objective function for train operation plans using a genetic algorithm, a penalty factor is introduced through the fitness function to penalize operation plans that violate operational capacity constraints, thereby guiding the population to evolve in a direction that "both satisfies physical limits and smoothly adapts to fluctuations." Ultimately, the algorithm outputs an optimal dynamic operation plan that minimizes total time consumption and smooths traffic fluctuations. By using this determined operation plan to schedule trains in the heavy-haul railway system, the balance between capacity and demand is effectively improved while ensuring minimal total time consumption.

[0122] In one embodiment, a genetic algorithm is used to perform crossover and mutation operations based on the fitness function and the initial feasible column flow corresponding to all traffic flows to obtain a train operation scheme for the heavy-haul railway system. This may include the following steps:

[0123] Step 1: Determine the fitness of all initial optional column streams based on the fitness function.

[0124] Step 2: Based on the roulette wheel strategy and all fitnesss, determine the parent selectable column flow of the genetic algorithm from all initial selectable column flows.

[0125] Step 3: Based on the intersection of the gene segments corresponding to the parent optional column streams in the column stream running path, the gene segments of the parent optional column streams are exchanged to obtain the initial offspring optional column streams.

[0126] Step 4: Based on the intersection of gene segments corresponding to the initial offspring optional stream in multiple operating periods, exchange gene segments of the initial offspring optional stream to obtain the offspring optional stream corresponding to the parent optional stream.

[0127] Step 5: Perform a mutation operation on the departure frequency of the child selectable train flow during the target operating period to obtain the mutated child selectable train flow. Then, repeatedly perform crossover and mutation operations on the mutated child selectable train flow according to the fitness function until the iteration conditions are met to obtain the train operation plan.

[0128] The target operating period can be any one of multiple operating periods, and the variation operations include increasing or decreasing the frequency of train departures.

[0129] For example, during the crossover and mutation operations of the genetic algorithm on all initial optional column streams using the fitness function, the fitness of each initial optional column stream can be determined based on the fitness function. Furthermore, a roulette wheel selection strategy is used as the selection operator to determine the parent optional column streams of the genetic algorithm.

[0130] As an example, the roulette strategy specifically employs the following operations:

[0131] The fitness value of each initial selectable stream in all initial selectable streams is calculated based on the fitness function. ;in, Indicates the initial optional column stream.

[0132] Calculate the probability that each of the initial optional column streams will be inherited by the next generation. :

[0133] ;

[0134] Determine the cumulative probability of each initial optional column stream in all initial optional column streams. Perform the calculation:

[0135] ;

[0136] Generate a uniformly distributed random number r in the interval [0, 1]; if r < If the initial optional column stream i is selected, then the initial optional column stream k is selected; otherwise, the initial optional column stream k is selected, requiring that the following conditions are met: The process of generating random numbers and determining initial optional column streams is repeated until M initial optional column streams are generated. These M initial optional column streams are then designated as parent optional column streams. This method allows for the selection of superior individuals from all initial optional column streams as "parents". If r ≥ Then, a mutation operation is performed on the initial selectable column stream i.

[0137] Furthermore, crossover and mutation are performed on the selected parental candidate streams. Specifically, in the genetic algorithm, the crossover operator generates new individuals by exchanging partial gene segments between two paired chromosomes through a single-point crossover, thus forming two new chromosomes.

[0138] As an example, the parent optional column streams are paired up, and the gene segments of the paired parent optional column streams are exchanged according to the intersection of the gene segments corresponding to the column stream running path, to obtain the initial offspring optional column stream.

[0139] Specifically, two paired parental selectable streams are selected from the parental selectable streams. To ensure the uniqueness of the selection of a stream by a vehicle stream, the crossover point can be chosen as the boundary point of the gene segments along the stream's path. The gene segments of the corresponding chromosomes of the two parental selectable streams are exchanged to the right of the crossover point, generating two new offspring chromosomes, which are the initial offspring selectable streams. After single-point crossover, the chromosomes corresponding to the initial offspring selectable streams are checked. If the same node appears repeatedly, the redundant node is deleted to ensure that there are no duplicate genes in the chromosomes corresponding to the initial offspring selectable streams.

[0140] Figure 8 This is a schematic diagram illustrating a single-point intersection of a parent selectable column stream, as provided in an embodiment of this application. Figure 8As shown, the intersection of gene segments in the running path is randomly selected in two paired parent selectable streams, and the right-hand part is swapped at the selected position to obtain two different initial offspring selectable streams.

[0141] Furthermore, temporal segment crossover is performed on all determined initial child optional streams. Specifically, since the opening scheme in this embodiment is divided into multiple operating periods, two initial child optional streams are randomly selected. Then, the crossover points of the gene segments corresponding to the two selected initial child optional streams in multiple operating periods are randomly determined, and the gene segments after the crossover point are exchanged. That is, a split point t is randomly selected in the T periods of the initial child optional streams, and all opening sequences at t+1 and thereafter are exchanged, thereby obtaining the child optional streams corresponding to the parent optional streams. This makes the algorithm more convergent and stable when dealing with traffic fluctuations over a longer period.

[0142] Furthermore, through single-point crossover and time-domain segment crossover, all progeny selectable streams are determined, and mutation operations are performed on all progeny selectable streams. Specifically, gene segments in the progeny selectable streams can be randomly selected for mutation operations. As an example, the mutation operation can specifically employ the following steps:

[0143] Generate a uniformly distributed random number in the interval [0, 1]. ;like If so, select one gene from the chromosome corresponding to the selectable stream of the offspring, and change the gene code of that gene segment to form the chromosome corresponding to the selectable stream of the mutated offspring; if so, changing the gene code of the gene segment can be by increasing or decreasing the opening frequency. Figure 9 This is a schematic diagram of a mutation operation provided in an embodiment of this application, such as... Figure 9 As shown, the gene code with a mutation frequency of 7 is changed to a mutation frequency of 6.

[0144] Furthermore, the chromosomes corresponding to the mutated offspring selectable streams are checked. If the constraints are not met, the chromosomes corresponding to the unmutated offspring selectable streams are retained. If the chromosomes corresponding to the mutated offspring selectable streams meet the constraints, the mutated offspring selectable streams are retained, and the genetic algorithm's crossover and mutation operations are repeatedly performed on the retained mutated offspring selectable streams according to the fitness function. The mutated offspring selectable streams retained when the iteration count meets the iteration condition are determined as the train operation scheme for the heavy-haul railway system. Then, the genetic algorithm performs crossover and mutation operations on the parent selectable column stream according to the fitness function, and the mutated offspring selectable column stream retained when the iteration condition is met is determined as the train operation scheme of the heavy-haul railway system.

[0145] In the above implementation process, the fitness of all initial optional train flows is determined according to the fitness function. The optional train flows are then evaluated based on their fitness; higher fitness indicates a better optional train flow and a greater probability of being retained. Then, using a roulette wheel strategy and the parent optional train flows of all fitness-based genetic algorithms, the optional train flows with high fitness are identified as parent optional train flows. Further, crossover and mutation are performed on these high-fitness optional train flows to ensure that the best solution is not lost during crossover and mutation, thus improving the balance between capacity and demand in the heavy-haul railway system.

[0146] In one embodiment, the method further includes the following steps:

[0147] Step 1: Perform a mutation operation on the departure frequency of the current child optional stream during the target operating period to obtain the mutated child optional stream. The current child optional stream is any one of the child optional streams.

[0148] Step 2: If the operational capacity of the mutated sub-generation selectable train flow exceeds the corresponding station operational capacity constraint, perform mutation operations on other sub-generation selectable train flows passing through stations within the target operating period to obtain mutated sub-generation selectable train flows. Repeat the step of performing mutation operations on sub-generation selectable train flows, and obtain the train operation plan of the heavy-haul railway system based on the mutated sub-generation selectable train flows that meet the station operational capacity constraints.

[0149] Other child optional train flows are child optional train flows other than the current child optional train flow. The fitness of other child optional train flows is lower than that of the current child optional train flow. Operational capabilities include station throughput capacity, line throughput capacity, and operations of combined and decomposed stations.

[0150] For example, during the mutation operation of the optional train flow, firstly, a child optional train flow l of a certain operating period t is randomly selected. The operating period t is the target operating period, and the child optional train flow l is the current child optional train flow. The frequency of its operation is appropriately increased or decreased. Secondly, it is checked whether the change causes the operation capacity of the traversed station v and physical segment E to exceed the corresponding station operation capacity constraint. The operation capacity includes station throughput capacity, line throughput capacity, and operation of combined decomposition stations.

[0151] If the operational capacity constraint is exceeded, then find the suboptimal alternative train flow l' that also passes through station v and physical segment E during the same operating period. Increase or decrease its operating frequency and repeatedly check whether the change causes the passing station v and physical segment E to exceed the operational capacity constraint. If the operational capacity constraint is met, the mutation is retained. If the operational capacity constraint is not met, other alternative train flows are selected again for mutation operation until the operational capacity of the mutated alternative train flow does not exceed the corresponding station operational capacity constraint.

[0152] Furthermore, the mutated offspring train flow that does not exceed the corresponding station operation capacity constraint can be retained, and then the retained mutated offspring train flow can be determined as the train operation scheme for the heavy-haul railway system. Alternatively, the genetic algorithm can be iteratively executed on the retained mutated offspring train flow using a fitness function, performing crossover and mutation operations until the number of iterations reaches the iteration threshold.

[0153] Specifically, the fitness of the suboptimal column stream l' is lower than that of the column stream l. That is, the order of column stream selection is based on the fitness of the column streams from high to low.

[0154] In the above implementation process, the mutation operation is improved. After the optional column flow is mutated, the operation capacity of the mutated offspring optional column flow is compared with the corresponding station operation capacity constraint. If the operation capacity exceeds the corresponding station operation capacity constraint, the optional column flow with the second best fitness is selected for mutation operation. Finally, the offspring optional column flow that meets the operation capacity constraint is retained. This effectively avoids the loss of the best individual in the current population in the next generation, which would prevent the genetic algorithm from converging to the optimal. This application adopts an elite retention strategy, which retains the best individual that appears during the population iteration process to avoid destroying the best individual.

[0155] In one embodiment, the method may further include the following steps:

[0156] Step 1: Based on the fitness function, iteratively perform crossover and mutation operations of the genetic algorithm on the column flow corresponding to the current train operation plan until the iteration conditions are met.

[0157] The current train operation plan corresponds to the column flow that is retained after the mutation operation of the genetic algorithm.

[0158] Step 2: The column streams retained after the mutation operation when the iteration conditions are met are determined as the train operation scheme for the heavy-haul railway system.

[0159] For example, during the crossover and mutation operations of the initial selectable train flows corresponding to all train flows based on the fitness function using a genetic algorithm, the retained mutated offspring selectable train flows are determined as the train flows corresponding to the current train operation scheme. Further, the crossover and mutation operations of the mutated offspring selectable train flows based on the fitness function are iteratively performed until the iteration condition is met. Specifically, the iteration condition can be that the number of iterations reaches an iteration threshold, or that the difference in fitness among all mutated offspring selectable train flows is less than a preset fitness threshold. The mutated offspring selectable train flows that meet the iteration condition are then determined as the train operation scheme for the heavy-haul railway system.

[0160] In the above implementation process, crossover mutation operation is performed iteratively on the retained column stream after mutation according to the fitness function until the iteration condition of the number of iterations is met, or the iteration condition that the difference between the fitness values ​​of all mutated offspring selectable column streams is less than the preset fitness threshold is met. Finally, the mutated offspring selectable column streams that meet the iteration conditions are determined as the train operation scheme of the heavy-haul railway system, effectively ensuring the convergence of the genetic algorithm and obtaining the train operation scheme of the heavy-haul railway system.

[0161] In one embodiment, the objective function for the train operation plan is determined according to the following expression:

[0162] ;

[0163] in, Minimize the objective function of the train operation plan Indicates the loading and assembly time. This indicates that traffic flow k is at station The aggregation parameters, This indicates the column flow that the group passes through arc (i,j). Number of vehicles required The value represents whether traffic flow k passes through arc (i,j) during operating period t. If traffic flow k passes through arc (i,j) during operating period t, then... The value is 1. If traffic flow k does not pass through arc (i,j) during the operating period t, then The value is 0. Indicates travel time. Indicates the section through which traffic flow k passes ( , The runtime of ) The volume of traffic flow k within the operating period t represents the traffic volume of the vehicle flow k. Indicates the time required for combining and decomposing tasks. This indicates that traffic flow k is at station The combined decomposition station operation time. Indicates the operation period t column flow The frequency of train operations, Indicates grouped column flow Number of vehicles required This indicates the train flow of group t during the same historical operating period. Average demand reference value, The parameters represent the balance of traffic volume, where K represents the set of all train flows in the heavy-haul railway system, T represents the set of all operating time periods in the heavy-haul railway system, A represents the set of arcs corresponding to all sections in the heavy-haul railway system, and L represents the set of optional train flows generated by the OD of the train flows.

[0164] Specifically, the loading and assembly time is determined by multiplying the assembly parameters by the average number of cars required for marshalling flows within the heavy-haul railway system. The loading and assembly time T1 can be characterized by the following expression:

[0165] ;

[0166] in, This indicates that traffic flow k is at station The aggregation parameters; This indicates the column flow that the group passes through arc (i,j). Number of vehicles required; The value represents whether traffic flow k passes through arc (i,j) during operating period t. If traffic flow k passes through arc (i,j) during operating period t, then... The value is 1. If traffic flow k does not pass through arc (i,j) during the operating period t, then The value is 0; Indicates grouped column flow The required average number of vehicles; K represents the set of all traffic flows within the heavy-haul railway system; T represents the set of all operating time periods within the heavy-haul railway system; A represents the set of arcs corresponding to all sections within the heavy-haul railway system.

[0167] Specifically, the travel time can be determined by multiplying the travel time of traffic on each route by the total number of traffic lines. The travel time T2 can be represented by the following expression:

[0168] ;

[0169] in, Indicates the section through which traffic flow k passes ( , The runtime of ) Characterizes the traffic volume of vehicle flow k within the operating period t; This indicates the total number of vehicles.

[0170] Specifically, the combination and decomposition operation time can be determined by multiplying the combination and decomposition time of traffic flow at each station by the total number of traffic flows. The combination and decomposition operation time T3 can be represented by the following expression:

[0171] ;

[0172] in, This indicates that traffic flow k is at station The combined decomposition station operation time.

[0173] Furthermore, a capacity balance can be constructed based on the deviation between the total number of train formations in the current heavy-haul railway system and the total number of train formations in historical transport volumes. :

[0174] ;

[0175] in, Indicates the operation period t column flow The frequency of train operations, Indicates grouped column flow Number of vehicles required This indicates the train flow of group t during the same historical operating period. Average demand reference value, This represents the parameter indicating the balance of transport volume.

[0176] Furthermore, based on the expression of the objective function of the train operation plan, the corresponding constraints may include station throughput capacity constraints, line throughput capacity constraints, combined decomposition station operation capacity constraints, train flow balancing capacity constraints, train formation capacity constraints, traffic volume fluctuation constraints, and value constraints for each decision variable.

[0177] Specifically, the station throughput constraint is that the throughput capacity of station v should be greater than or equal to the total number of trains passing through that station, and its expression is:

[0178] ;

[0179] in, This represents a 0-1 parameter; if train flow l passes through station v, it takes the value 1; otherwise, it takes the value 0. v This indicates the throughput capacity of station v, measured in columns.

[0180] The line capacity constraint is that the capacity of physical section e should be greater than or equal to the total number of trains passing through that line, and its expression is:

[0181] ;

[0182] in, This represents a 0-1 parameter; it is set to 1 if the path of column flow l contains physical segment e, and 0 otherwise. This indicates the passability of physical segment e.

[0183] The operational capacity constraint of a combination and breakdown station is that the station's operational capacity should be greater than or equal to the total number of trains performing combination operations at that station, expressed as:

[0184] ;

[0185] in, This represents a 0-1 parameter; if train flow l undergoes combination and decomposition operations at station v, it is set to 1; otherwise, it is set to 0. This indicates the operational capacity of the combination and decomposition station v, in columns.

[0186] Train flow balancing constraint: For each station on the line, if the station is a loading station, it only dispatches trains, and the number of trains dispatched to each unloading station is equal to the total number of trains dispatched to each unloading station; if the station is an unloading station, it only receives trains, and the number of trains received is equal to the total number of trains dispatched by each loading station; if the station is an intermediate station, the number of trains dispatched by the station is equal to the number of trains received. The corresponding expression is:

[0187] ;

[0188] Among them, O k D represents the starting point of traffic flow k. k This indicates the endpoint of traffic flow k.

[0189] The train formation capacity constraint is: the number of cars in each train is less than or equal to the maximum number of cars in the formation, and the corresponding expression is:

[0190] ;

[0191] The constraint on passenger volume fluctuation is that the train frequency must be within a certain fluctuation range, and its expression is:

[0192] ;

[0193] in, This represents the historical departure frequency of each train flow, determined based on the average departure frequency of all train flows in the historical OD information. , This indicates the preset threshold for traffic volume fluctuations.

[0194] The constraints on the values ​​of each decision variable are as follows:

[0195] ;

[0196] .

[0197] In the above implementation process, the objective function of the train operation plan is expressed in a parameterized manner, which makes it easier to solve the objective function of the train operation plan according to the constraints of the parameterized expression, thereby obtaining the train operation plan of the heavy-haul railway system.

[0198] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0199] Based on the same inventive concept, this application also provides a heavy-haul railway train operation scheduling device for implementing the above-mentioned heavy-haul railway train operation scheduling method. The solution provided by this device is similar to the solution described in the above-described method. Therefore, the specific limitations of one or more embodiments of the heavy-haul railway train operation scheduling device provided below can be found in the limitations of the heavy-haul railway train operation scheduling method above, and will not be repeated here.

[0200] In one exemplary embodiment, Figure 10 This is a schematic diagram of the structure of a heavy-haul railway train operation scheduling device provided in an embodiment of this application, as shown below. Figure 10 As shown, the device includes:

[0201] The objective function construction module 111 is used to construct the objective function of the train operation plan based on the line information, station information and historical traffic flow OD information in the heavy-haul railway system. The objective function of the train operation plan includes the total train operation time and the traffic balance. The total operation time includes loading and assembly time, travel time and combination and decomposition operation time. The traffic balance is constructed based on the deviation between the total number of train formations under the current traffic volume and the total number of train formations under the historical traffic volume in the heavy-haul railway system.

[0202] The constraint determination module 112 is used to determine the traffic volume fluctuation constraints of each train flow based on the historical departure frequency of each train flow obtained from the historical traffic flow OD information and the preset traffic volume fluctuation threshold; the historical traffic flow OD information includes multiple train flows with the same origin and destination stations.

[0203] The solution module 113 is used to solve the train operation scheme objective function based on the traffic fluctuation constraints of each train flow and the operation capacity constraints of each train flow in the heavy-haul railway system. The objective function is to minimize the function value of the train operation scheme objective function to obtain the train operation scheme of the heavy-haul railway system. The operation capacity constraints include station throughput capacity constraints, line throughput capacity constraints, combined decomposition station operation capacity constraints, train flow balancing capacity constraints, and train formation capacity constraints.

[0204] The operation scheduling module 114 is used to schedule the operation of trains in the heavy-haul railway system based on the train operation plan.

[0205] In one embodiment, the solving module 113 is specifically used for:

[0206] The solution parameters in the objective function of the train operation plan are mapped to chromosomes with gene structure in the genetic space; each chromosome corresponds to a train operation plan.

[0207] Based on the multiple operating periods of the heavy-haul railway system, each chromosome is divided into multiple sub-chromosomes. The number of sub-chromosomes corresponding to each chromosome corresponds to the number of operating periods of the heavy-haul railway system. The gene positions of each sub-chromosome include the station identifiers of the running path and the frequency of operation within the corresponding operating period.

[0208] All train flows in the heavy-haul railway system are sequentially identified as target train flows, and a set of optional train flows for the target train flows is determined. The set of optional train flows includes at least one optional train flow, and each optional train flow corresponds to an optional train operation scheme.

[0209] The pre-selected train flow for the target train flow is determined from the set of optional train flows. The remaining operational capacity of the heavy-haul railway system is updated based on the pre-selected train flow. The remaining operational capacity includes the remaining station throughput capacity, the remaining line throughput capacity, and the remaining operational capacity of the combined and decomposed stations.

[0210] Based on the remaining operational capacity and constraints, determine the initial selectable train flow for the target traffic flow;

[0211] Traverse and determine the initial selectable train flow corresponding to all train flows in the heavy-haul railway system;

[0212] Based on the initial selectable train flows corresponding to all train flows, crossover and mutation operations of the genetic algorithm are performed to obtain the train operation scheme of the heavy-haul railway system.

[0213] In one embodiment, the solving module 113 is specifically used for:

[0214] Determine the operational capacity of each initial optional train flow during each operating period. The operational capacity includes station throughput capacity, line throughput capacity, combined and decomposed station operation capacity, and traffic volume fluctuations.

[0215] If the operational capacity exceeds the corresponding capacity constraint, the penalty value is determined based on the amount by which the operational capacity exceeds the corresponding capacity constraint.

[0216] Based on the objective function of the train operation plan and the penalty value, a fitness function is constructed;

[0217] Based on the fitness function and the initial selectable train flow corresponding to all train flows, the crossover and mutation operations of the genetic algorithm are performed to obtain the train operation scheme of the heavy-haul railway system.

[0218] In one embodiment, the solving module 113 is specifically used for:

[0219] The fitness of all initial optional column streams is determined based on the fitness function;

[0220] Based on the roulette wheel strategy and all fitnesss, the parent selectable column flow of the genetic algorithm is determined from all initial selectable column flows;

[0221] Based on the intersection of the gene segments corresponding to the parent optional column streams in the column stream running path, the gene segments of the parent optional column streams are exchanged to obtain the initial offspring optional column streams;

[0222] Based on the intersection of gene segments corresponding to the initial offspring optional stream in multiple operating periods, the gene segments of the initial offspring optional stream are exchanged to obtain the offspring optional stream corresponding to the parent optional stream;

[0223] The departure frequency of the offspring selectable train flow during the target operating period is mutated to obtain the mutated offspring selectable train flow. The genetic algorithm crossover and mutation operations are then performed on the mutated offspring selectable train flow according to the fitness function until the iteration conditions are met to obtain the train operation plan. The target operating period can be any one of multiple operating periods, and the mutation operation includes increasing or decreasing the departure frequency.

[0224] In one embodiment, the solver module 113 is further configured to:

[0225] The departure frequency of the current child optional queue flow during the target operating period is mutated to obtain the mutated child optional queue flow; the current child optional queue flow is any one of the child optional queue flows.

[0226] If the operational capacity of the mutated child optional train flow exceeds the corresponding station operational capacity constraint, the other child optional train flows passing through the station within the target operating period are mutated to obtain the mutated child optional train flow. The step of mutating the child optional train flow is executed iteratively, and the train operation plan of the heavy-haul railway system is obtained based on the mutated child optional train flow that satisfies the station operational capacity constraint. Other child optional train flows are child optional train flows other than the current child optional train flow. The fitness of other child optional train flows is lower than that of the current child optional train flow. Operational capacity includes station throughput capacity, line throughput capacity, and operations of combined and decomposed stations.

[0227] In one embodiment, the solver module 113 is further configured to:

[0228] Based on the fitness function, the column flow corresponding to the current train operation plan is iteratively subjected to crossover and mutation operations of a genetic algorithm until the iteration condition is met; the column flow corresponding to the current train operation plan is the column flow retained after the mutation operation of the genetic algorithm;

[0229] The column streams retained after mutation operations when the iteration conditions are met are determined as the train operation scheme for the heavy-haul railway system.

[0230] In one embodiment, the objective function for the train operation plan is determined according to the following expression:

[0231] ;

[0232] in, Minimize the objective function of the train operation plan Indicates the loading and assembly time. This indicates that traffic flow k is at station The aggregation parameters, This indicates the column flow that the group passes through arc (i,j). Number of vehicles required The value represents whether traffic flow k passes through arc (i,j) during operating period t. If traffic flow k passes through arc (i,j) during operating period t, then... The value is 1. If traffic flow k does not pass through arc (i,j) during the operating period t, then The value is 0. Indicates travel time. Indicates the section through which traffic flow k passes ( , The runtime of ) The volume of traffic flow k within the operating period t represents the traffic volume of the vehicle flow k. Indicates the time required for combining and decomposing tasks. This indicates that traffic flow k is at station The combined decomposition station operation time. Indicates the operation period t column flow The frequency of train operations, Indicates grouped column flow Number of vehicles required This indicates the train flow of group t during the same historical operating period. Average demand reference value, The parameters represent the balance of traffic volume, where K represents the set of all train flows in the heavy-haul railway system, T represents the set of all operating time periods in the heavy-haul railway system, A represents the set of arcs corresponding to all sections in the heavy-haul railway system, and L represents the set of optional train flows generated by the OD of the train flows.

[0233] Each module in the aforementioned heavy-haul railway train operation scheduling device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0234] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 11 As shown, Figure 11 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data from a heavy-haul railway system. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a heavy-haul railway train operation scheduling method.

[0235] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0236] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the methods of any of the above embodiments.

[0237] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods of any of the above embodiments.

[0238] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0239] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0240] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0241] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for scheduling the operation of heavy-haul railway trains, characterized in that, The method includes: Based on the line information, station information, and historical traffic flow OD information in the heavy-haul railway system, a train operation plan objective function is constructed. The train operation plan objective function includes the total train operation time and the traffic volume balance. The total operation time includes loading and assembly time, travel time, and combination and decomposition operation time. The traffic volume balance is constructed based on the deviation between the total number of train formations under the current traffic volume and the total number of train formations under the historical traffic volume. Based on the historical train flow OD information, the historical operating frequency of each train flow is obtained, and the preset traffic volume fluctuation threshold is used to determine the traffic volume fluctuation constraint of each train flow; the historical train flow OD information includes train flow information with the same origin and destination stations. Based on the traffic volume fluctuation constraints of each train flow and the operational capacity constraints of each train flow in the heavy-haul railway system, a genetic algorithm is used to solve the objective function of the train operation scheme with the objective of minimizing the function value of the objective function of the train operation scheme, thereby obtaining the train operation scheme of the heavy-haul railway system; wherein, the operational capacity constraints include station throughput capacity constraints, line throughput capacity constraints, combined and decomposed station operational capacity constraints, train flow balancing capacity constraints, and train formation capacity constraints; Based on the train operation plan, the trains of the heavy-haul railway system are scheduled for operation.

2. The method according to claim 1, characterized in that, The train operation scheme for the heavy-haul railway system is obtained by solving the objective function of the train operation scheme based on the traffic volume fluctuation constraints of each train flow and the operating capacity constraints of each train flow in the heavy-haul railway system, using a genetic algorithm to minimize the function value of the objective function of the train operation scheme. The objective function includes: Each solution parameter in the objective function of the train operation scheme is mapped to a chromosome with gene structure in the genetic space; each chromosome corresponds to a train operation scheme. Based on the multiple operating periods of the heavy-haul railway system, each chromosome is divided into multiple sub-chromosomes. The number of sub-chromosomes corresponding to each chromosome corresponds to the number of operating periods of the heavy-haul railway system. The gene positions of each sub-chromosome include the station identifier of the running path and the operating frequency within the corresponding operating period. All train flows in the heavy-haul railway system are sequentially identified as target train flows, and a set of optional train flows for the target train flows is determined. The set of optional train flows includes at least one optional train flow, and each optional train flow corresponds to an optional train operation scheme. The pre-selected train flow of the target train flow is determined from the set of optional train flows, and the remaining operational capacity of the heavy-haul railway system is updated based on the pre-selected train flow. The remaining operational capacity includes the remaining station throughput capacity, the remaining line throughput capacity, and the remaining operational capacity of the combined and decomposed stations. Based on the remaining operational capacity and the corresponding constraints, the initial selectable train flow for the target traffic flow is determined; Traverse and determine the initial selectable train flow corresponding to all train flows in the heavy-haul railway system; Based on the initial selectable train flows corresponding to all train flows, crossover and mutation operations of a genetic algorithm are performed to obtain the train operation scheme of the heavy-haul railway system.

3. The method according to claim 2, characterized in that, The process of performing crossover and mutation operations using a genetic algorithm on the initial selectable train flows corresponding to all train flows to obtain the train operation scheme for the heavy-haul railway system includes: Determine the operational capacity of each of the initial optional train flows during each of the operating periods, wherein the operational capacity includes station throughput capacity, line throughput capacity, combined and decomposed station operational capacity, and traffic volume fluctuations; If the operational capacity exceeds the corresponding capacity constraint, a penalty value is determined based on the amount by which the operational capacity exceeds the corresponding capacity constraint. Based on the objective function of the train operation plan and the penalty value, a fitness function is constructed; Based on the fitness function and the initial selectable train flows corresponding to all train flows, the crossover and mutation operations of the genetic algorithm are performed to obtain the train operation scheme of the heavy-haul railway system.

4. The method according to claim 3, characterized in that, The process of performing crossover and mutation operations using a genetic algorithm based on the fitness function and the initial feasible column flows corresponding to all traffic flows to obtain the train operation scheme for the heavy-haul railway system includes: The fitness of all the initial optional column streams is determined based on the fitness function; Based on the roulette wheel strategy and all the fitness values, the parent selectable column stream of the genetic algorithm is determined from all the initial selectable column streams; Based on the intersection of the gene segments corresponding to the parent selectable column streams in the column stream running path, the gene segments of the parent selectable column streams are exchanged to obtain the initial offspring selectable column streams; Based on the intersection points of gene segments corresponding to the initial offspring selectable stream in multiple operating periods, the gene segments of the initial offspring selectable stream are exchanged to obtain the offspring selectable stream corresponding to the parent selectable stream; The departure frequency of the offspring selectable train flow during the target operating period is mutated to obtain the mutated offspring selectable train flow. The genetic algorithm crossover and mutation operations are then performed on the mutated offspring selectable train flow according to the fitness function until the iteration condition is met to obtain the train operation scheme. The target operating period can be any one of the multiple operating periods, and the mutation operation includes increasing or decreasing the departure frequency.

5. The method according to claim 4, characterized in that, The method further includes: The departure frequency of the current child optional queue stream during the target operating period is mutated to obtain the mutated child optional queue stream; the current child optional queue stream is any one of all child optional queue streams; If the operational capacity of the mutated sub-generation selectable train flow exceeds the corresponding station operational capacity constraint, the other sub-generation selectable train flows passing through the station within the target operating period are mutated to obtain mutated sub-generation selectable train flows. The step of mutating the sub-generation selectable train flows is executed cyclically, and the train operation scheme of the heavy-haul railway system is obtained based on the mutated sub-generation selectable train flows that satisfy the station operational capacity constraint. The other sub-generation selectable train flows are sub-generation selectable train flows other than the current sub-generation selectable train flow. The fitness of the other sub-generation selectable train flows is lower than that of the current sub-generation selectable train flow. The operational capacity includes station throughput capacity, line throughput capacity, and operations of combined and decomposed stations.

6. The method according to any one of claims 3-5, characterized in that, The method further includes: Based on the fitness function, the column flow corresponding to the current train operation plan is iteratively subjected to crossover and mutation operations of a genetic algorithm until the iteration condition is met; the column flow corresponding to the current train operation plan is the column flow retained after the mutation operation of the genetic algorithm. The column streams retained after the mutation operation when the iteration conditions are met are determined as the train operation scheme of the heavy-haul railway system.

7. The method according to claim 1, characterized in that, The objective function of the train operation plan is determined according to the following expression: ； in, Minimize the objective function of the train operation plan Indicates the loading and assembly time. This indicates that traffic flow k is at station The aggregation parameters, This indicates the column flow that the group passes through arc (i,j). Number of vehicles required The value represents whether traffic flow k passes through arc (i,j) during operating period t. If traffic flow k passes through arc (i,j) during operating period t, then... The value is 1. If traffic flow k does not pass through arc (i,j) during the operating period t, then The value is 0. Indicates travel time. Indicates the section through which traffic flow k passes ( , The runtime of ) The volume of traffic flow k within the operating period t represents the traffic volume of the vehicle flow k. Indicates the time required for combining and decomposing tasks. This indicates that traffic flow k is at station The combined decomposition station operation time. Indicates the operation period t column flow The frequency of train operation, Indicates grouped column flow Number of vehicles required This indicates the train flow of group t during the same historical operating period. Average demand reference value, The parameters represent the balance of transport volume, where K represents the set of all train flows in the heavy-haul railway system, T represents the set of all operating time periods in the heavy-haul railway system, A represents the set of arcs corresponding to all sections in the heavy-haul railway system, and L represents the set of optional train flows generated by the OD of the train flows.

8. A heavy-haul railway train operation scheduling device, characterized in that, The device includes: The objective function construction module is used to construct an objective function for train operation schemes based on line information, station information, and historical traffic flow OD information in the heavy-haul railway system. The objective function for train operation schemes includes the total train operation time and the transport volume balance. The total operation time includes loading and assembly time, travel time, and combination and decomposition operation time. The transport volume balance is constructed based on the deviation between the total number of train formations in the current transport volume and the total number of train formations in the historical transport volume of the heavy-haul railway system. The constraint determination module is used to determine the traffic volume fluctuation constraints of each train flow based on the historical departure frequency of each train flow obtained from the historical traffic flow OD information and a preset traffic volume fluctuation threshold; the historical traffic flow OD information includes multiple train flows with the same origin and destination stations. The solution module is used to solve the train operation scheme objective function based on the traffic fluctuation constraints of each train flow and the operational capacity constraints of each train flow in the heavy-haul railway system. The objective function is to minimize the function value of the train operation scheme objective function, thereby obtaining the train operation scheme of the heavy-haul railway system. The operational capacity constraints include station throughput constraints, line throughput constraints, combined decomposition station operation capacity constraints, train flow balancing capacity constraints, and train formation capacity constraints. The operation scheduling module is used to schedule the operation of trains in the heavy-haul railway system based on the train operation plan.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. 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 steps of the method according to any one of claims 1 to 7.

Images