A railway transportation path planning method and device, electronic equipment and storage medium

Abstract

The present application relates to the technical field of railway transportation path planning, and discloses a railway transportation path planning method, device, electronic equipment and storage medium, the method comprising collecting railway network operation and maintenance data; preprocessing the operation and maintenance data to obtain structured data; determining the path preference and path priority of each transportation task based on the structured data; calculating an optimal path set based on the structured data and path priority; and outputting a final path scheme based on the optimal path set. The method can ensure that the input data is standard and reliable, laying a solid foundation for subsequent operations; effectively coordinates the competition for line resources among multiple trains, avoiding iterative dead loop problems; calculates the optimal path set in combination with data and priority, taking into account multiple operation objectives and achieving dynamic road condition adaptation, reducing overall computing power consumption; and finally outputs the path scheme, which is comprehensive and intuitive in information display, and can fully meet the actual use requirements of railway intelligent dispatching.

Description

Technical Field

[0001] This invention relates to the field of railway transportation route planning technology, specifically to a railway transportation route planning method, apparatus, electronic device, and storage medium. Background Technology

[0002] While existing railway transportation route planning technologies have made some progress, they generally suffer from insufficient dynamic adaptability and global coordination. Traditional solutions often rely on static planning approaches to solve routes, making it difficult to adjust routes in real time based on unforeseen circumstances such as construction, weather, and equipment failures. This results in a disconnect between the planned results and actual on-site conditions. Furthermore, these technologies cannot effectively resolve conflicts of interest among multiple stakeholders in complex scenarios, making it difficult to achieve globally optimal configuration. When multiple trains experience concentrated delays due to malfunctions or weather conditions, iterative route adjustments can easily fall into a vicious cycle. Some existing solutions also have high computational resource requirements when performing calculations on complex network topologies, leading to high deployment and usage costs and making them unsuitable for the application needs of actual railway dispatching. Summary of the Invention

[0003] This invention provides a railway transportation route planning method, device, electronic equipment, and storage medium to solve the problems of iterative adjustment getting stuck in a dead loop in multi-train delay scenarios, planning results being difficult to match real-time traffic conditions, and overall computation requiring high computing resources.

[0004] In a first aspect, the present invention provides a railway transportation route planning method, the method comprising: Collect operation and maintenance data for the railway network; Preprocess the operation and maintenance data to obtain structured data; Based on structured data, determine the route preferences and route priorities for each transportation task; Calculate the optimal set of paths based on structured data and path priorities; Output the final path scheme based on the optimal path set.

[0005] This method obtains structured data by sequentially collecting and preprocessing railway operation and maintenance data, ensuring the standardization and reliability of the input data and laying a solid foundation for subsequent calculations. Based on the structured data, it determines the path preferences and priorities of each transportation task, effectively coordinating competition for resources across multiple train lines and avoiding iterative deadlocks. Combining data and priorities, it calculates the optimal path set, balancing multiple operational objectives and achieving dynamic road condition adaptation, thus reducing overall computational power consumption. Finally, it outputs a path scheme with comprehensive and intuitive information display, fully meeting the practical needs of intelligent railway scheduling.

[0006] In one optional implementation, the operation and maintenance data is preprocessed to obtain structured data, including: Perform data cleaning and transformation on the operation and maintenance data to obtain semantic feature data corresponding to the operation and maintenance data; The semantic feature data is filtered and integrated to obtain a structured dataset.

[0007] This method cleans and converts the format of operation and maintenance data, extracts effective features, filters out irrelevant information, and integrates the data. It can not only eliminate abnormal and invalid data and unify the data format, but also reduce the data volume, making subsequent path planning calculations smoother and the results more accurate.

[0008] In one optional implementation, based on structured data, the path preference and path priority of each transportation task are determined, including: Independent intelligent agents corresponding to each transportation task are constructed and initialized based on structured data; Based on the delay time of each train in the railway network, the network efficiency, and the probability of path conflict, a first function is constructed. Based on Nash equilibrium, the first function is solved to obtain the path preferences and path priorities of each independent agent.

[0009] This method builds an independent intelligent agent for each transportation task based on well-organized structured data. It constructs functions by combining train delays, network efficiency, and path conflicts, and then calculates the path tendency and priority of each task through Nash equilibrium. This can coordinate the competition for line resources among different trains, balance the overall traffic order, and reduce line conflicts and large-scale delays from the source.

[0010] In one optional implementation, the optimal path set is calculated based on structured data and path priorities, including: Based on structured data and path priorities, an initial path set is generated, and the fitness value of each initial path in the initial path set in the target dimension is configured. Based on the non-dominated ranking of fitness values, the initial path is divided into different levels; Calculate the congestion distance of the initial path within the same level in the target space; The optimal path set is calculated based on the non-dominated ordering and congestion distance corresponding to the initial path.

[0011] This method generates initial routes by combining path priorities and evaluates the overall performance of each route. Then, it selects routes by hierarchical sorting and calculating congestion distance. This method can prioritize high-priority transportation tasks while retaining diverse route options, avoiding the algorithm from getting trapped in local optima too early, and ultimately selecting the route with better overall performance.

[0012] In one optional implementation, the optimal path set is calculated based on the non-dominated ordering and congestion distance corresponding to the initial path, including: Using non-dominated hierarchy as the first priority and crowding distance as the second priority, a first path set is selected from the initial path set. The first priority is higher than the second priority. The non-dominated hierarchy is used to represent the arrangement hierarchy of the initial path in the non-dominated sorting. The size of the first path set is the same as that of the initial path set. Based on the first set of paths, perform path intersection transformations and merging to obtain the second set of paths; The optimal path set is determined based on the non-dominated sorting of the second path set.

[0013] This method prioritizes routes with better overall performance when selecting paths, and further prioritizes routes with greater congestion distances within the same route category, ensuring sufficient diversity of route options. It then uses cross-variation to generate new routes, integrates and filters them, and continuously optimizes and iterates to gradually select the overall optimal transportation route.

[0014] In one optional implementation, a second set of paths is obtained by performing path intersection transformations and merging based on the first set of paths, including: Cross-mutation is performed between parent paths in the first path set to obtain child paths; Perform hard constraint validation on child paths and retain child paths that pass the validation. The paths in the first path set whose non-dominant level is less than the first level threshold are merged with the verified child paths to obtain the second path set.

[0015] This method generates new routes by cross-modifying existing routes, then adheres to strict railway operation rules to eliminate non-compliant routes. Simultaneously, it retains existing high-quality routes and integrates them with qualified new routes, enabling continuous exploration of better travel paths while preserving and optimizing good routes.

[0016] In an optional implementation, the optimal path set is calculated based on the non-dominated ordering and congestion distance corresponding to the initial path, and further includes: If the rate of change of the second function corresponding to the optimal path set is less than the preset threshold, or the global delay time corresponding to the optimal path set is less than the preset threshold and the line capacity utilization rate is higher than the preset threshold.

[0017] The iteration is terminated, and the optimal path set is output. The second function is a comprehensive evaluation function constructed based on the fitness value of each path in the target dimension and combined with the path priority.

[0018] This method stops iterating and outputs the final path when the comprehensive evaluation indicators stabilize, or when the overall delay and route capacity reach ideal levels. This saves unnecessary calculations, improves efficiency, and ensures that the given route plan matches actual driving requirements.

[0019] In a second aspect, the present invention provides a railway transportation route planning device, the device comprising: The data acquisition module is used to collect operation and maintenance data of the railway network; The preprocessing module is used to preprocess operation and maintenance data to obtain structured data; The determination module is used to determine the route preferences and route priorities for each transportation task based on structured data; The calculation module is used to calculate the optimal set of paths based on structured data and path priorities; The output module is used to output the final path scheme based on the optimal path set.

[0020] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the railway transportation route planning method of the first aspect or any corresponding embodiment described above.

[0021] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the railway transportation route planning method of the first aspect or any corresponding embodiment described above.

[0022] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the railway transportation route planning method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first type of railway transportation route planning method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a second process for a railway transportation route planning method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the third process of the railway transportation route planning method according to an embodiment of the present invention; Figure 5 This is a structural block diagram of a railway transportation route planning device according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. 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 embodiments of the present invention, not all embodiments. 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.

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0027] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0028] As an optional application scenario of this invention, such as Figure 1 As shown, the railway transportation route planning system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0029] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0030] According to an embodiment of the present invention, a railway transportation route planning method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] This embodiment provides a railway transportation route planning method, which can be used in the aforementioned electronic equipment. Figure 2 This is a schematic diagram of the first type of railway transportation route planning method according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps: Step S201: Collect operation and maintenance data of the railway network.

[0032] The railway network refers to the overall railway transportation network consisting of interconnected facilities such as railway lines, stations, tracks, signaling equipment, track circuits, and transponders. It is the physical carrier for train operation and transportation tasks. For example, main railway lines, stations along the lines, tracks between sections, turnouts, and throat areas are all components of the railway network.

[0033] Operation and maintenance data is the general term for all kinds of data generated and used in the entire process of railway network operation management, control and maintenance. It includes static basic data and dynamic real-time data, and is the core basis for route planning.

[0034] Operational and maintenance data specifically includes two main categories: static basic data and dynamic real-time data. Static basic data includes railway network topology information, such as the location and parameters of track circuits, transponders, and signals; track length, gradient, direction of travel, and track grade; as well as station arrival and departure line capacity and throat area operation interval requirements; it also covers train-related fixed information and transportation task information, such as train number, train type, traction parameters, maximum speed, cargo attributes, and the origin and destination, planned arrival and departure times, and task priority for each task.

[0035] Dynamic real-time data refers to information that is constantly updated on-site, such as the real-time location, speed, direction of travel, and fault status of trains, the location of track construction, track occupancy, equipment malfunction alarms, and other on-site road conditions, as well as weather conditions, temporary speed limit instructions issued by dispatch, and track maintenance arrangements. The system will align all the above data with timestamps before sending them to the next stage of processing.

[0036] Data acquisition refers to the process of actively acquiring relevant raw data of the railway network through various hardware devices, data interfaces, and monitoring systems, and then uniformly collecting and summarizing it. For example, train operation status data is collected through track circuits and on-board ATP devices; on-site road condition data is collected using millimeter-wave radar and video surveillance; meteorological information and temporary dispatch instructions are obtained through meteorological interfaces and dispatching system interfaces; and all acquired data is uniformly summarized to the backend system.

[0037] In this embodiment, the collection of railway network operation and maintenance data mainly relies on various monitoring equipment, business systems and data interfaces at the railway site to comprehensively collect the original data related to the operation and maintenance of the railway network, providing complete data support for subsequent data preprocessing, path analysis and calculation.

[0038] For example, after the system is started, it reads static operation and maintenance data such as road network topology, equipment parameters, and train attributes on the one hand, and continuously collects dynamic operation and maintenance data such as train position, speed, line construction, temporary speed limit, weather warning, and track occupancy in real time from on-board equipment, monitoring equipment along the line, track maintenance system, meteorological platform, and dispatching and command system on the other hand. All the collected raw data are uniformly collected.

[0039] Step S202: Preprocess the operation and maintenance data to obtain structured data.

[0040] For details regarding operation and maintenance data, please refer to the above text, which will not be repeated here.

[0041] Structured data refers to data that has been organized, has a unified format, clear logic, and well-organized classification, with each piece of information clearly defined, making it easy for the system to read and process. For example, well-organized road network parameter tables, train operation information in a unified format, and categorized maintenance and dispatching data are all examples of structured data.

[0042] After collecting various scattered raw operation and maintenance data, such as road network, train, road conditions, weather, and maintenance data, the system uniformly sorts, organizes, and integrates the data, removes erroneous information, standardizes data format, and removes irrelevant content. Finally, it produces a unified and logically structured set of road network parameters, train status, and line operation data, forming complete structured data that can be directly read and processed by subsequent models.

[0043] Step S203: Based on structured data, determine the path preference and path priority for each transportation task.

[0044] A transportation mission refers to the train operation for each journey, including travel, freight transport, or emergency rescue. Each independent mission has its own specific departure point, destination, and time requirements. For example, ordinary passenger train travel, freight train transport of supplies, and emergency rescue material delivery are all different transportation missions.

[0045] Route preference refers to the preferred route for each transportation task, taking into account factors such as route conditions, operational status, and conflict risks. It is a route selection tendency formed based on actual road conditions. For example, a train may prioritize routes with less traffic, no construction sections, and low risk of delays.

[0046] Route priority is a sequence of priorities based on the importance and timeliness of the task. It is used to distinguish the priority levels of different trains in the allocation of line resources and route selection. For example, emergency relief trains and long-distance passenger trains have higher priority than ordinary freight trains.

[0047] Based on the structured data processed in the previous step, and taking into account the overall operation status of the road network, the traffic conditions of the lines, and the actual needs of different tasks, the system clarifies the route selection tendency for each transportation task and classifies the path priority of each task. For example, the system retrieves data on the entire road network, trains, and road conditions after the entire line is normalized, comprehensively assesses the traffic pressure and operational risks of each line, and determines the more suitable route for each train. Then, combined with the urgency and service attributes of the task, the system distinguishes the traffic priority of different trains, and finally forms a complete route tendency and classification result for use in the subsequent route planning stage.

[0048] Step S204: Calculate the optimal path set based on structured data and path priority.

[0049] The optimal route set refers to a set of routes with the best overall performance selected for all transportation tasks after considering various operational constraints and target requirements. For example, it takes into account traffic efficiency, transportation cost, and line load, and matches reasonable routes for multiple trains along the entire line, forming a complete route plan.

[0050] The calculation refers to the process of comparing, screening, and evaluating a large number of alternative routes based on the system's operational logic, and completing the entire process of route selection. For example, the process involves calculating the travel time, congestion risk, and compliance of different routes one by one, and then selecting the appropriate solution.

[0051] Based on the previously obtained organized data and task priorities, the system comprehensively evaluates and filters various alternative routes to obtain the optimal route combination that suits all transportation tasks. For example, the system retrieves structured data such as road network, trains, and real-time traffic conditions. At the same time, it refers to the defined task priorities and comprehensively evaluates all available routes. In the process of selecting the best route, priority is given to ensuring the passage needs of high-level transportation tasks, while taking into account the operation arrangements of other trains. After multiple rounds of comparison and screening, a set of routes with the best overall effect is determined.

[0052] Step S205: Output the final path scheme based on the optimal path set.

[0053] The final route plan refers to the formal route arrangement formed for actual scheduling and train operation. It is the final result of the entire planning process being implemented and used. For example, it includes a complete train operation scheduling plan that includes train routes, estimated arrival and departure times, and precautions.

[0054] Output refers to transforming the route data obtained from the background calculation into intuitive and usable content and pushing it to the corresponding user terminal. For example, route information can be displayed on the dispatch screen, paper instruction documents can be generated, and the information can be sent to the vehicle-mounted equipment simultaneously.

[0055] The railway transportation route planning method provided in this embodiment obtains structured data by sequentially collecting railway operation and maintenance data and preprocessing the data, which ensures that the input data is standardized and reliable, laying a solid foundation for subsequent calculations. Based on the structured data, the route preferences and priorities of each transportation task are determined, which can effectively coordinate the competition for resources on multiple train lines and avoid the problem of iterative dead loops. The optimal route set is calculated by combining data and priorities, taking into account multiple operational objectives and achieving dynamic road condition adaptation, thereby reducing the overall computing power consumption. Finally, the route plan is output, and the information is displayed comprehensively and intuitively, which can fully meet the actual needs of railway intelligent scheduling.

[0056] This embodiment provides a railway transportation route planning method, which can be used in the aforementioned electronic equipment. Figure 3 This is a schematic diagram of a second process for a railway transportation route planning method according to an embodiment of the present invention, as shown below. Figure 3 As shown, the process includes the following steps: Step S301: Collect operation and maintenance data of the railway network.

[0057] Please see details Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0058] Step S302: Preprocess the operation and maintenance data to obtain structured data.

[0059] Specifically, step S302 includes: Step S3021: Perform data cleaning and data transformation on the operation and maintenance data to obtain semantic feature data corresponding to the operation and maintenance data.

[0060] The main focus is on cleaning and format conversion of the collected railway operation and maintenance data to generate corresponding semantic feature data. For example, the data is first cleaned by using the 3σ discriminant rule to remove abnormal speed data caused by electromagnetic interference from track circuit sensors and invalid position information caused by transponder communication timeouts. At the same time, the sliding window mean filtering algorithm is used to eliminate errors caused by data jitter from on-board positioning equipment, ensuring the accuracy and reliability of the basic data. Next, the data is converted to unify the data from different systems and with different formats into a standard semantic form. For example, the coordinates of the construction area recorded by the track maintenance system are converted into the node numbers corresponding to the road network topology, and the rainfall levels provided by the meteorological department are converted into risk weights for line passage.

[0061] Step S3022: Perform data filtering and data integration on the semantic feature data to obtain a structured dataset.

[0062] The generated semantic feature data is filtered and integrated to obtain a structured dataset. For example, the semantic feature data is filtered by combining the start and end points of this transportation task to remove redundant information outside the planned route, retaining only the signals, tracks, and corresponding dynamic data within the target section. Finally, the data is integrated by associating the static parameters of the road network, basic train information, and real-time operation data according to timestamps to construct data such as the road network node adjacency matrix, train state vector, and environmental risk vector, forming a complete structured dataset. This data is then sent to the multi-agent game model and the path planning module to support subsequent computation.

[0063] First, data cleaning and format conversion are completed. On the one hand, abnormal and distorted information is removed to ensure that all data is authentic and usable. On the other hand, the expression standards of multi-source data are unified and the core semantic features are extracted. Then, by filtering and simplifying the data content and integrating and reconstructing the data structure, the computational resource consumption caused by invalid data is reduced, and a structured dataset with standardized format and unified logic is formed. The entire data processing process is checked at each level to optimize data quality and fully meet the operation requirements of subsequent intelligent agent game and path optimization algorithms, ensuring the stable and efficient progress of the entire path planning process.

[0064] Step S303: Based on structured data, determine the path preference and path priority for each transportation task.

[0065] Specifically, step S303 includes: Step S3031: Construct and initialize independent intelligent agents corresponding to each transportation task based on structured data.

[0066] Independent agents are the basic units in the multi-agent game model of this scheme. Each agent corresponds to a train to be dispatched or an independent transportation task. Each agent has its own state information and selectable travel path. It can perceive the road network environment and the choices of other agents, and participate in the competition and cooperation for line resources.

[0067] Based on the structured dataset, a multi-agent game model for railway route planning was built. A dedicated independent agent was created for each transportation task and each train to be dispatched. Initial parameter configurations for all agents were completed. According to the model settings, each agent corresponds to a single train or an independent transportation task, and its range of actions is all available travel paths within the railway network. Agents can perceive their own real-time location and the occupancy status of the track ahead, and can also obtain the path selection results of other agents, laying the foundation for subsequent competition and cooperation among agents.

[0068] Step S3032: Based on the delay time of each train in the railway network, the network traffic efficiency, and the probability of path conflict, construct the first function.

[0069] This step combines three core indicators—real-time train delay duration, overall network efficiency, and the probability of path conflicts on different lines—to construct the corresponding first function. This first function serves as the core computational basis for game theory decision-making, quantifying the comprehensive state of multiple trains during the competition for line resources and collaborative operation. It also connects to the model's two-tiered reward mechanism: on the one hand, it generates immediate rewards based on individual train delay time and path conflict probability, corresponding to the competitive game logic of agents vying for capacity resources such as tracks and bottlenecks; on the other hand, it generates delayed rewards based on the overall network delay situation and network efficiency, corresponding to the cooperative game logic of trains avoiding peak hours, yielding to each other, and reducing the spread of delays.

[0070] Step S3033: Based on Nash equilibrium, solve the first function to obtain the path preferences and path priorities of each independent agent.

[0071] Nash equilibrium is a stable decision-making state in game theory. In this invention, the parties involved in the game are the independent agents corresponding to each train. Under the current situation, changing their choices individually will not yield a better result. At this point, the overall decision reaches Nash equilibrium. The independent agents will not actively break the current state, but will choose to find a balance between competition and compromise.

[0072] The Nash equilibrium theory is used to solve the first function constructed in the previous step. Under the premise of taking into account the competition and cooperation among agents, the balanced allocation of the network's transportation capacity resources is achieved. The path selection tendency of each independent agent and the order of each transportation task in route use and path planning are finally determined through calculation, that is, path preference and path priority. The result will be output to the subsequent path planning module as a constraint condition and weight reference for multi-objective optimization calculation.

[0073] By combining multi-agent models with game theory for decision-making, the operational needs of individual trains and the overall operational goals of the entire network are taken into account, thereby resolving conflicts of interest among multiple stakeholders. This approach not only restores the complex operational interactions of the railway network but also finds a globally relatively optimal stable solution through Nash equilibrium, effectively reducing line contention, train passing conflicts, and the propagation of delays. At the same time, it provides clear reference data for subsequent route planning, making the overall planning scheme more aligned with on-site dispatching needs.

[0074] Step S304: Calculate the optimal path set based on structured data and path priority.

[0075] Specifically, step S304 includes: Step S3041: Based on structured data and path priority, generate an initial path set and configure the fitness value of each initial path in the target dimension.

[0076] Based on the network topology structured data obtained from data preprocessing, and combined with the train path priorities output by the multi-agent game model, multiple feasible routes that conform to railway operation rules are generated in batches to form an initial path set. When generating paths, hard constraints such as line travel direction, minimum turning radius of trains, and station arrival and departure line capacity are strictly followed, and obviously invalid routes are eliminated. The number of initial paths is set between 50 and 200 according to the scale of transportation tasks.

[0077] Subsequently, fitness values ​​for the four target dimensions are calculated for each initial path. The four targets can be transportation cost, line capacity utilization, timeliness deviation, and maintenance compliance. Transportation cost is calculated based on the total traction energy consumption and line usage fees of the entire path; line capacity utilization is calculated by weighting the real-time track occupancy saturation and bottleneck track occupancy; timeliness deviation is the absolute value of the difference between the estimated arrival time and the planned arrival time; and maintenance compliance is calculated based on the number of conflicts between the path and the track maintenance time window. Path priority is also introduced as a weighting factor for dynamic adjustment. For high-priority tasks such as passenger trains and emergency supply trains, the weight of timeliness deviation is increased by 30%-50%, thus completing the configuration of fitness values ​​for all paths.

[0078] Step S3042: Based on the non-dominated sorting of fitness values, the initial path is divided into different levels.

[0079] After calculating the fitness values, a non-dominated ranking is performed on the entire initial path set according to multi-objective optimization rules. Based on the comprehensive performance of each path in four dimensions—transportation cost, capacity utilization, timeliness, and maintenance compliance—paths are distinguished in terms of quality, and all paths are divided into multiple different frontier levels. The ranking logic follows the Pareto optimality principle: if a path cannot optimize a certain indicator without compromising other objectives, it is assigned to the corresponding frontier level. This distinguishes the overall performance of the paths and lays the foundation for subsequent selection.

[0080] Step S3043: Calculate the congestion distance of the initial path in the target space within the same level.

[0081] For all paths at the same level after non-dominated sorting, the congestion distance of each path in the four-dimensional target space is calculated uniformly. The congestion distance is calculated using the following formula: .

[0082] in, Let represent the congestion distance of the i-th path in the target space. The maximum value of the k-th target. The minimum value of the k-th target. Let j be the value of path j at the k-th target.

[0083] The calculation is performed using the difference between adjacent values ​​of the path under a single objective dimension, as well as the maximum and minimum values ​​of the index for that dimension. Crowding distance is used to evaluate the balance of paths at the same level among multiple objectives. The larger the crowding distance value, the better the overall balance effect of this path among various optimization objectives, and it can also effectively prevent the algorithm from converging to a local optimum too early during the iteration process.

[0084] Step S3044: Calculate the optimal path set based on the non-dominated order and congestion distance corresponding to the initial path.

[0085] Combining the previously obtained non-dominated ranking level and congestion distance indicators, an adaptive tournament selection method is used to screen high-quality paths: a portion of the path samples are randomly selected, prioritizing paths with lower non-dominated ranking levels. If multiple paths are at the same level, individuals with larger congestion distances are selected. After selecting the parent path, child paths are generated using adaptive crossover and mutation operators adapted to the railway scenario. Hard constraint verification is then performed on the child paths to check for limitations such as line capacity, maintenance time windows, and train tracking intervals, eliminating invalid paths. Then, high-quality parent paths and compliant child paths are merged, and non-dominated ranking is performed again. A specified number of high-quality individuals are retained to form a new generation population. This process is iterated repeatedly, and the termination time is determined by combining dual convergence conditions. When the change in the optimal path indicator is less than 1% for multiple consecutive generations, or when the global delay and capacity utilization rate reach the preset standards, the iteration stops, and finally, the set of paths with the best overall performance is obtained.

[0086] Step S305: Output the final path scheme based on the optimal path set.

[0087] Based on the optimal path set obtained in the previous step, a complete train operation plan is simultaneously output in multiple forms, exhibiting multimodal output. Exemplary forms can be categorized into three types: The first type uses a visual path map, marking the routes of each train, the signal nodes along the way, and key stations on the railway network electronic map, along with the estimated arrival and departure times for each station. Optionally, different colors can be used to distinguish path priorities; for example, red represents high-priority passenger train routes, and blue represents freight train routes. The second type is a textual description document, detailing the overall direction of each path, construction sections to be avoided, and special driving precautions such as speed-limited sections, areas with strong winds, and lightning warnings. The third type is a structured data table, containing information such as train number, departure time, estimated arrival time, stations along the way, total path length, and estimated transportation costs. The specific implementation of these tables is not limited here; they can be set according to actual needs.

[0088] Optionally, in addition to the three external display solutions mentioned above, the optimal path set can also be simultaneously pushed to the railway dispatch terminal and train onboard equipment to ensure that dispatchers and train operators can obtain information in a timely manner. At the same time, the output results will be sent back to the front-end data acquisition module, triggering dynamic updates throughout the entire process and continuously responding to various real-time changes within the railway network.

[0089] This embodiment provides a railway transportation route planning method, which can be used in the aforementioned electronic equipment. Figure 4 This is a schematic diagram of the third process of the railway transportation route planning method according to an embodiment of the present invention, as shown below. Figure 4 As shown, step S304 above further includes the following steps: Step S401: Based on structured data and path priorities, generate an initial path set and configure the fitness value of each initial path in the target dimension.

[0090] Please see details Figure 3 Step S3041 of the illustrated embodiment will not be described again here.

[0091] Step S402: Based on the non-dominated sorting of fitness values, the initial path is divided into different levels.

[0092] Please see details Figure 3 Step S3042 of the illustrated embodiment will not be described again here.

[0093] Step S403: Calculate the congestion distance of the initial path in the target space within the same level.

[0094] Please see details Figure 3 Step S3043 of the illustrated embodiment will not be described again here.

[0095] Step S404: Calculate the optimal path set based on the non-dominated order and congestion distance corresponding to the initial path.

[0096] Specifically, step S404 includes: Step S4041: Select a first path set from the initial path set, with the non-dominated level as the first priority and the congestion distance as the second priority. The first priority is higher than the second priority. The non-dominated level is used to represent the arrangement level of the initial path in the non-dominated sorting. The size of the first path set is the same as that of the initial path set.

[0097] A first set of paths of the same size is selected from the initial path set according to a dual selection rule. During the selection, the non-dominated level is used as the primary criterion and the crowding distance is used as the secondary criterion, with the level having higher priority than the crowding distance. Paths with better non-dominated levels are selected first. If multiple paths are at the same level, the path with a larger crowding distance is selected. Such paths have better balance among multiple objectives. An adaptive tournament selection method is used to extract samples for selection. Finally, the first set of paths with the same number as the initial path set is selected as the parent population for subsequent calculations.

[0098] Step S4042: Perform path intersection transformation and merging based on the first path set to obtain the second path set.

[0099] The first path set obtained in the previous step is subjected to crossover and mutation operations. Paths in the first path set with non-dominated levels lower than the first-level threshold are then merged with their validated offspring paths to obtain the second path set. Crossover and mutation operations are performed based on the characteristics of the railway network. After completion, the generated paths are checked to ensure they meet hard constraints such as line capacity, maintenance time windows, and train tracking intervals. Invalid paths are removed, and the final set is the second path set. The first-level threshold is a pre-set maximum number of levels to retain, used to define the range of elite paths. For example, when the first-level threshold is set to 3, paths at levels 1 and 2 will be retained. This threshold can be adaptively adjusted according to actual scheduling needs and computing power conditions.

[0100] Step S4043: Determine the optimal path set based on the non-dominated sorting of the second path set.

[0101] The second path set is re-sorted and hierarchically divided using non-dominated sorting, and then the optimal selection is completed by combining the crowding distance. At the same time, the high-quality paths retained from the previous generation are merged with the current path, and the path is sorted and hierarchically divided again, retaining a specified number of high-quality individuals. The calculation is continued iteratively.

[0102] If the rate of change of the second function corresponding to the optimal path set is less than a preset threshold, or if the global delay time corresponding to the optimal path set is less than a preset threshold and the line capacity utilization rate is higher than a preset threshold, then the iteration terminates and the optimal path set is output. The second function is a comprehensive evaluation function constructed based on the fitness values ​​of each path in the target dimension and combined with path priorities. Specifically, the second function is a comprehensive evaluation function constructed by weighting the fitness values ​​of each path in four dimensions—transportation cost, line capacity utilization rate, timeliness deviation, and maintenance compliance—combined with the path priorities output by the multi-agent game model.

[0103] The preset thresholds for numerical change rate, duration, and utilization rate are three sets of independent preset parameters, corresponding to three different evaluation characteristics: numerical change rate, global delay time, and line capacity utilization rate, respectively. The value range and preset rules of the three thresholds are independent of each other and can be configured separately according to the route scheduling business requirements. Simultaneously, the numerical change rate of the second function, global delay time, and route capacity utilization rate are set to construct dual judgment conditions as the basis for iteration termination, and the operation indicators of the optimal path set are monitored in real time. For example, if the preset change rate is 1%, the preset time is 5 minutes, and the preset utilization rate is 65%, then on the one hand, it is judged whether the numerical change rate of the second function corresponding to the optimal path of the population for 10 consecutive generations is less than 1%, and on the other hand, it is judged whether the global delay time of the road network is less than 5 minutes, and whether the route capacity utilization rate is higher than 65%. The above indicators are continuously compared. As long as any judgment condition is met, the iteration process is terminated, and the optimal path set with the best overall performance is finally determined and output. The path scheme obtained at this time has achieved balanced optimization among multiple objectives such as transportation cost, capacity utilization, train travel time, and maintenance matching, while taking into account the passage priority of different trains. It can be directly used as the final path scheme and delivered to subsequent modules to complete multimodal display and scheduling applications.

[0104] This embodiment also provides a railway transportation route planning device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0105] This embodiment provides a railway transportation route planning device, such as... Figure 5 As shown, it includes: The data acquisition module 501 is used to collect operation and maintenance data of the railway network; Preprocessing module 502 is used to preprocess operation and maintenance data to obtain structured data; The determination module 503 is used to determine the path preference and path priority of each transportation task based on structured data; Calculation module 504 is used to calculate the optimal set of paths based on structured data and path priorities; Output module 505 is used to output the final path scheme based on the optimal path set.

[0106] In some alternative implementations, module 502 includes: The data cleaning unit is used to clean and transform the operation and maintenance data to obtain semantic feature data corresponding to the operation and maintenance data.

[0107] The data filtering unit is used to filter and integrate semantic feature data to obtain a structured dataset.

[0108] In some alternative implementations, module 503 includes: An initialization unit is used to construct and initialize the independent intelligent agents corresponding to each transportation task based on structured data; The construction unit is used to construct the first function based on the delay time of each train in the railway network, the network traffic efficiency, and the probability of path conflict. The solution unit is used to solve the first function based on Nash equilibrium to obtain the path preferences and path priorities of each independent agent.

[0109] In some alternative implementations, module 504 includes: The configuration unit is used to generate an initial path set based on structured data and path priorities, and to configure the fitness value of each initial path in the initial path set in the target dimension. Partitioning units are used to divide the initial path into different levels based on non-dominated ranking of fitness values; The first calculation unit is used to calculate the congestion distance of the initial path in the target space within the same level.

[0110] The second calculation unit is used to calculate the optimal path set based on the non-dominated order and congestion distance corresponding to the initial path.

[0111] In some alternative implementations, the second computing unit includes: Selecting a sub-unit is used to select a first path set from the initial path set, with the non-dominated hierarchy as the first priority and the congestion distance as the second priority. The first priority is higher than the second priority. The non-dominated hierarchy is used to represent the arrangement hierarchy of the initial path in the non-dominated sorting. The size of the first path set is the same as that of the initial path set.

[0112] The merged sub-unit is used to perform path intersection transformation and merging based on the first path set to obtain the second path set.

[0113] Determine sub-units to determine the optimal set of paths based on the non-dominated sorting of the second set of paths.

[0114] In some alternative implementations, the merging subunit includes: The crossover mutation operator is used to perform crossover mutations between parent paths in the first path set to obtain child paths.

[0115] The verification operator is used to perform hard constraint verification on the child paths and retain the child paths that pass the verification. The merging operator merges paths in the first path set whose non-dominated level is less than the first level threshold with the verified child paths to obtain the second path set.

[0116] In some optional implementations, the second computing unit further includes: The judgment sub-unit is used if the rate of change of the value of the second function corresponding to the optimal path set is less than a preset threshold, or the global delay time corresponding to the optimal path set is less than a preset threshold and the line capacity utilization rate is higher than a preset threshold.

[0117] The output sub-unit is used to terminate the iteration and output the optimal path set. The second function is a comprehensive evaluation function constructed based on the fitness value of each path in the target dimension and combined with the path priority. The railway transportation route planning device provided in this embodiment of the invention can execute the railway transportation route planning method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0118] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0119] The following is a detailed reference. Figure 6 This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in ROM 602 or a program loaded from memory 608 into RAM 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via bus 604. An input / output (I / O) interface 605 is also connected to bus 604; wherein ROM is a read-only memory and RAM is a random access memory.

[0120] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0121] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the railway transportation route planning method of the embodiments of the present invention.

[0122] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0123] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the railway transportation route planning method shown in the above embodiments is implemented.

[0124] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0125] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A railway transportation route planning method, characterized in that, The method includes: Collect operation and maintenance data for the railway network; The operation and maintenance data is preprocessed to obtain structured data; Based on the structured data, the path preference and path priority of each transportation task are determined; Based on the structured data and the path priorities, calculate the optimal path set; The final path scheme is output based on the optimal path set.

2. The method according to claim 1, characterized in that, The preprocessing of the operation and maintenance data to obtain structured data includes: The operation and maintenance data is cleaned and transformed to obtain semantic feature data corresponding to the operation and maintenance data; The semantic feature data is filtered and integrated to obtain a structured dataset.

3. The method according to claim 1, characterized in that, The process of determining the route preference and route priority for each transportation task based on the structured data includes: Based on the structured data, construct and initialize independent intelligent agents corresponding to each of the transportation tasks; Based on the delay time of each train in the railway network, the network efficiency, and the probability of path conflict, a first function is constructed. Based on Nash equilibrium, the first function is solved to obtain the path preferences and path priorities of each independent agent.

4. The method according to claim 1, characterized in that, The calculation of the optimal path set based on the structured data and the path priority includes: Based on the structured data and the path priority, an initial path set is generated, and the fitness value of each initial path in the initial path set in the target dimension is configured. Based on the non-dominated ranking of the fitness values, the initial path is divided into different levels; Calculate the congestion distance of the initial path within the same level in the target space; The optimal path set is calculated based on the non-dominated ordering corresponding to the initial path and the congestion distance.

5. The method according to claim 4, characterized in that, The calculation of the optimal path set based on the non-dominated ranking corresponding to the initial path and the congestion distance includes: Using the non-dominated hierarchy as the first priority and the congestion distance as the second priority, a first path set is selected from the initial path set, wherein the first priority is higher than the second priority, the non-dominated hierarchy is used to characterize the arrangement hierarchy of the initial path in the non-dominated sorting, and the size of the first path set is the same as that of the initial path set. Based on the first path set, perform path intersection transformations and merging to obtain the second path set; The optimal path set is determined based on the non-dominated sorting of the second path set.

6. The method according to claim 5, characterized in that, The second path set is obtained by performing path intersection transformation and merging based on the first path set, including: Cross-mutation is performed between parent paths in the first path set to obtain child paths; Perform hard constraint verification on the child paths and retain the child paths that pass the verification; The paths in the first path set whose non-dominant level is less than the first level threshold are merged with the verified child paths to obtain the second path set.

7. The method according to claim 4, characterized in that, The step of calculating the optimal path set based on the non-dominated sorting corresponding to the initial path and the congestion distance further includes: If the rate of change of the value of the second function corresponding to the optimal path set is less than the preset rate of change, or the global delay time corresponding to the optimal path set is less than the preset time and the line capacity utilization rate is higher than the preset utilization rate, The iteration is terminated, and the optimal path set is output, wherein the second function is a comprehensive evaluation function constructed based on the fitness value of each path in the target dimension and combined with the path priority.

8. A railway transportation route planning device, characterized in that, The device includes: The data acquisition module is used to collect operation and maintenance data of the railway network; The preprocessing module is used to preprocess the operation and maintenance data to obtain structured data; The determination module is used to determine the path preference and path priority of each transportation task based on the structured data. The calculation module is used to calculate the optimal path set based on the structured data and the path priority; The output module is used to output the final path scheme based on the optimal path set.

9. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory storing computer instructions, and the processor executing the computer instructions to perform a railway transportation route planning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute a railway transportation route planning method according to any one of claims 1 to 7.

Images