A method and system for constructing a heavy-load railway locomotive operation organization scheme

Abstract

The application provides a heavy haul railway locomotive operation organization scheme construction method and system, relates to the railway transportation organization technical field, and comprises the following steps: acquiring railway transportation capacity data and railway transportation demand parameters; constructing according to the railway transportation demand parameters and the railway transportation capacity data to obtain a train task structure; constructing based on the train task structure, train operation rules and locomotive operation rules to obtain a multi-layer space-time network; constructing a locomotive route operation scheme according to the multi-layer space-time network and a preset heavy haul transportation constraint system to obtain a locomotive route operation optimization model; and iteratively solving the locomotive route operation optimization model according to a tabu search algorithm to obtain a locomotive operation organization scheme. The application solves the problem of the decline of the overall transportation organization efficiency of heavy haul railways.

Description

Technical Field

[0001] This invention relates to the field of railway transportation organization technology, and more specifically, to a method and system for constructing a locomotive operation organization scheme for heavy-haul railways. Background Technology

[0002] In existing railway transportation organization technologies, the operation of locomotives on heavy-haul railways mostly adopts a segmented management and short-route locomotive swapping mode. During periods of stable traffic volume, this mode can match the responsibilities of segmented management with the needs of locomotive preparation. Each hub station carries out technical operations such as locomotive coupling / uncoupling, depot entry / exit, coupling, and air testing in an orderly manner according to a predetermined plan, and the occupancy of arrival / departure tracks and throat areas is controllable. Under high-volume conditions, the short-route layout makes it difficult for a large number of transit trains to complete locomotive swapping and preparation en route. They can only converge at at least a few hub stations to carry out technical operations. Trains repeatedly perform coupling / uncoupling, depot entry / exit, coupling, and air testing operations, repeatedly occupying arrival / departure tracks and throat areas. The operation links are closely connected and mutually restrictive, which not only lengthens the duration of each occupation but also increases the frequency of occupation. This directly leads to train queuing and congestion, a decrease in locomotive turnaround efficiency, and ultimately a decline in the overall transportation organization efficiency of heavy-haul railways.

[0003] Therefore, there is an urgent need for a method and system for constructing a locomotive operation organization scheme for heavy-haul railways, which solves the problem of declining overall transportation organization efficiency of heavy-haul railways. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for constructing a locomotive operation organization scheme for heavy-haul railways, so as to improve the above-mentioned problems. To achieve the above objective, the technical solution adopted by this invention is as follows:

[0005] Firstly, this application provides a method for constructing a locomotive operation organization scheme for heavy-haul railways, including:

[0006] Obtain railway transport capacity data and railway transport demand parameters;

[0007] The train task structure is constructed based on the railway transport demand parameters and the railway transport capacity data.

[0008] Based on the train mission structure, train operation rules and locomotive operation rules, a multi-layered spatiotemporal network is constructed, wherein the train operation rules include at least the minimum train tracking interval, and the locomotive operation rules include at least the upper limit of the locomotive's single continuous traction mileage.

[0009] Based on the multi-layered spatiotemporal network and the preset heavy-load transportation constraint system, a locomotive route utilization scheme is constructed to obtain a locomotive route utilization optimization model;

[0010] The locomotive routing optimization model is iteratively solved using the tabu search algorithm to obtain the locomotive operation organization scheme.

[0011] Secondly, this application also provides a system for constructing a heavy-haul railway locomotive operation organization scheme, including:

[0012] The acquisition module is used to acquire railway transport capacity data and railway transport demand parameters;

[0013] The first construction module is used to construct, based on the railway transportation demand parameters and the railway transportation capacity data, to obtain the train task structure;

[0014] The second construction module is used to construct a multi-layer spatiotemporal network based on the train task structure, train operation rules and locomotive operation rules. The train operation rules include at least the minimum train tracking interval, and the locomotive operation rules include at least the upper limit of the locomotive's single continuous traction mileage.

[0015] The third construction module is used to construct a locomotive route utilization scheme based on the multi-layer spatiotemporal network and the preset heavy-load transportation constraint system, so as to obtain a locomotive route utilization optimization model.

[0016] The iterative solution module is used to iteratively solve the locomotive route optimization model according to the tabu search algorithm to obtain the locomotive operation organization scheme.

[0017] The beneficial effects of this invention are as follows:

[0018] This invention constructs a train task structure using railway transport capacity data and transport demand parameters, reducing locomotive empty running rates and minimizing idle and wasted transport resources. Based on this, a spatiotemporal network of train service and locomotive operation layers is built according to the train task structure, train operation rules, and locomotive utilization rules, explicitly depicting the entire process of locomotive-train coupling, decoupling, and reconstruction. Subsequently, by integrating the multi-layered spatiotemporal network and the heavy-haul transport constraint system, the spatiotemporal correlation characteristics of the railway network are taken into account, ensuring that locomotive routing schemes conform to the actual operation scenarios of heavy-haul railways. Finally, the tabu search algorithm iteratively solves the optimization model, reducing the risk of getting trapped in local optima during the algorithm's solution process, quickly outputting the optimized locomotive operation organization scheme, improving the rationality of locomotive routing, and ensuring stable, efficient, and smooth heavy-haul railway transport order. In summary, this invention solves the problem of declining overall transport organization efficiency in heavy-haul railways.

[0019] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the process for constructing a heavy-haul railway locomotive operation organization scheme as described in this embodiment of the invention;

[0022] Figure 2 This is a schematic diagram of the multi-layer spatiotemporal network described in an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of the equipment structure for constructing the heavy-haul railway locomotive operation organization scheme as described in this embodiment of the invention.

[0024] The diagram is labeled as follows: 800, Heavy-haul railway locomotive operation organization scheme construction equipment; 801, Processor; 802, Memory; 803, Multimedia component; 804, I / O interface; 805, Communication component. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0026] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0027] In the actual application scenario of high-capacity transportation organization on heavy-haul railways, the railway lines adopt the traditional locomotive operation mode of segmented management and short-route swapping. When the traffic volume is stable, it can adapt to the segmented management responsibilities and locomotive preparation needs of each hub station. Each station completes the technical operations of locomotive coupling / uncoupling, entering / leaving the depot, coupling, and air testing in an orderly manner according to plan. The occupancy scale of the station arrival / departure tracks and throat area is under control. However, under high-capacity conditions, a large number of transit trains cannot complete locomotive swapping and preparation operations en route. They can only gather at least a few hub stations to carry out the relevant technical operations. Trains frequently repeat operations such as coupling / uncoupling, entering / leaving the depot, coupling, and air testing, continuously occupying the station arrival / departure tracks and throat area resources. This not only prolongs the single occupation time of station equipment but also significantly increases the occupation frequency, leading to train queuing and congestion and a significant decrease in locomotive turnaround efficiency. Ultimately, this results in a decline in the overall transportation organization efficiency of heavy-haul railways, making it impossible to meet the demand for efficient and stable heavy-haul railway transportation.

[0028] Example 1:

[0029] This embodiment provides a method for constructing a locomotive operation organization scheme for heavy-haul railways.

[0030] See Figure 1 The figure shows that the method includes steps S1 to S5, including:

[0031] S1: Obtain railway transport capacity data and railway transport demand parameters;

[0032] In this step, for specific transportation scenarios of heavy-haul railways, the heavy-haul railway dispatching department combines the specific section line conditions, technical standards, and transportation organization requirements. The railway transportation demand parameters include transportation demand, freight flow demand between loading and unloading stations within the planning period, and target traffic volume for freight volume growth. The railway transportation capacity data includes the network topology, the connection relationship between loading and unloading stations, core hub stations, and adjacent sections, the number of effective arrival and departure tracks at stations, section throughput capacity, minimum tracking interval, long and short route organization rules, train formation methods, locomotive type and traction performance, maximum number of cars in a formation, long route through operation time, short route carriage change operation time, combination and decomposition operation time, locomotive preparation time, and station waiting time.

[0033] S2: Based on the railway transportation demand parameters and the railway transportation capacity data, a train task structure is constructed;

[0034] To clarify the specific method for obtaining the train task structure, step S2 includes S21 to S24, specifically:

[0035] S21: Based on the freight flow demand of loading and unloading stations in the railway transportation demand parameters and the preset transportation organization rules, train flow tasks are constructed to obtain candidate train flow tasks;

[0036] In this step, based on the OD freight flow demand of each loading station to unloading station in the railway transportation demand parameters, and combined with the heavy-haul railway transportation organization rules and line operation restrictions, an initial candidate train flow task is generated using the Cartesian product permutation method. This task covers all possible originating stations, terminating stations, train formation types, and route modes, comprehensively covering potential train flow organization forms such as direct, indirect, and technically direct routes from loading locations, to ensure that no feasible transportation organization scheme is overlooked.

[0037] S22: Based on the operational characteristics of the hub station, the candidate train flow tasks are divided into train flow types;

[0038] In this step, based on whether the hub station performs operations such as locomotive swapping and train combination decomposition, the candidate train flow tasks are divided into direct short-route train flows from the loading point, direct long-route train flows from the loading point, non-direct train flows, and technically direct train flows. At the same time, different train formation types such as 10,000-ton trains, 20,000-ton combined trains, and general freight trains are distinguished, as well as two route modes: long-route through and short-route swapping, in order to define the operational logic and organization of various train flows within the hub station.

[0039] S23: Mark the column stream task attributes of the column stream type to obtain a column stream candidate set;

[0040] In this step, the train flow types are standardized by labeling key information such as originating station, destination station, combined station, train flow type, route, planned number of trains, and required locomotive type and quantity. At the same time, invalid train flows that do not meet the requirements of transportation organization theory, line physical limits, locomotive maintenance mileage, and continuous operation time of crew members are eliminated to obtain an initial train flow set. The initial train flow set is then subjected to restrictions such as path connectivity, locomotive maintenance mileage, and continuous operation time of crew members to form a valid train flow candidate set that meets the actual operational constraints.

[0041] The expression for the initial column stream set is:

[0042] ;

[0043] In the above formula, Represents the initial column stream set, Indicates train The starting point (i.e., the loading station). Indicates train The final destination (i.e., the unloading station). Indicates train Grouping types, Indicates train The route pattern Indicates the assembly point at the loading station. Indicates the assembly point at the unloading station. This represents the set of train formation types. This represents the set of train route patterns.

[0044] S24: Based on the railway transport capacity data, the train flow candidate set is filtered to obtain the train task structure.

[0045] In this step, based on the railway transport capacity data and the OD (Original Demand) volume demand of heavy-haul railways in the direction of heavy-haul trains, freight tasks are allocated to the train flow candidate set for consideration of constraints such as transport demand satisfaction, section throughput capacity, station arrival and departure line capacity, minimum tracking interval, and adaptability of long and short routes. Guided by the optimization of the generalized operating cost of the system, including traction energy consumption, vehicle assembly, hub operations, and organizational risks, the train flow candidate set is subjected to dual screening for compliance and economy, ultimately obtaining a train task structure that meets the requirements of line capacity and transport efficiency.

[0046] The consideration of transportation demand satisfaction is the proportion of OD freight flow demand between each loading station and unloading station covered by the actual train capacity. For any OD pair, it is the ratio of the sum of the train flow carrying capacity selected into the train task structure to the planned transport volume demand of the OD pair. The closer the ratio is to 1, the better the transportation demand satisfaction.

[0047] The section throughput capacity refers to the maximum number of train pairs that can safely pass through a single section of the railway line within a cycle. It is calculated based on the minimum tracking interval of the line and the available capacity of the station's arrival and departure tracks to obtain the theoretical maximum number of trains that can pass through.

[0048] The traction energy consumption refers to the energy consumption generated by the train during its operation within a section due to traction power consumption. Based on the train traction calculation procedure, it is determined by the train weight, operating speed, track longitudinal profile conditions, and locomotive traction characteristic curve, and is measured in terms of electricity consumption per ton-kilometer or fuel consumption per ton-kilometer.

[0049] S3: Based on the train task structure, train operation rules and locomotive operation rules, a multi-layer spatiotemporal network is constructed to obtain the train operation rules, which at least include the minimum train tracking interval, and the locomotive operation rules at least include the upper limit of the locomotive's single continuous traction mileage.

[0050] To clarify the specific method for obtaining the multi-layer spatiotemporal network, step S3 includes S31 to S35, specifically:

[0051] S31: Obtain the station set, the section line set, and the train time node set;

[0052] S32: Based on the train task structure, input the station set and the section line set into the topology network to obtain the train physical topology network;

[0053] In this step, based on the train task structure, the station set and the section line set are input into an undirected basic triplet topology network constructed with heavy-haul railway physical facilities as entities and line connectivity as the association logic. Specifically, the heavy-haul railway physical network needs to be abstracted into a topology network containing a station set and a section line set including loading stations, unloading stations, and core hub stations, to obtain the train physical topology network.

[0054] The physical topology network of the locomotive and train is logically divided into an upper train service layer and a lower locomotive operation layer, such as... Figure 2 As shown, in the upstream and downstream sections of the hub station, the train and locomotive maintain a coupled relationship (i.e., fixed matching operation); within the hub station, the separation and redistribution of train tasks and locomotive tasks are achieved through decoupling and reconfiguration mechanisms.

[0055] S33: Discretize the time node set according to the planning period to obtain a discrete time node set;

[0056] In this step, the time interval of the planning cycle is discretized for the set of time nodes. The feasible arrival time, departure time, dwell time and loading / unloading / passing time of each station at each discrete time point are formed to form a discrete time node set covering the entire operation process of trains and locomotives.

[0057] S34: Based on the physical topology network of the locomotive and train, the train operation rules, the locomotive operation rules, and the set of discrete time nodes, an operation network is constructed to obtain a locomotive-train cooperative operation network;

[0058] To clarify the specific method for obtaining the train-machine cooperative operation network, step S34 includes steps S341 to S343, specifically:

[0059] S341: Based on the physical topology network of the train, the set of discrete time nodes, and the train spatiotemporal state nodes and train spatiotemporal flow arcs in the train operation rules, a train service layer network is constructed to obtain the train service layer network.

[0060] In this step, the train spatiotemporal state node includes the train arrival node. Train departure node Empty train arrives at node Empty car departure node Train waiting nodes The train's spatiotemporal flow arc includes the loaded train running arc. Straight-through operation arc locomotive changing arc Off-hook operation arc Hanging-up operation arc Train connection arc Train combination arc Empty car return arc and train decomposition arc A service layer node set is constructed by using the physical topology network of the train and the discrete time node set and the train spatiotemporal status node. Then, a directed flow arc is built between the spatiotemporal nodes of the service layer node set by using the train operation rules and the train spatiotemporal flow arc. Each directed flow arc is bound to a standard operation duration, and a 0-1 decision variable is set to identify the train's occupancy status of the arc segment. The train service layer network is constructed to describe the operation process of heavy-haul trains in sections, stops at stations, through hubs, changing carriages, and combination and decomposition operations.

[0061] The train operation rules mentioned above are the official train operation regulations for heavy-haul railways. They refer to the set of operational standards that heavy-haul railway trains should follow when running on the line, including minimum train following intervals, train formation speed limits, interval running time standards, station arrival and departure operation time, rules for separating empty and loaded cars, standard operating procedures for train combination / disassembly, restrictions on freight train stops en route, and rules for direct trains to pass without changing carriages.

[0062] S342: Based on the physical topology network of the locomotive train, the set of discrete time nodes, and the locomotive operation time-space nodes and locomotive operation arcs in the locomotive operation rules, a locomotive operation layer network is constructed to obtain the locomotive operation layer network.

[0063] In this step, the locomotive operation time and space nodes include locomotive arrival nodes. Locomotive departure node Empty locomotive arrives at the node , departure node of empty locomotive and locomotive waiting nodes The locomotive operating arc includes a loaded vehicle traction arc. Locomotive Straight Through Arc locomotive disassembly arc Locomotive coupling arc Locomotive connection arc Single-machine return arc and empty car traction arc The entire set of application layer nodes is constructed by using the physical topology network of the locomotive train, the set of discrete time nodes, and the spatiotemporal nodes of locomotive operations. Then, by using the locomotive operation rules and the locomotive operation arcs, heavy-duty traction, locomotive through traffic, coupling / uncoupling, single-locomotive return, and other operation arcs are built on the entire set of application layer nodes. Each operation arc is bound to a standard operation duration, and an integer variable is set to record the number of different locomotive types in each arc segment. The locomotive application layer network is constructed to characterize locomotive traction, waiting, preparation, empty return, coupling / uncoupling, and turnover operation behaviors.

[0064] The locomotive operation rules are the locomotive management specifications of the locomotive depot, which refer to the set of operating specifications that locomotives should follow in the operation and turnover of heavy-haul railway transportation. These include the upper limit of the single continuous traction mileage of a locomotive, the locomotive preparation cycle and preparation time, the traction quota matching standard for multiple types of locomotives, the locomotive turnaround and replacement operation process, the speed limit and route restriction for single locomotive return, the constraint of the continuous working time of the crew, and the locomotive standby parking rules.

[0065] S343: Based on the train service layer network and the locomotive operation layer network, a train-locomotive cooperative operation network is constructed.

[0066] In this step, the train service layer network and the locomotive operation layer network are aligned at nodes, associated at arcs, and logically connected under a unified spatiotemporal framework to form an integrated train-locomotive collaborative operation network covering train operation and locomotive operation.

[0067] S35: Based on the upstream and downstream of the hub station, the train-machine cooperative operation network is spatiotemporally coupled and constructed through the power matching relationship to obtain a multi-layer spatiotemporal network.

[0068] In this step, the upstream and downstream of the hub station are used as the dividing points, and the loaded vehicle operation arc is used in the upstream and downstream sections. With the heavy vehicle traction arc The traction power matching relationship is used to couple the train and the machine. Within the hub station, the through operation arc of the train is used. The straight arc with the locomotive The mapping relationship establishes a long-distance through relationship, and the train swapping operation is used to disconnect the locomotive from the arc. The locomotive coupling arc The mapping relationship between them establishes a short-route coupling relationship, and simultaneously constrains the change in the number of locomotives before and after the train combination. The locomotive-train cooperative operation network is spatiotemporally coupled through the long-route through relationship and the short-route coupling relationship to complete the logical closed loop and form a two-layer spatiotemporal network that can support the train service layer and the locomotive operation layer for locomotive-train cooperative optimization.

[0069] S4: Based on the multi-layered spatiotemporal network and the preset heavy-load transportation constraint system, a locomotive route utilization scheme is constructed to obtain a locomotive route utilization optimization model;

[0070] To clarify the specific method for obtaining the locomotive route utilization optimization model, step S4 includes S41 to S44, specifically:

[0071] S41: Based on the nodes and arcs in the multi-layer spatiotemporal network and the train task structure, a networked decision model is constructed to obtain the networked decision model;

[0072] In this step, information such as the number of trains, route patterns, and train formation types in the train service layer and locomotive operation layer of the multi-layered spatiotemporal network is uniformly transformed into quantifiable network flow decision variables. These variables are used to clarify the occupancy, connection, coupling, and decoupling relationships between trains and locomotives in the spatiotemporal network, forming a networked decision model that supports locomotive route optimization.

[0073] S42: Based on the networked decision-making model, a comprehensive objective function is constructed to minimize operating costs by using the minimum number of locomotives and the shortest total travel time for trains in the loaded direction as dual objective functions. In this step, based on the networked decision-making model, a sub-objective of minimizing the number of locomotives is constructed with the aim of reducing locomotive asset investment and improving locomotive utilization. A sub-objective of minimizing the total travel time for trains in the loaded direction is constructed with the aim of reducing train on-the-way running and non-production waiting time at hubs and improving cargo delivery efficiency. Locomotive cost weight and transportation efficiency weight are added to weight and fuse the two sub-objectives with different dimensions to construct a comprehensive objective function oriented towards minimizing operating costs.

[0074] Taking the minimum number of locomotives used as a sub-objective, this approach optimizes locomotive connection relationships to increase daily locomotive output, thereby minimizing the required locomotive scale while meeting transport demand. The expression for minimizing the number of locomotives used is:

[0075] ;

[0076] In the above formula, This indicates that the number of locomotives used is the minimum. This represents the minimize operator. This indicates the total number of locomotives put into use that day. This refers to all stations in the railway network. Summation, This indicates all locomotive types. Summation, express At that time The type of station stay is The number of locomotives Indicates from time , stand, The initial state of this type of locomotive, continuing until the end of the day at 14:40, still shows it stopped at... Locomotive connection at the station; express The number of locomotives still in operation at that time This represents the set of locomotive connection schemes for cross-section operation. express The number of locomotives that are still operating across sections and have not yet stopped at stations. Indicates the set of railway station locations. Let represent the set of locomotive types; taking the shortest total travel time for trains in the loaded direction as the sub-objective, by imposing penalty constraints on train travel time and invalid station stay time, the model is guided to prioritize the longer-distance through transport mode with shorter travel time. The expression for the shortest total travel time for trains in the loaded direction is:

[0077] ;

[0078] In the above formula, This indicates that the train traveling in the direction of the loaded vehicle has the shortest total travel time. This represents the minimize operator. This indicates the total travel time for all trains traveling in the loaded direction. This represents the summation operator. express For set Any directed arc segment in the array, Let represent the set of all directed arcs on the train service level. Represents arc segment The corresponding task or running time; Indicates the train flow in the service level. For arc segment The occupancy status. Due to and Due to the different units of measurement, a locomotive cost weight is introduced. and transportation efficiency weight The weighted fusion of the two sub-objectives into a comprehensive objective function that minimizes the generalized operating cost of the system is expressed as follows:

[0079] ;

[0080] In the above formula, Represents the overall objective function. This represents the overall broad operating costs. Indicates the cost weight of locomotives. This represents the minimize operator. This refers to all stations in the railway network. Summation, This indicates all locomotive types. Summation, Indicates the set of railway station locations. Represents the set of locomotive types. express At that time The type of station stay is The number of locomotives Indicates from time , stand, The initial state of this type of locomotive, continuing until the end of the day at 14:40, still shows it stopped at... Locomotive connection at the station; Then it means The number of locomotives still in operation at that time This represents the set of locomotive connection schemes for cross-section operation. express The number of locomotives that are still operating across sections and have not yet stopped at stations. Indicates the weight of transportation efficiency. This represents the summation operator. express For set Any directed arc segment in the array, Let represent the set of all directed arcs on the train service level. Represents arc segment The corresponding task or running time; Indicates the train flow in the service level. For arc segment The occupancy status.

[0081] The locomotive cost weight is used to reflect the railway enterprise's sensitivity to fixed asset investment, and the transportation efficiency weight is used to reflect the railway enterprise's emphasis on the timeliness of cargo delivery and the efficiency of the railway network turnover.

[0082] S43: Based on the operational feasibility constraints of trains, the locomotive routing coupling constraints of hub stations, and the preset arrival and departure line capacity constraints and traffic safety constraints, a heavy-haul transportation constraint system is constructed.

[0083] In this step, the actual operation and safe operation requirements of heavy-haul railway trains are used as operational feasibility constraints to ensure that the timing of technical operations of locomotives and trains within stations and the availability of resources meet the basic operational conditions. This involves constructing constraints on the number of trains (to ensure that all types of train flows in the input train flow set generate running trajectories according to predetermined quantities), network flow balance constraints between train flows and locomotive flows (to ensure that train flows and locomotive flows meet inflow and outflow balance at each intermediate node), traction power matching constraints (to ensure that the number of locomotives assigned to trains in upstream and downstream sections meets the traction requirements of the corresponding lines), and locomotive route coupling constraints at hub stations. These locomotive route coupling constraints include long-route through-run coupling constraints (to ensure that long-route train flows at hub stations...). The system includes the following constraints when performing through operations: locomotive synchronous selection of through connection relationship, short-route coupling constraints (to ensure that when short-route trains are coupled at hub stations, the original locomotive is uncoupled and the new locomotive is coupled), train combination logic constraints (to ensure that 20,000-ton combined trains are formed by merging two unit trains), locomotive release constraints after combination (to characterize the change in the number of locomotives before and after combination), arrival and departure line capacity constraints, and traffic safety constraints (including minimum train tracking interval constraints, upper limit of simultaneous occupation of station throat area, safe interval for double-track passing, locomotive traction and braking performance matching constraints, exclusive operation restrictions for oversized freight trains, and nighttime speed reduction constraints: to ensure that the scheme meets the requirements of station capacity and traffic safety).

[0084] The train operation safety constraints refer to the set of constraints set to ensure the safe operation of trains.

[0085] The expression for the heavy-haul transportation constraint system is:

[0086] ;

[0087] ;

[0088] ;

[0089] ;

[0090] ;

[0091] ;

[0092] ;

[0093] ;

[0094] ;

[0095] ;

[0096] ;

[0097] ;

[0098] ;

[0099] ;

[0100] ；

[0101] ;

[0102] In the above formula, This indicates traversing each discrete time node within the planning period. Summation, Indicates traversing the column stream All originating loaded trains operating arc Summation, This represents the set of discrete time points within the planning period. Indicates a stream from the column The set of heavy-duty train running arcs originating from the physical starting station. This indicates that for each column stream All are established. Indicates the train flow in the train operation plan The set, Indicates the train flow in the service level Occupied arc The decision variable is 0-1, with 1 for occupied and 0 for unoccupied; Represents column stream Opening logarithm Indicates that the endpoint is a stream. The set of loaded train running arcs at the physical terminal stations. This indicates traversing all incoming nodes. Summing the arc segments, Indicates entering the node The set of arcs, This indicates traversing all outflow nodes. Summing the arc segments, Indicates leaving the node The set of arcs, Represents column stream The set of intermediate nodes, Indicates the use of the locomotive's arc segment The number of locomotives on board is a variable. This represents the set of intermediate nodes in the locomotive operation layer. Indicates all that belong to the set nodes , Indicates the use of the locomotive's arc segment superior The number of different types of locomotives This indicates traversing all column streams. Summation, Indicates train The required upstream section bounded by the hub station The number of different types of locomotives Indicates the train flow in the service level Occupied arc 0-1 decision variables This represents the set of mappings between the train's running arc and its corresponding locomotive traction arc. Indicates train The required downstream section bounded by the hub station The number of different types of locomotives This means that for all elements belonging to the set... ordered arc pairs , This indicates summing all long-intersection flow sequences. This represents the set of long-distance train flows in the train operation plan. This represents the mapping set of through operation arcs within a train station and their corresponding locomotive through connection arcs. This means for all elements belonging to the set ordered arc pairs , Indicates the removal of arc On Number of locomotives of this type This represents summing the flows of all shortest intersections. This represents the set of short-route train flows in the train operation plan. Indicates short-circuit train flow Upstream section required Number of locomotives of different types This represents the mapping set of locomotive changing arcs and their corresponding locomotive unloading arcs. Indicates a continuous arc On Number of locomotives of different types Indicates short-circuit train flow Downstream section required Number of locomotives of different types This means for all elements belonging to the set Ordered decomposition arc , This means for all elements belonging to the set Orderly hanging arc , This represents the mapping set of locomotive coupling arcs and their corresponding locomotive coupling arcs. Represents a combined column stream Occupy combined operation arc , Indicates a combined operation arc. This represents the set of combined train flows in the train operation plan. This represents summing the quantities of all units in the 10,000-ton column. Represents a unit of 10,000-ton column flow set. Represents cell column flow Occupy waiting arc 0-1 decision variables Indicates the departure time of the combined train. This represents the maximize operator. This indicates the arrival time of the first train to be assembled. This indicates the arrival time of the second train to be assembled. Indicates the standard time for combined operations. Indicates locomotive arc disengagement superior Number of locomotives of different types This represents summing the train flows of all combinations of 10,000-ton trains. Represents the set of combined train flows. Indicates the upstream section required by the unit train Number of locomotives of different types Indicates the required downstream section of the combined train Number of locomotives of different types Represents a combined column stream Occupy combined operation arc 0-1 decision variables Indicates the traversal time. Summation of the occupied work arcs within the station. Indicates at time A set of operational arcs within a hub station that are currently occupied. This indicates the number of valid arrival and departure tracks at the hub station. This indicates that for each discrete time node within the planning period... , Indicates from time arrive Summation of consecutive time windows Indicates traversing the stations time Sum of all starting arcs. This indicates the minimum train tracking interval. Indicates station At any moment The train departure arc assembly, Represents the set of railway station locations Each station in , Represents the set of discrete time nodes within the planning period. Each time point in , Indicates the set of railway station locations. Indicates the use of the locomotive's arc segment superior The number of different types of locomotives This represents the set of all directed arcs in the train service layer. Represents the set of positive integers. This represents the set of all directed arcs in the locomotive operation layer.

[0103] S44: Based on the comprehensive objective function and the heavy-haul transportation constraint system, the locomotive route utilization scheme is optimized and constructed to obtain the locomotive route utilization optimization model.

[0104] In this step, the comprehensive objective function is used as the optimization direction, and the heavy-haul transportation constraint system is used as the feasible solution boundary. The decision problems such as locomotive route configuration, train running time, and locomotive turnaround are transformed into constrained bi-objective optimization problems, and finally a locomotive route utilization optimization model is formed for solving the locomotive route utilization scheme of heavy-haul railways.

[0105] S5: The locomotive routing optimization model is iteratively solved using the tabu search algorithm to obtain the locomotive operation organization scheme.

[0106] To clarify the specific method for obtaining the locomotive operation organization plan, step S5 includes S51 to S56, specifically:

[0107] S51: Based on the greedy heuristic rules in the tabu search algorithm, prioritize the assignment of available locomotives in the locomotive route utilization optimization model to generate an initial locomotive route chain set;

[0108] In this step, a train task queue is constructed according to the train departure time sequence. Based on the greedy heuristic rule, available locomotives are matched for each train task, and a complete traction, return, preparation, and waiting turnaround task chain for each locomotive within the planning period is formed in sequence, thereby generating an initial locomotive route chain set.

[0109] S52: During the iterative search process of the tabu search algorithm, a neighborhood call is performed using the neighborhood search operator in locomotive routing to generate a candidate solution set;

[0110] In this step, during the iterative search process of the tabu search algorithm, the task exchange operator, the preparation time shift operator, and the long / short route mode switching operator in the neighborhood search operator are called to adjust the task allocation, shift the preparation time period, and switch the hub through and carriage change modes between different locomotive route chains, thereby generating a candidate solution set and expanding the search range of the algorithm.

[0111] The task exchange operator is used to exchange tasks of similar nature between different locomotive routes. The maintenance time shift operator is used to adjust the position of maintenance tasks in the route. The long / short route mode switching operator is used to switch train tasks passing through hub stations between through mode and coupling mode. The long / short routes are short routes (when the train passes through the hub station, the locomotive is uncoupled and re-coupled to a new locomotive, and the locomotive is only responsible for traction of a single section and does not work continuously across hubs) and long routes (the locomotive travels directly with the train throughout the entire journey, does not uncouple or recouple when passing through the hub station, the train and locomotive are coupled throughout the entire journey, and only through operations are handled within the hub).

[0112] S53: Construct the locomotive identifier, train identifier, and operation mode in the candidate solution set to obtain taboo features;

[0113] The operational mode described in this step is the train matching and organization mode within the hub station, which refers to the specific way in which the train completes technical operations within the hub station. Specifically, it is divided into: long-route through mode (the locomotive travels directly with the train throughout the entire journey without being detached or coupled at the hub station), short-route coupling mode (after the train arrives at the hub, the original locomotive is detached and a new locomotive is re-coupled to continue operation), and combination and decomposition mode (two 10,000-ton units are combined into a 20,000-ton train / split at the hub).

[0114] S54: Based on the initial locomotive routing chain set, and combining the candidate solution set with the taboo features, perform backtracking of restricted candidate solutions to select the current optimal solution;

[0115] In this step, based on the initial solution in the initial locomotive routing chain set, the search process is repeatedly backtracked to the poorer solutions that have already been explored, in combination with the candidate solution set and the taboo features, to avoid the algorithm getting stuck in a local loop. At the same time, the optimal solution for the current iteration is selected according to the selection rules based on the size of the objective function value.

[0116] S55: Iterative optimization process: Based on the candidate solution set, the current optimal solution is judged. When a candidate solution with taboo characteristics is better than the optimal solution, the amnesty criterion is triggered and the current optimal solution is updated to obtain the next optimal solution.

[0117] In this step, the current optimal solution is judged based on the candidate solution set. The generalized operating cost target value of the candidate solution set is compared with that of the current optimal solution one by one, and candidate solutions generated by neighborhood movement are then considered. Although it contains taboo features, its fitness value Better than the historical best solution If the taboo is lifted, the candidate solution is updated to the next optimal solution, thus ensuring that the algorithm can escape local optima.

[0118] S56: Continue to execute the iterative optimization process for the next optimal solution until the preset maximum number of iterations is reached or the convergence condition is met, then terminate the iteration and output the locomotive operation organization scheme.

[0119] In this step, the neighborhood search, tabu judgment, amnesty and update process is repeatedly performed on the next optimal solution. The iteration stops when the preset maximum number of iterations is reached or the objective function value tends to stabilize and converge. Finally, the locomotive operation organization scheme is output. The locomotive operation organization scheme includes long and short route configuration scheme, train operation time scheme and locomotive turnaround and connection scheme.

[0120] Example 2:

[0121] This embodiment provides a device for constructing a heavy-haul railway locomotive operation organization scheme, the device comprising:

[0122] The acquisition module is used to acquire railway transport capacity data and railway transport demand parameters;

[0123] The first construction module is used to construct, based on the railway transportation demand parameters and the railway transportation capacity data, to obtain the train task structure;

[0124] The second construction module is used to construct a multi-layer spatiotemporal network based on the train task structure, train operation rules and locomotive operation rules. The train operation rules include at least the minimum train tracking interval, and the locomotive operation rules include at least the upper limit of the locomotive's single continuous traction mileage.

[0125] To clarify the specific method for obtaining the second building block, the following are details:

[0126] The acquisition unit is used to acquire the station set, the section line set, and the train time node set;

[0127] The time node unit is used to input the station set and the section line set into the topology network based on the train task structure to obtain the train physical topology network;

[0128] Discrete unit, used to perform planning period discretization on the set of time nodes to obtain a discrete set of time nodes;

[0129] The network unit is used to construct the network based on the physical topology of the train and locomotive, the train operation rules, the locomotive operation rules, and the set of discrete time nodes, to obtain the train and locomotive cooperative operation network.

[0130] To clarify the specific methods for obtaining network units, the following are included:

[0131] The first construction subunit is used to construct, based on the train physical topology network, the set of discrete time nodes, and the train spatiotemporal state nodes and train spatiotemporal flow arcs in the train operation rules, to obtain the train service layer network.

[0132] The second construction subunit is used to construct, based on the locomotive physical topology network, the set of discrete time nodes, and the locomotive operation spatiotemporal nodes and locomotive operation arcs in the locomotive operation rules, to obtain the locomotive operation layer network.

[0133] The third construction subunit is used to construct a train-locomotive cooperative operation network based on the train service layer network and the locomotive operation layer network.

[0134] The coupling construction unit is used to construct the train-machine cooperative operation network in a spatiotemporal coupling manner based on the upstream and downstream of the hub station through the power matching relationship, so as to obtain a multi-layer spatiotemporal network.

[0135] The third construction module is used to construct a locomotive route utilization scheme based on the multi-layer spatiotemporal network and the preset heavy-load transportation constraint system, so as to obtain a locomotive route utilization optimization model.

[0136] To clarify the specific methods for obtaining the third building block, the following are included:

[0137] A network decision-making unit is used to construct a networked decision-making model based on the nodes and arcs in the multi-layer spatiotemporal network and the train task structure.

[0138] The operating cost unit is used to construct a comprehensive objective function by minimizing the operating cost based on the networked decision model, with the dual objective functions of minimizing the number of locomotives used and minimizing the total travel time of trains in the loaded direction.

[0139] The constraint system unit is used to construct the heavy-haul transportation constraint system based on the operational feasibility constraints of trains, the locomotive routing coupling constraints of hub stations, and the preset arrival and departure line capacity constraints and traffic safety constraints.

[0140] An optimization construction unit is used to optimize and construct locomotive route utilization schemes based on the comprehensive objective function and the heavy-haul transportation constraint system, thereby obtaining a locomotive route utilization optimization model.

[0141] The iterative solution module is used to iteratively solve the locomotive route optimization model according to the tabu search algorithm to obtain the locomotive operation organization scheme.

[0142] To clarify the specific methods for obtaining the iterative solution module, the following are included:

[0143] The priority assignment unit is used to prioritize the assignment of available locomotives in the locomotive route utilization optimization model according to the greedy heuristic rule in the tabu search algorithm, and generate an initial locomotive route chain set.

[0144] The neighborhood call unit is used to perform neighborhood calls through the neighborhood search operator in locomotive routing during the iterative search process of the tabu search algorithm to generate a candidate solution set;

[0145] The constraint unit is used to construct locomotive identifiers, train identifiers, and operating modes from the candidate solution set to obtain taboo features;

[0146] The constraint unit is used to perform backtracking of restricted candidate solutions based on the initial locomotive routing chain set, combined with the candidate solution set and the taboo features, and select the current optimal solution.

[0147] The judgment unit is used for the iterative optimization process: based on the candidate solution set, the current optimal solution is judged, and when a candidate solution with taboo characteristics is better than the optimal solution, the amnesty criterion is triggered and the current optimal solution is updated to obtain the next optimal solution;

[0148] The iteration unit is used to continue the iterative optimization process for the next optimal solution until the preset maximum number of iterations is reached or the convergence condition is met, at which point the iteration terminates and outputs the locomotive operation organization scheme.

[0149] It should be noted that the specific manner in which each module performs its operation in the apparatus described in the above embodiments has been described in detail in the embodiments of the method, and will not be elaborated here.

[0150] Example 3:

[0151] Corresponding to the above method embodiments, this embodiment also provides a heavy-haul railway locomotive operation organization scheme construction device. The heavy-haul railway locomotive operation organization scheme construction device described below and the heavy-haul railway locomotive operation organization scheme construction method described above can be referred to in correspondence.

[0152] Figure 3 This is a block diagram illustrating a heavy-haul railway locomotive operation organization scheme construction device 800 according to an exemplary embodiment. For example... Figure 3 As shown, the heavy-haul railway locomotive operation organization scheme construction device 800 may include: a processor 801 and a memory 802. The heavy-haul railway locomotive operation organization scheme construction device 800 may also include one or more of the following: a multimedia component 803, an I / O interface 804, and a communication component 805.

[0153] The processor 801 controls the overall operation of the heavy-haul railway locomotive operation organization scheme construction device 800 to complete all or part of the steps in the aforementioned heavy-haul railway locomotive operation organization scheme construction method. The memory 802 stores various types of data to support the operation of the heavy-haul railway locomotive operation organization scheme construction device 800. This data may include, for example, instructions for any application or method operating on the heavy-haul railway locomotive operation organization scheme construction device 800, as well as application-related data, such as contact data, sent and received messages, images, audio, video, etc. The memory 802 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and audio components. The screen may be, for example, a touchscreen. The I / O interface 804 provides an interface between the processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. The communication component 805 is used for wired or wireless communication between the heavy-haul railway locomotive operation organization scheme construction device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or one or more of them, therefore the corresponding communication component 805 may include: a Wi-Fi module, a Bluetooth module, an NFC module.

[0154] In an exemplary embodiment, the heavy-haul railway locomotive operation organization scheme construction device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the above-described heavy-haul railway locomotive operation organization scheme construction method.

[0155] Example 4:

[0156] Corresponding to the above method embodiments, this embodiment also provides a medium. The medium described below can be referred to in conjunction with the method for constructing a heavy-haul railway locomotive operation organization scheme described above.

[0157] A medium storing a computer program, which, when executed by a processor, implements the steps of the method for constructing a heavy-haul railway locomotive operation organization scheme as described in the above method embodiments.

[0158] The medium can specifically be any medium capable of storing program code, such as a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0159] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0160] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for constructing a locomotive operation organization scheme for heavy-haul railways, characterized in that, include: Obtain railway transport capacity data and railway transport demand parameters; The train task structure is constructed based on the railway transport demand parameters and the railway transport capacity data. Based on the train mission structure, train operation rules and locomotive operation rules, a multi-layered spatiotemporal network is constructed, wherein the train operation rules include at least the minimum train tracking interval, and the locomotive operation rules include at least the upper limit of the locomotive's single continuous traction mileage. Based on the multi-layered spatiotemporal network and the preset heavy-load transportation constraint system, a locomotive route utilization scheme is constructed to obtain a locomotive route utilization optimization model; The locomotive routing optimization model is iteratively solved using the tabu search algorithm to obtain the locomotive operation organization scheme.

2. The method for constructing a heavy-haul railway locomotive operation organization scheme according to claim 1, characterized in that, Based on the aforementioned train task structure, train operation rules, and locomotive operation rules, a multi-layered spatiotemporal network is constructed, including: Obtain the station set, the section route set, and the train time node set; Based on the train task structure, the station set and the section line set are input into the topology network to obtain the train physical topology network; The time node set is discretized by planning period to obtain a discrete time node set; Based on the physical topology of the locomotive and train, the train operation rules, the locomotive operation rules, and the set of discrete time nodes, an operation network is constructed to obtain a locomotive-train cooperative operation network; Based on the upstream and downstream of the hub station, the train-machine cooperative operation network is constructed by spatiotemporal coupling through power matching relationship, resulting in a multi-layer spatiotemporal network.

3. The method for constructing a heavy-haul railway locomotive operation organization scheme according to claim 2, characterized in that, Based on the physical topology of the locomotive and train system, the train operation rules, the locomotive operation rules, and the set of discrete time nodes, an operational network is constructed to obtain a locomotive-train cooperative operation network, including: The train service layer network is constructed based on the train physical topology network, the set of discrete time nodes, and the train spatiotemporal state nodes and train spatiotemporal flow arcs in the train operation rules. The locomotive operation layer network is constructed based on the physical topology network of the locomotive train, the set of discrete time nodes, and the locomotive operation spatiotemporal nodes and locomotive operation arcs in the locomotive operation rules. A train-train cooperative operation network is constructed based on the train service layer network and the locomotive operation layer network.

4. The method for constructing a heavy-haul railway locomotive operation organization scheme according to claim 1, characterized in that, Based on the aforementioned multi-layered spatiotemporal network and the preset heavy-haul transportation constraint system, a locomotive route utilization scheme is constructed, resulting in a locomotive route utilization optimization model, including: A networked decision model is obtained by constructing a networked decision model based on the nodes and arcs in the multi-layered spatiotemporal network and the train task structure. Based on the networked decision-making model, the operating cost is minimized by taking the minimum number of locomotives used and the shortest total travel time of trains in the loaded direction as the dual objective functions, and a comprehensive objective function is obtained. The heavy-haul transportation constraint system is constructed based on the operational feasibility constraints of trains, the locomotive routing coupling constraints of hub stations, and the preset arrival and departure line capacity constraints and traffic safety constraints. Based on the comprehensive objective function and the heavy-haul transportation constraint system, the locomotive route utilization scheme is optimized and constructed to obtain the locomotive route utilization optimization model.

5. The method for constructing a heavy-haul railway locomotive operation organization scheme according to claim 1, characterized in that, The locomotive routing optimization model is iteratively solved using the tabu search algorithm to obtain a locomotive operation organization scheme, including: Based on the greedy heuristic rule in the tabu search algorithm, the available locomotives in the locomotive route utilization optimization model are preferentially assigned to generate an initial locomotive route chain set. During the iterative search process of the tabu search algorithm, a neighborhood search operator in locomotive routing is used to perform neighborhood calls and generate a candidate solution set. The locomotive identifier, train identifier, and operation mode in the candidate solution set are constructed to obtain taboo features; Based on the initial locomotive routing chain set, and combined with the candidate solution set and the taboo features, a restricted candidate solution backtracking is performed to select the current optimal solution; Iterative optimization process: Based on the candidate solution set, the current optimal solution is judged. When a candidate solution with taboo characteristics is better than the optimal solution, the amnesty criterion is triggered and the current optimal solution is updated to obtain the next optimal solution. The iterative optimization process continues for the next optimal solution until the preset maximum number of iterations is reached or the convergence condition is met, at which point the iteration terminates and the locomotive operation organization scheme is output.

6. A system for constructing a heavy-haul railway locomotive operation organization scheme, characterized in that, include: The acquisition module is used to acquire railway transport capacity data and railway transport demand parameters; The first construction module is used to construct, based on the railway transportation demand parameters and the railway transportation capacity data, to obtain the train task structure; The second construction module is used to construct a multi-layer spatiotemporal network based on the train task structure, train operation rules and locomotive operation rules. The train operation rules include at least the minimum train tracking interval, and the locomotive operation rules include at least the upper limit of the locomotive's single continuous traction mileage. The third construction module is used to construct a locomotive route utilization scheme based on the multi-layer spatiotemporal network and the preset heavy-load transportation constraint system, so as to obtain a locomotive route utilization optimization model. The iterative solution module is used to iteratively solve the locomotive route optimization model according to the tabu search algorithm to obtain the locomotive operation organization scheme.

7. The heavy-haul railway locomotive operation organization scheme construction system according to claim 6, characterized in that, The second building module includes: The acquisition unit is used to acquire the station set, the section line set, and the train time node set; The time node unit is used to input the station set and the section line set into the topology network based on the train task structure to obtain the train physical topology network; Discrete unit, used to perform planning period discretization on the set of time nodes to obtain a discrete set of time nodes; The network unit is used to construct the network based on the physical topology of the train and locomotive, the train operation rules, the locomotive operation rules, and the set of discrete time nodes, to obtain the train and locomotive cooperative operation network. The coupling construction unit is used to construct the train-machine cooperative operation network in a spatiotemporal coupling manner based on the upstream and downstream of the hub station through the power matching relationship, so as to obtain a multi-layer spatiotemporal network.

8. The heavy-haul railway locomotive operation organization scheme construction system according to claim 7, characterized in that, The operating network unit includes: The first construction subunit is used to construct, based on the train physical topology network, the set of discrete time nodes, and the train spatiotemporal state nodes and train spatiotemporal flow arcs in the train operation rules, to obtain the train service layer network. The second construction subunit is used to construct, based on the locomotive physical topology network, the set of discrete time nodes, and the locomotive operation spatiotemporal nodes and locomotive operation arcs in the locomotive operation rules, to obtain the locomotive operation layer network. The third construction subunit is used to construct a train-locomotive cooperative operation network based on the train service layer network and the locomotive operation layer network.

9. The heavy-haul railway locomotive operation organization scheme construction system according to claim 6, characterized in that, The third building module includes: A network decision-making unit is used to construct a networked decision-making model based on the nodes and arcs in the multi-layer spatiotemporal network and the train task structure. The operating cost unit is used to construct a comprehensive objective function by minimizing the operating cost based on the networked decision model, with the dual objective functions of minimizing the number of locomotives used and minimizing the total travel time of trains in the loaded direction. The constraint system unit is used to construct the heavy-haul transportation constraint system based on the operational feasibility constraints of trains, the locomotive routing coupling constraints of hub stations, and the preset arrival and departure line capacity constraints and traffic safety constraints. An optimization construction unit is used to optimize and construct locomotive route utilization schemes based on the comprehensive objective function and the heavy-haul transportation constraint system, thereby obtaining a locomotive route utilization optimization model.

10. The heavy-haul railway locomotive operation organization scheme construction system according to claim 6, characterized in that, The iterative solution module includes: The priority assignment unit is used to prioritize the assignment of available locomotives in the locomotive route utilization optimization model according to the greedy heuristic rule in the tabu search algorithm, and generate an initial locomotive route chain set. The neighborhood call unit is used to perform neighborhood calls through the neighborhood search operator in locomotive routing during the iterative search process of the tabu search algorithm to generate a candidate solution set; The constraint unit is used to construct locomotive identifiers, train identifiers, and operating modes from the candidate solution set to obtain taboo features; The constraint unit is used to perform backtracking of restricted candidate solutions based on the initial locomotive routing chain set, combined with the candidate solution set and the taboo features, and select the current optimal solution. The judgment unit is used for the iterative optimization process: based on the candidate solution set, the current optimal solution is judged, and when a candidate solution with taboo characteristics is better than the optimal solution, the amnesty criterion is triggered and the current optimal solution is updated to obtain the next optimal solution; The iteration unit is used to continue the iterative optimization process for the next optimal solution until the preset maximum number of iterations is reached or the convergence condition is met, at which point the iteration terminates and outputs the locomotive operation organization scheme.

Images