Optimization method and system for quickly solving motor train set route plan

Abstract

The application relates to the technical field of computer application, in particular to an optimization method for quickly solving a motor train unit interchange plan. The method comprises the following steps: obtaining real-time state data of a motor train unit; constructing a time-space axis network of the motor train unit interchange plan based on the real-time state data of the motor train unit; establishing an original model of the motor train unit interchange plan based on actual state data of the motor train unit and the time-space axis network; the actual state data comprises real-time state data and maintenance state data of the motor train unit; establishing an aggregated optimization model based on the real-time state data of the motor train unit and the original model of the motor train unit interchange plan, the aggregated optimization model is based on the real-time state data of the motor train unit to obtain a solving result; constructing a disaggregated solving model based on the solving result of the aggregated model, the disaggregated solving model combines the aggregated result with the obtained actual state data to generate a specific real-name interchange plan.

Description

Technical Field

[0001] This invention relates to the field of computer application technology, and in particular to an optimization method and system for rapidly solving high-speed train route plans. Background Technology

[0002] The preparation of EMU (Electric Multiple Unit) route planning is a core component of high-speed railway operation organization. Its solution efficiency directly determines the timeliness and practicality of the plan, thus affecting the response speed and quality of operational adjustments. With the continuous expansion of the high-speed railway network and the increasing train frequency, the search space for route planning is experiencing explosive growth, posing a severe challenge to traditional methods in terms of solution speed. Furthermore, existing technologies cannot obtain real-time location information and mileage data of EMUs, resulting in route plans lacking specificity and practicality, and failing to achieve personalized route arrangements based on the actual status of the EMUs. Currently, existing technologies for EMU route planning mainly rely on manual experience. Conventional manual planning methods are labor-intensive and inefficient, and can no longer meet the high-precision and high-efficiency requirements of large-scale railway networks. More importantly, the inability of existing technologies to obtain real-time location information and mileage data of EMUs means that the prepared route plans cannot consider the actual status of the EMUs, easily leading to practical problems such as EMU location mismatch and mileage exceeding limits.

[0003] Most existing technologies focus on constructing precise mathematical models to achieve theoretically optimal solutions, such as integer programming, multi-commodity network flow, or dynamic programming models, and rely on commercial solvers or decomposition algorithms for solving. While these methods have good theoretical properties in linear scenarios, their computation time increases dramatically with the scale of the problem, sometimes even failing to obtain a feasible solution within an acceptable timeframe, severely limiting their application in real-world complex road networks and high-density operation diagrams. Although some studies have attempted to improve solution efficiency using heuristic rules or metaheuristic algorithms, they still suffer from slow convergence speed, unstable solution quality, or getting trapped in local optima when dealing with ultra-large-scale problems or complex, sudden scenarios. Furthermore, existing methods generally lack efficient search strategies and pruning mechanisms designed for the special structure of high-speed rail routes, making it difficult to achieve a balance between solution speed and solution quality.

[0004] The disadvantages of the existing EMU route planning method mentioned above include:

[0005] Currently, the existing technology for manually compiling EMU (Electric Multiple Unit) route plans suffers from problems such as tight deadlines, heavy workload, low efficiency, and insufficient accuracy. Furthermore, this method is constrained by factors such as the experience and professional competence of the compilers, making it difficult to meet the needs of railway operation and development. Summary of the Invention

[0006] To address the technical problems existing in the prior art, the present invention provides an optimization method for quickly solving the EMU (Electric Multiple Unit) route plan.

[0007] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0008] In a first aspect, in one embodiment of the present invention, an optimization method for rapidly solving the EMU (Electric Multiple Unit) route plan is provided, the method comprising the following steps:

[0009] Obtain real-time status data of the high-speed train;

[0010] Based on real-time status data of EMU trains, a spatiotemporal axis network for EMU train route planning is constructed.

[0011] Based on the actual status data and spatiotemporal axis network of the EMU, an original model of the EMU route plan is established; the actual status data includes the real-time status data and maintenance status data of the EMU.

[0012] Based on the real-time status data of the EMU and the original EMU route plan model, an aggregate optimization model is established. The aggregate optimization model is based on the real-time status data of the EMU to obtain the solution results.

[0013] Based on the results of the aggregation model, a deaggregation solution model is constructed. The deaggregation solution model combines the aggregation results with the acquired actual state data to generate a specific real-name route plan.

[0014] As a further aspect of the present invention, the real-time status data includes the actual location information and cumulative mileage data of each EMU; the actual location information includes the station, operating section or EMU depot; the cumulative mileage data includes the total mileage, daily mileage and mileage within the maintenance cycle.

[0015] As a further aspect of the present invention, the real-time status data of the EMU is obtained by collecting data deployed in the EMU status monitoring system.

[0016] As a further aspect of the present invention, the step of constructing a spatiotemporal axis network for EMU route planning based on real-time EMU status data includes:

[0017] Based on the actual location information of the EMU, a corresponding initial node is constructed for each EMU within the spatiotemporal axis network, and the time, space and status attributes of the node are set; the EMU depot, station or operating section where the EMU is located is determined by database query, and then the corresponding virtual start node and end node are established.

[0018] Based on the cumulative mileage data, a maintenance status judgment algorithm is used to compare the cumulative mileage with the maintenance threshold to determine the maintenance status of each EMU. For EMUs that are close to the maintenance mileage, their long-distance operation tasks are restricted when building the network, and the corresponding arc capacity is adjusted. For EMUs that have exceeded the maintenance mileage, they are removed from the set of available EMUs and no network nodes are created for them. At the same time, according to the preset maintenance plan, an available operating section and time window are set for each EMU.

[0019] Based on the processed EMU status data, a network generation algorithm is used to abstract stations in the train time map into nodes and feasible connection relationships between stations into arcs, thereby constructing an axis network based on the actual status of the EMU for a preset time period.

[0020] As a further aspect of the present invention, an original model of the EMU route plan is established based on the actual status data of the EMU; the actual status data includes real-time status data and maintenance status data of the EMU, including:

[0021] The pre-acquired vehicle candidate set, node set, and arc set are used as model parameters;

[0022] Based on actual location information, initial position constraints are set for each EMU to ensure that the EMU starts executing the route plan from its actual location; maintenance constraints are set based on cumulative mileage data to ensure that the EMU does not exceed the mileage limit before maintenance; and timetable constraints, station capacity constraints, and flow balance constraints are set based on actual timetable data.

[0023] As a further aspect of the present invention, an aggregated optimization model is established based on the real-time status data of the EMU and the original EMU route plan model, including:

[0024] The acquired real-time status data of the EMUs are aggregated to combine the location and mileage data of individual EMUs into network-wide resource allocation information. A data aggregation algorithm is used to aggregate the vehicle-level variables in the original model into arc-level flow variables, reducing model complexity. The distribution status of EMUs across the network is determined based on GPS positioning data, and the maintenance resource constraints of the entire network are determined based on mileage data.

[0025] Convert the original model into an aggregate model.

[0026] As a further aspect of the present invention, the objective function of the aggregation model is based on actual operating cost data, including vehicle usage costs, operating costs, and maintenance costs.

[0027] As a further aspect of the present invention, the constraints of the aggregation model are based on actual train schedule data and EMU status data, including train schedule constraints, station capacity constraints, and flow balance constraints.

[0028] As a further aspect of the present invention, the solution model combines the aggregation results with the acquired actual state data to generate a specific real-name route plan, including:

[0029] Based on the aggregation results and actual status data, the aggregation results are matched with specific EMU train sets through a data matching algorithm to determine the available operating range of each EMU train set.

[0030] Based on the aggregation results and actual status data, a specific operating path is generated for each EMU (Electric Multiple Unit).

[0031] A path optimization algorithm is used to determine the optimal starting position by combining the current location information with the cumulative mileage data to ensure that the maintenance limit is not exceeded.

[0032] Generate a real-name route plan that includes specific train set numbers, running times, and running routes.

[0033] In a first aspect, in one embodiment of the present invention, an optimization system for rapidly solving EMU (Electric Multiple Unit) route plans is provided, the system comprising:

[0034] The data acquisition unit is used to acquire real-time status data of the EMU (Electric Multiple Unit).

[0035] The spatiotemporal axis network construction unit is used to construct the spatiotemporal axis network of the EMU route plan based on the real-time status data of the EMU.

[0036] The original model building unit is used to establish an original model of the EMU route plan based on the actual state data and spatiotemporal axis network of the EMU. The actual state data includes real-time state data and maintenance state data of the EMU.

[0037] The aggregation optimization model construction unit is used to build an aggregation optimization model based on the real-time status data of the EMU and the original EMU route plan model. The aggregation optimization model is based on the real-time status data of the EMU to obtain the solution results.

[0038] The de-aggregation solution model construction unit is used to construct a de-aggregation solution model based on the solution results of the aggregation model. The de-aggregation solution model combines the aggregation results with the acquired actual state data to generate a specific real-name route plan.

[0039] The technical solution provided by this invention has the following beneficial effects:

[0040] (1) This invention employs a two-stage optimization method that combines the construction of an aggregation optimization model with a deaggregation solution model, decomposing the originally complex EMU route planning problem into two levels for solution. In the aggregation stage, the flow of the entire network arc segment is quickly determined; in the deaggregation stage, a refined route is generated one by one based on this. This method effectively avoids the problem of excessively long solution time caused by combinatorial explosion in traditional methods, greatly improves the solution speed, and can adapt to large-scale, high-density railway timetable scenarios.

[0041] (2) Under the premise of ensuring the scientificity and rationality of the EMU route plan, this invention uses an aggregation model to initially allocate global resources, and then uses a deaggregation model to carry out fine-tuning of the routes. This approach avoids the problem of heuristic algorithms getting trapped in local optima, and also makes up for the shortcomings of the precise model in quickly solving large-scale problems, thus achieving an effective balance between solution efficiency and solution quality.

[0042] (3) In the spatiotemporal axis network construction stage of the present invention, the actual position and mileage status of the EMU are fully considered, and personalized route planning based on the actual status of the EMU is realized, avoiding practical problems such as EMU position mismatch and mileage exceeding limit, and improving the practicality and operability of the route plan.

[0043] (4) The optimization method provided by the present invention has high computational efficiency and strong adaptability, and can provide timely and reliable decision support for the operation and management of EMU vehicles, daily scheduling and adjustment and resource allocation. It helps to improve the flexibility of high-speed railway operation organization and the ability to respond to emergencies, and has broad engineering application value.

[0044] These or other aspects of the invention will become more apparent from the following description of embodiments. It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating an embodiment of the optimization method for rapidly solving the EMU (Electric Multiple Unit) route plan according to the present invention.

[0047] Figure 2A schematic diagram of the spatiotemporal axis network used in the decomposition and reconnection operation in a method for rapidly solving the EMU route planning optimization according to an embodiment of the present invention.

[0048] Figure 3 This is a structural diagram of an optimization system for rapidly solving EMU (Electric Multiple Unit) route planning according to an embodiment of the present invention. Detailed Implementation

[0049] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0051] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0052] Specifically, the embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0053] Please see Figure 1 , Figure 1 This is a flowchart of an optimization method for quickly solving the EMU (Electric Multiple Unit) route plan, provided by an embodiment of the present invention. Figure 1 As shown, the optimization method for quickly solving the EMU route plan includes steps S10 to S50.

[0054] S10. Obtain real-time status data of the EMU.

[0055] In embodiments of the present invention, real-time status data includes the actual location information and cumulative mileage data of each train set.

[0056] In embodiments of the present invention, the current location information includes the station, operating section, or EMU depot. Based on the actual location information of the EMU, the initial position of each EMU at the start of the planning process is determined.

[0057] In embodiments of the present invention, the cumulative mileage data includes total mileage, daily mileage, and mileage within a maintenance cycle. Based on the cumulative mileage data of the EMU (Electric Multiple Unit), the maintenance status and mileage constraints for each EMU are determined.

[0058] In an embodiment of the present invention, the real-time status data of the EMU can be obtained by collecting data deployed in the EMU status monitoring system.

[0059] In an embodiment of the present invention, the EMU status monitoring system includes a GPS positioning device and a mileage recording device.

[0060] In an embodiment of the present invention, the GPS positioning device includes a GPS receiving module, a data processing module, and a data transmission module. The GPS receiving module receives satellite signals and calculates the precise location information of the train, including latitude and longitude coordinates, altitude, and motion status. The data processing module processes and stores the GPS data. The data transmission module transmits the location information to a ground data processing center in real time.

[0061] In an embodiment of the present invention, the mileage recording device includes a mileage sensor, a data storage module, and a communication module. The mileage sensor is used to record the cumulative mileage, operating time, and maintenance history data of the train. The data storage module is used to store historical mileage data. The communication module is used to transmit the mileage data to a ground data processing center in real time.

[0062] The mileage sensor includes a speed sensor and a mileage calculation unit. The speed sensor detects wheel rotation with an accuracy of 0.1 kilometers; the mileage calculation unit calculates the cumulative mileage based on the speed data and the wheel circumference.

[0063] This invention relates to a data acquisition and transmission system, which includes an onboard data acquisition module, a wireless communication module, and a ground data processing center. The onboard data acquisition module is responsible for acquiring and preprocessing the EMU's status data. The wireless communication module uses GSM-R or 4G / 5G communication technology to achieve real-time transmission of the EMU's status data. The ground data processing center is responsible for receiving, storing, and processing all the EMU's status data.

[0064] The vehicle-mounted data acquisition module integrates data interfaces for GPS positioning and mileage recording devices; the data preprocessing module performs filtering of GPS data and anomaly detection for mileage data; the wireless communication module uses mobile communication technology and is equipped with an antenna to ensure communication stability in high-speed operation and tunnel environments; the data compression module compresses and transmits data; and the ground data processing center, including a database server, application server, and storage system, adopts a distributed architecture to support real-time data processing and storage.

[0065] S20. Based on real-time status data of EMU trains, construct a spatiotemporal axis network for EMU train route planning.

[0066] like Figure 2 As shown, in an embodiment of the present invention, step S20, constructing a spatiotemporal axis network for EMU route planning based on real-time EMU status data, includes:

[0067] Based on the train timetable, EMU information, station information, and acquired EMU actual status data, a spatiotemporal axis network is established through the network construction module of the ground data processing center, denoted as... .

[0068] In an embodiment of the present invention, the step of establishing a spatiotemporal axis network through the network construction module of the ground data processing center based on the train timetable, EMU information, station information, and acquired actual EMU status data includes:

[0069] Based on the actual location information of the EMU, a corresponding initial node is created for each EMU in the spatiotemporal axis network, and the time, space and status attributes of the node are set; the EMU depot, station or operating section where the EMU is located is determined by database query, and the corresponding virtual start node and end node are established.

[0070] Specifically, the location data from the vehicle-mounted GPS positioning device can be received through the ground data processing center, and the GPS coordinates can be matched with the railway network topology using a location matching algorithm to determine the precise location of each EMU at the start of the planning process.

[0071] In an embodiment of the present invention, based on the actual location information of the EMU (Electric Multiple Unit), a corresponding initial node is created for each EMU in the spatiotemporal axis network, and the node's time, space, and state attributes are set; the EMU's depot, station, or operating section is determined through database queries, and corresponding virtual start and end nodes are established, including:

[0072] for middle, All have The three attributes represent time, location, and type, respectively. The point types include source point and station node, explained in detail below:

[0073] Source point: Represents the virtual start and end points of the network, denoted as , ... and Among them, for ; , .

[0074] Station Nodes: For all train services within the consideration scope, a station node is established for both the origin and destination. The origins and destinations of all operating lines form sets. and Due to actual production requirements, high-speed trains only depart from certain specific stations and return to those stations after completing their assigned tasks. These specific stations are called high-speed train depots. To distinguish the high-speed train depot nodes from the station nodes, the set of high-speed train depot nodes is denoted as […]. To ensure that high-speed trains can depart from and return to a depot, the original one-day station nodes have been extended to two days. The train number nodes for the second day are copied from the first day's nodes, with the station's time increased by 1440 minutes. All other attributes remain the same as the first day's nodes. Specifically... It has attributes , respectively, represent the train number, the station to which it belongs, and the time to which it belongs.

[0075] To distinguish the station nodes for the two days, the sets of starting and ending points of the operating lines on the first day are respectively denoted as... and The starting and ending points of the route on the second day are denoted as follows: and .

[0076] Finally, the set of all nodes is denoted as .

[0077] Based on the cumulative mileage data, a maintenance status judgment algorithm is used to compare the cumulative mileage with the maintenance threshold to determine the maintenance status of each EMU. For EMUs that are close to the maintenance mileage, their long-distance operation tasks are restricted when building the network, and the corresponding arc capacity is adjusted. For EMUs that have exceeded the maintenance mileage, they are excluded from the set of available EMUs and no network nodes are created for them. And according to the preset maintenance plan, the available operating range and time window are set for each EMU.

[0078] In an embodiment of the present invention, the maintenance status of each train set is determined by comparing the cumulative mileage with a maintenance threshold based on the cumulative mileage data using a maintenance status judgment algorithm; for train sets approaching their maintenance mileage, their long-distance operation tasks are restricted during network construction, and the corresponding arc capacity is adjusted; for train sets exceeding their maintenance mileage, they are excluded from the set of available train sets, and no network nodes are created for them; and according to a preset maintenance plan, available operating intervals and time windows are set for each train set, including:

[0079] Based on the connections between the nodes described above, arcs are constructed in the network. For middle, All have , , , , The six attributes represent the arc start time, arc end time, arc start station, arc end station, arc type, grouping type, and arc capacity. Arc types include virtual arcs, demand arcs, connecting arcs, disjointing arcs, reconnecting arcs, cross-day waiting arcs, and virtual direct-connection arcs. The establishment rules for each arc are as follows, and all must be satisfied during establishment: , .

[0080] Virtual arc: An arc connecting the source point and the depot node, including a virtual start arc and a virtual end arc. The creation method is as follows: [The text abruptly ends here, so the translation stops.] Establish a virtual starting arc The set of virtual starting arcs is denoted as Similarly, for Establish a virtual endpoint arc The set of virtual endpoint arcs is denoted as .

[0081] Demand arc: The arc connecting the start and end points of the running line. The method for establishing it is as follows: If satisfied Then establish a demand arc ,like "Single compilation" ;like "Reconnection" The set of demand arcs is denoted as .

[0082] Connecting arc: An arc that connects the nodes of the running line. The method for establishing it is as follows: For... , If satisfied , And for , All have or Then establish a connecting arc The arc begins at time The arc terminates at time The starting station of the arc is equal to the ending station of the arc. , Let the maximum number of trains that can stop at a station be denoted as the set of connecting axes and arcs. .

[0083] Uncoupling Arc: An arc used for trainset uncoupling operations. Since trainset uncoupling operations are usually only performed at the train depot, to reduce network size, uncoupling arcs are only generated at the train depot node. The establishment method is as follows: For... , If satisfied , And for , All have or Then establish the uncoding arc The arc begins at time The arc terminates at time The starting station of the arc is equal to the ending station of the arc. , =“Decompiled Arc” The maximum number of trains that can stop at a station is denoted by the unwrapped arc set. .

[0084] Multiple-unit arc: An arc used for multiple-unit operation of EMU trains. The construction method is similar to that of uncoupling arc. = "concurrent arcs", the set of concurrent arcs is denoted as .

[0085] Cross-day waiting arc: An arc connecting the last time point of the first day to the first time point of the second day for each station. The construction method is as follows: [The text abruptly ends here, likely due to an incomplete sentence or a formatting error.] , If satisfied And for , , All have or Then establish a cross-day waiting arc The arc begins at time The arc terminates at time The starting station of the arc is equal to the ending station of the arc. , Let be the maximum number of trains that can stop at a station, and let the set of waiting arcs spanning multiple days be denoted as . .

[0086] Virtual direct-connection arcs: The starting point is a virtual starting point, and the ending point is a virtual ending point; these are used to indicate that the vehicle is not in use. The set of virtual direct-connection arcs is denoted as... .

[0087] Finally, the set of all arcs is denoted as .

[0088] Based on the processed EMU status data, the network generation algorithm of the ground data processing center abstracts stations in the train time map into nodes and feasible connections between stations into arcs, constructing an axis network for a preset time period based on the actual status of the EMU, denoted as . Each node in the axis network contains time and space information obtained from the GPS device, and each arc takes into account maintenance constraints obtained from the mileage recording device.

[0089] The preset time period can be two days, three days, or four days.

[0090] The processed EMU status data includes the EMU's departure location, arrival location, departure time, arrival time, running time, mileage, and formation status.

[0091] S30. Based on the actual status data and spatiotemporal axis network of the EMU, establish the original model of the EMU route plan; the actual status data includes the real-time status data and maintenance status data of the EMU.

[0092] In an embodiment of the present invention, S30, an original model of the EMU route plan is established based on the actual status data of the EMU; the actual status data includes real-time status data and maintenance status data of the EMU, including:

[0093] Based on the constructed spatiotemporal axis network, the original model of the EMU route plan is established through the model building module of the ground data processing center. This model takes the acquired GPS positioning data and mileage data as input parameters to generate an executable route plan.

[0094] The establishment of the original model for the EMU route plan based on the actual status data of the EMU includes:

[0095] The actual status data of the EMUs are read from the database by the ground data processing center, including the GPS location information, cumulative mileage, and maintenance status of each EMU. These actual physical data are used as model parameters, including the vehicle candidate set K (based on the actual available EMUs), the node set N (based on the actual location determined by GPS positioning), and the arc set A (based on the actual operation diagram and time constraints).

[0096] Based on actual location information, initial position constraints are set for each EMU to ensure that the EMU starts executing the route plan from its actual location; maintenance constraints are set based on cumulative mileage data to ensure that the EMU does not exceed the mileage limit before maintenance; and timetable constraints, station capacity constraints, and flow balance constraints are set based on actual timetable data.

[0097] The actual train operation schedule data can be obtained from the train operation schedule at the dispatching and command center. This data can include datasets such as train numbers, stations, arrival and departure times, and train formation requirements, used for network construction and constraint building.

[0098] The steps to construct the original model of the EMU route plan are as follows:

[0099] (1) Define the following parameters and variables:

[0100] (2)

[0101] (3) Objective function of the original model of EMU route planning

[0102] The objective function of the original model is to minimize the number of vehicles in use and maximize service coverage. The combined expression of the objective function is as follows:

[0103]

[0104] (4) Constraints of the original model of EMU route plan

[0105] 1) Run graph constraints

[0106] For any train number specified in the train timetable ,need Number of EMU trains serving:

[0107]

[0108] 2) Station capacity constraints

[0109] The total number of vehicles waiting and operating within the station must not exceed the station's maximum capacity.

[0110]

[0111] 3) Flow balance constraint

[0112] Each transport request can be served by a maximum of one vehicle:

[0113]

[0114]

[0115] 4) Constraints on the values ​​of decision variables

[0116] .

[0117] S40. Based on the real-time status data of the EMU and the original EMU route plan model, an aggregate optimization model is established. The aggregate optimization model is based on the real-time status data of the EMU to obtain the solution results.

[0118] In an embodiment of the present invention, step S40, establishing an aggregated optimization model based on real-time status data of the EMU and the original EMU route plan model, includes:

[0119] Based on the original model of the EMU route plan, an aggregation optimization model is established through the aggregation optimization module of the ground data processing center. This model takes the acquired real-time status data of the EMU as input and quickly determines the flow distribution of the entire network arc segment through aggregation processing to obtain the solution results.

[0120] In an embodiment of the present invention, an aggregated optimization model is established based on the real-time status data of the EMU and the original EMU route plan model, including:

[0121] The real-time status data of the EMUs acquired by the ground data processing center is aggregated and processed to combine the location and mileage data of individual EMUs into network-wide resource allocation information. A data aggregation algorithm is used to aggregate the vehicle-level variables in the original model into arc-level flow variables, reducing model complexity. The distribution status of EMUs across the network is determined based on GPS positioning data, and the maintenance resource constraints of the entire network are determined based on mileage data.

[0122] The original model is converted into an aggregated model through the model conversion module of the ground data processing center. The objective function of the aggregated model is based on actual operating cost data, including vehicle usage cost, operating cost and maintenance cost. The constraints are based on actual operation diagram data and EMU status data, including operation diagram constraints, station capacity constraints and flow balance constraints.

[0123] Constructing an aggregate optimization model involves the following steps:

[0124] (1) Define the following parameters and variables:

[0125]

[0126] (2) Objective function of the original model of EMU route planning

[0127] The objective function of the aggregation model is to minimize the number of vehicles in use and maximize service coverage. The comprehensive expression of the objective function is as follows:

[0128]

[0129] (3) Constraints of the original model of EMU route plan

[0130] 1) Run graph constraints

[0131] For any train number specified in the train timetable ,need Number of EMU trains serving:

[0132]

[0133] 2) Station capacity constraints

[0134] The total number of vehicles waiting and operating within the station must not exceed the station's maximum capacity.

[0135]

[0136] 3) Flow balance constraint

[0137] Except for the virtual start and end points, the inflow of each node must equal the outflow; the net outflow of the virtual start point equals the total number of vehicles, and the net inflow of the virtual end point equals the total number of vehicles.

[0138]

[0139]

[0140] 4) Constraints on the values ​​of decision variables

[0141]

[0142] S50. Based on the solution results of the aggregation model, construct a deaggregation solution model. The deaggregation solution model combines the aggregation results with the acquired actual state data to generate a specific real-name route plan.

[0143] In an embodiment of the present invention, S50, based on the solution results of the aggregation model, a deaggregation solution model is constructed. The deaggregation solution model combines the aggregation results with the acquired actual state data to generate a specific real-name route plan, including:

[0144] Based on the results of the aggregation model, a de-aggregation solution model is established through the de-aggregation solution module of the ground data processing center. This model combines the aggregation results with the acquired actual status data to generate a specific real-name route plan.

[0145] In an embodiment of the present invention, the solution model combines the aggregation results with the acquired actual state data to generate a specific real-name route plan, including:

[0146] The solution results of the aggregation model are received by the ground data processing center, including the flow distribution information of each arc segment; combined with the actual status data of the EMU, including the GPS location information, cumulative mileage, and maintenance status of each EMU; and the aggregation results are matched with the specific EMUs through the data matching algorithm to determine the available operating range of each EMU.

[0147] The maintenance status is obtained by collecting the cumulative mileage through the vehicle's onboard mileage recording device and determining whether the cumulative mileage exceeds a specified threshold. If the maintenance threshold is exceeded, maintenance must be performed.

[0148] The path generation algorithm at the ground data processing center generates a specific running path for each EMU based on the aggregation results and the actual status of the EMU. The path optimization algorithm, combined with GPS positioning data, determines the optimal starting position and combines mileage data to ensure that maintenance restrictions are not exceeded. A real-name route plan containing the specific EMU number, running time, and running path is generated, which can be directly transmitted to the EMU control system for execution.

[0149] Constructing the de-aggregation solution model includes the following steps:

[0150] (1) Define the following parameters and variables:

[0151]

[0152] (2) Objective function of the original model of EMU route planning

[0153] The objective function of the original model is to minimize the number of vehicles in use and maximize service coverage. The combined expression of the objective function is as follows:

[0154]

[0155] (3) Constraints of the original model of EMU route plan

[0156] 1) Arc capacity constraint

[0157] The usage of each arc cannot exceed the available capacity determined during the aggregation phase:

[0158]

[0159] 2) Flow balance constraint

[0160] Ensure that each vehicle starts from the virtual origin, maintains an inflow equal to an outflow at all intermediate nodes, and finally converges at the virtual destination to form a complete origin-end path:

[0161]

[0162]

[0163] 3) Constraints on the values ​​of decision variables

[0164] .

[0165] This invention discloses a rapid optimization method for solving EMU (Electric Multiple Unit) route plans based on EMU positioning and mileage records. By collecting real-time actual status information of EMUs, stations in the train timetable are abstracted as nodes, and feasible connections between stations are abstracted as arcs, constructing a two-day axis network. Based on this, an original model of the EMU route plan considering EMU location and mileage constraints is constructed, and a rapid solution method based on a two-stage aggregation and deaggregation approach is proposed: First, an aggregation optimization model is constructed with the objective of minimizing the total cost on all arcs in the network, determining the flow of each arc segment, i.e., the number of times each arc is used; then, based on the results of the aggregation solution, each route is solved one by one, minimizing the total cost of the selected arcs for that route, thereby obtaining a refined, real-name vehicle route plan. This invention achieves rapid solution of EMU (Electric Multiple Unit) route planning by the collaborative work of an aggregation optimization model and a deaggregation solution model: the aggregation optimization model first determines the flow allocation of each arc segment, and the deaggregation solution model generates a personalized route plan for each EMU based on the aggregation results and the actual status of the EMU, including the specific EMU number, running time, and running path. This route plan can be directly transmitted to the EMU control system for execution, thereby realizing personalized route plan optimization based on the actual status of the EMU. This solves the problem of route plan mismatch caused by the inability of traditional methods to obtain the EMU status in real time, significantly improves the solution speed, and ensures the practicality and operability of the route plan.

[0166] like Figure 3 As shown in the figure, this embodiment of the invention also provides an optimization system for quickly solving the EMU (Electric Multiple Unit) route plan, the system comprising:

[0167] The data acquisition unit is used to acquire real-time status data of the EMU (Electric Multiple Unit).

[0168] The spatiotemporal axis network construction unit is used to construct the spatiotemporal axis network of the EMU route plan based on the real-time status data of the EMU.

[0169] The original model building unit is used to establish the original model of the EMU route plan based on the actual state data and spatiotemporal axis network of the EMU. The actual state data includes the real-time state data and maintenance state data of the EMU.

[0170] The aggregation optimization model construction unit is used to build an aggregation optimization model based on the real-time status data of the EMU and the original EMU route plan model. The aggregation optimization model is based on the real-time status data of the EMU to obtain the solution results.

[0171] The de-aggregation solution model building unit is used to build a de-aggregation solution model based on the solution results of the aggregation model. The de-aggregation solution model combines the aggregation results with the acquired actual state data to generate a specific real-name route plan.

[0172] It should be understood that although the above description follows a certain order, these steps are not necessarily executed in that order. Unless otherwise expressly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, some steps in this embodiment may include multiple steps or multiple stages, which are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be performed alternately or in turn with other steps or at least a portion of the steps or stages in other steps.

[0173] It should be understood that, as used herein, the singular form "a" is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations of one or more of the associatedly listed items. The embodiment numbers disclosed above are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0174] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples. Within the framework of the invention, technical features of the above embodiments or different embodiments can be combined, and many other variations of different aspects of the invention exist, which are not provided in the details for the sake of brevity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the invention should be included within the protection scope of the invention.

Claims

1. A method for quickly solving the optimization of a train set route plan, characterized in that, The method includes: Obtain real-time status data of the high-speed train; Based on real-time status data of EMU trains, a spatiotemporal axis network for EMU train route planning is constructed. Based on the actual status data and spatiotemporal axis network of the EMU, an original model of the EMU route plan is established. The actual status data includes the real-time status data and maintenance status data of the EMU. Based on the real-time status data of the EMU and the original EMU route plan model, an aggregate optimization model is established. The aggregate optimization model is based on the real-time status data of the EMU to obtain the solution results. The steps for constructing the aggregation model are as follows: Define parameters and variables; The objective function one of the original model for the EMU route plan is constructed, and the comprehensive formula of objective function one is as follows: ， wherein, is an overall variable, arc (i, j) is used by how many vehicles; is a sufficiently large positive number; is a demand arc set; is a virtual origin arc set; The constraints of the original model of the EMU route plan are determined, including timetable constraints, station capacity constraints, flow balance constraints, and decision variable value constraints. The operation diagram constraint is corresponding to any train on the train operation diagram , need The number of motor trains: ， In the formula, is an arbitrary train on the train diagram; is the number of marshalling of train q, 1 for single marshalling and 2 for double marshalling. The station capacity constraint is that the total number of vehicles waiting and operating within the station cannot exceed the station's maximum capacity. ， wherein is an upper bound on the capacity of arc (i, j), is a set of connecting arcs; is a set of break-of-journey arcs; is a set of re-connection arcs; is a set of cross-day waiting arcs; The flow balance constraint stipulates that, except for the virtual start and end points, the inflow at each node must equal the outflow; the net outflow at the virtual start point must equal the total number of vehicles, and the net inflow at the virtual end point must equal the total number of vehicles. ， In the formula, For the vehicle candidate set; It is a set of nodes, including train number nodes and EMU depot origin and destination nodes; For the set of virtual starting arcs; For the set of virtual endpoint arcs; The specific formula for the constraint on the value of the decision variable is as follows: ， In the formula, For the set of arcs; Based on the solution results of the aggregation model, a deaggregation solution model is constructed. The deaggregation solution model combines the aggregation results with the acquired actual state data to generate a specific real-name route plan. The steps for constructing the de-aggregation solution model are as follows: Define parameters and variables; The second objective function of the original model for the EMU route plan is constructed, and the comprehensive formula of the second objective function is as follows: , In the formula, The variable is 0-1, indicating whether vehicle k selects arc (i, j). Determine the constraints of the original model for the EMU route plan. The original model constraints include arc capacity constraints, flow balance constraints, and decision variable value constraints. The arc capacity constraint is that the usage of each arc cannot exceed the available capacity determined during the aggregation phase: ， In the formula, The arc capacity is obtained from the aggregation model; The flow balance constraint ensures that each vehicle starts from a virtual origin, maintains an equal flow rate at all intermediate nodes, and finally converges to a complete origin-end path at the virtual destination. The formula for the constraint on the value of the decision variable is as follows: 。 2. The optimization method for rapidly solving the EMU (Electric Multiple Unit) route plan as described in claim 1, characterized in that, The real-time status data includes the actual location information and cumulative mileage data of each EMU; the actual location information includes the station, operating section, or EMU depot. The cumulative mileage data includes total mileage, daily mileage, and mileage within the maintenance cycle.

3. The optimization method for rapidly solving the EMU (Electric Multiple Unit) route plan as described in claim 2, characterized in that, The real-time status data of the EMU is obtained by collecting data deployed in the EMU status monitoring system.

4. The optimization method for rapidly solving the EMU (Electric Multiple Unit) route plan as described in claim 2, characterized in that, The construction of a spatiotemporal axis network for EMU route planning based on real-time EMU status data includes: Based on the actual location information of the EMU, a corresponding initial node is constructed for each EMU within the spatiotemporal axis network, and the time, space and status attributes of the node are set; the EMU depot, station or operating section where the EMU is located is determined by database query, and then the corresponding virtual start node and end node are established. Based on the cumulative mileage data, a maintenance status judgment algorithm is used to compare the cumulative mileage with the maintenance threshold to determine the maintenance status of each EMU. For EMUs that are close to the maintenance mileage, their long-distance operation tasks are restricted when building the network, and the corresponding arc capacity is adjusted. For EMUs that have exceeded the maintenance mileage, they are removed from the set of available EMUs and no network nodes are created for them. At the same time, according to the preset maintenance plan, an available operating section and time window are set for each EMU. Based on the processed EMU status data, a network generation algorithm is used to abstract stations in the train time map into nodes and feasible connection relationships between stations into arcs, thereby constructing an axis network based on the actual status of the EMU for a preset time period.

5. The optimization method for rapidly solving the EMU (Electric Multiple Unit) route plan as described in claim 1, characterized in that, Based on the actual status data of the EMU, an original model of the EMU route plan is established. The actual status data includes real-time status data of the EMU and maintenance status data, including: The pre-acquired vehicle candidate set, node set, and arc set are used as model parameters; Based on actual location information, initial position constraints are set for each EMU to ensure that the EMU starts executing the route plan from its actual location; maintenance constraints are set based on cumulative mileage data to ensure that the EMU does not exceed the mileage limit before maintenance; and timetable constraints, station capacity constraints, and flow balance constraints are set based on actual timetable data.

6. The optimization method for rapidly solving the EMU (Electric Multiple Unit) route plan as described in claim 1, characterized in that, Based on real-time status data of EMU trains and the original EMU route plan model, an aggregated optimization model is established, including: The acquired real-time status data of the EMUs are aggregated to combine the location and mileage data of individual EMUs into network-wide resource allocation information. A data aggregation algorithm is used to aggregate the vehicle-level variables in the original model into arc-level flow variables, reducing model complexity. The distribution status of EMUs across the network is determined based on GPS positioning data, and the maintenance resource constraints of the entire network are determined based on mileage data. Convert the original model into an aggregate model.

7. The optimization method for rapidly solving the EMU (Electric Multiple Unit) route plan as described in claim 6, characterized in that, The objective function of the aggregation model is based on actual operating cost data, including vehicle usage costs, operating costs, and maintenance costs.

8. The optimization method for rapidly solving the EMU (Electric Multiple Unit) route plan as described in claim 7, characterized in that, The constraints of the aggregation model are based on actual train schedule data and EMU status data, including schedule constraints, station capacity constraints, and flow balance constraints.

9. The optimization method for rapidly solving the EMU (Electric Multiple Unit) route plan as described in claim 1, characterized in that, The solution model combines the aggregation results with the acquired actual state data to generate a specific, real-name route plan, including: Based on the aggregation results and actual status data, the aggregation results are matched with specific EMU train sets through a data matching algorithm to determine the available operating range of each EMU train set; Based on the aggregation results and actual status data, a specific operating path is generated for each EMU (Electric Multiple Unit). A path optimization algorithm is used to determine the optimal starting position by combining the current location information with the cumulative mileage data to ensure that the maintenance limit is not exceeded. Generate a real-name route plan that includes specific train set numbers, running times, and running routes.

10. An optimization system for rapidly solving EMU (Electric Multiple Unit) route planning, characterized in that, The system includes: The data acquisition unit is used to acquire real-time status data of the EMU (Electric Multiple Unit). The spatiotemporal axis network construction unit is used to construct the spatiotemporal axis network of the EMU route plan based on the real-time status data of the EMU. The original model building unit is used to establish an original model of the EMU route plan based on the actual state data and spatiotemporal axis network of the EMU. The actual state data includes real-time state data and maintenance state data of the EMU. The aggregation optimization model construction unit is used to build an aggregation optimization model based on the real-time status data of the EMU and the original EMU route plan model. The aggregation optimization model is based on the real-time status data of the EMU to obtain the solution results. The steps for constructing the aggregation model are as follows: Define parameters and variables; The objective function one of the original model for the EMU route plan is constructed, and the comprehensive formula of objective function one is as follows: ， In the formula, Let arc (i, j) be the total number of vehicles used. It is a sufficiently large positive number; For the set of demand arcs; For the set of virtual starting arcs; The constraints of the original model of the EMU route plan are determined, including timetable constraints, station capacity constraints, flow balance constraints, and decision variable value constraints. The timetable constraint corresponds to any train number specified on the train timetable. ,need Number of EMU trains serving: ， In the formula, Any train number specified on the train timetable; The number of train formations for train number q is 1 for a single formation and 2 for a double formation. The station capacity constraint is that the total number of vehicles waiting and operating within the station cannot exceed the station's maximum capacity. ， In the formula, Let (i, j) be the upper limit of the capacity of arc (i, j). For the set of connecting arcs; To unencode the arc set; For the set of reconnected arcs; For the set of waiting arcs across days; The flow balance constraint stipulates that, except for the virtual start and end points, the inflow at each node must equal the outflow; the net outflow at the virtual start point must equal the total number of vehicles, and the net inflow at the virtual end point must equal the total number of vehicles. ， In the formula, For the vehicle candidate set; It is a set of nodes, including train number nodes and EMU depot origin and destination nodes; For the set of virtual starting arcs; For the set of virtual endpoint arcs; The specific formula for the constraint on the value of the decision variable is as follows: ， In the formula, For the set of arcs; The de-aggregation solution model building unit is used to build a de-aggregation solution model based on the solution results of the aggregation model. The de-aggregation solution model combines the aggregation results with the acquired actual state data to generate a specific real-name route plan. The steps for constructing the de-aggregation solution model are as follows: Define parameters and variables; The second objective function of the original model for the EMU route plan is constructed, and the comprehensive formula of the second objective function is as follows: , In the formula, The variable is 0-1, indicating whether vehicle k selects arc (i, j). Determine the constraints of the original model for the EMU route plan. The original model constraints include arc capacity constraints, flow balance constraints, and decision variable value constraints. The arc capacity constraint is that the usage of each arc cannot exceed the available capacity determined during the aggregation phase: ， In the formula, The arc capacity is obtained from the aggregation model; The flow balance constraint ensures that each vehicle starts from a virtual origin, maintains an equal flow rate at all intermediate nodes, and finally converges to a complete origin-end path at the virtual destination. The formula for the constraint on the value of the decision variable is as follows: 。

Images