Heavy-haul train virtual marshalling dynamic unmarshalling method

Abstract

This application relates to the technical field of train control and scheduling, and in particular to a method for dynamic virtual formation and unforming of heavy-haul trains. The method includes, in response to a formation and unforming command for a target train, acquiring the working state of the turnout mechanism and the respective operating states of the target train and the following train; the following train is the train behind the target train; determining safety constraints based on the working state and the respective operating states of the target train and the following train; the safety constraints are used to constrain the distance between the following train and the target train at the beginning and end of the formation and unforming phases of the target train; determining control commands for the target train and the following train based on the safety constraints and the respective operating states of the target train and the following train, and executing the respective control commands for the target train and the following train. The solution adopted in this application can improve the safety of the formation and unforming process.

Description

Technical Field

[0001] This application relates to the technical field of train control and scheduling, and in particular to a method for the dynamic ungrouping and regrouping of virtual train formations for heavy-haul trains. Background Technology

[0002] In heavy-haul railway freight scenarios, based on transportation needs, multiple trains are virtually grouped into a single train formation and depart from the same origin along the track. Since different trains in the train formation may be heading to different destinations, according to the structure of rail transit, some trains need to switch tracks at corresponding locations along the track to change to the track leading to their destination. This process is called train formation decoupling.

[0003] In related technologies, train decoupling instructions are fixed, meaning that trains to be decoupled need to accelerate or decelerate to a fixed state at a fixed time and location. However, such a setup has many inflexible aspects during the decoupling process. For example, sometimes the operating speed and spacing between two trains may not be appropriate, or when problems occur on the track, timely countermeasures are often not possible, leading to safety accidents during the decoupling process (such as collisions, or causing significant delays to subsequent trains).

[0004] Therefore, improving the safety between trains during the decoupling process is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] Therefore, it is necessary to provide a method for the dynamic ungrouping and regrouping of virtual train formations for heavy-haul trains that can improve the safety between trains during the ungrouping and regrouping process, in order to address the aforementioned technical problems.

[0006] Firstly, this application provides a method for the dynamic ungrouping and regrouping of virtual train formations for heavy-haul trains, including:

[0007] In response to the uncoupling command for the target train, the working status of the turnout mechanism is obtained, and the operating status of the target train and the following train are obtained respectively; the following train is the train behind the target train.

[0008] Based on the working status and the respective operating statuses of the target train and the following train, safety constraints are determined; these safety constraints are used to constrain the distance between the following train and the target train at the beginning and end of the target train's decoupling phase.

[0009] Based on the safety constraints and the respective operating states of the target train and the following train, control commands are determined for the target train and the following train, and the control commands are used to apply traction or braking force to the train.

[0010] The effectiveness of the control command is verified using train models of both the target train and the following train, and the verification results are obtained; the train model represents the impact of the control command on the train's operating state.

[0011] If the verification result is valid, execute the control commands for the target train and the following train respectively.

[0012] In one embodiment, the operating state includes load information, temperature information, and wear degree of the turnout mechanism; the safety constraints include the expected interval distance before decoupling and the safe train distance after decoupling; determining the safety constraints based on the operating state and the respective operating states of the target train and the following train includes:

[0013] Based on the load information, temperature information, and wear level of the turnout mechanism, the basic switching time of the turnout mechanism is corrected to obtain the actual switching time;

[0014] The desired interval distance is determined based on the actual conversion time, communication lag time, mechanical lag time, and the operating status of the following train.

[0015] The maximum braking distance is determined based on the operating status of the following train, and the safe driving distance is determined based on the actual switching time, the redundancy distance, and the operating status of the following train.

[0016] In one embodiment, the train model is a multi-mass dynamic model constructed based on the train's mass distribution, traction force, braking force, combined resistance, braking characteristics, and inertial delay.

[0017] In one embodiment, determining the control commands for the target train and the following train based on the safety constraints and the respective operating states of the target train and the following train includes:

[0018] Using the safety constraints and the respective operating states of the target train and the following train, the objective function is solved to obtain the control commands for the target train and the following train;

[0019] The objective function is used to minimize the deviation between the actual interval between trains and the desired safe interval, minimize the deviation between the train speed and the turnout speed limit, and minimize the energy consumption caused by the control command; wherein the train model of the target train and the following train, as well as the turnout speed limit, are used as constraints in the solution process.

[0020] In one embodiment, the effectiveness of the control command is verified using the respective train models of the target train and the following train, and the verification result is obtained, including:

[0021] The control commands for the target train and the following train are input into their respective train models to obtain the estimated operating status for the target train and the following train.

[0022] Based on the respective operating status and estimated operating status of the target train and the following train, the estimated interval distance and estimated travel distance between the target train and the following train are determined;

[0023] The verification result is determined based on the estimated interval distance, the estimated driving distance, the expected interval distance, and the driving safety distance.

[0024] In one embodiment, the method further includes:

[0025] If the verification result is invalid, a safety weight is added to the objective function to update the objective function, and the operating states of the target train and the following train are updated respectively; the safety weight is used to reduce the speed and / or acceleration of the following train.

[0026] Using the safety constraints and the updated operating states of the target train and the following train, the updated objective function is solved to update the control commands for the target train and the following train.

[0027] In one embodiment, the method further includes:

[0028] Obtain the real-time location of each train in the train formation;

[0029] Based on the real-time location of each train and the corresponding decoupling location of each train, the remaining journey of each train is determined;

[0030] Trains with remaining journey time less than or equal to a preset threshold are identified as target trains, and decompilation instructions are generated for the target trains.

[0031] Secondly, this application also provides a dynamic decompilation device, which includes a state monitoring module, a constraint determination module, a control module, a verification model, and an execution module, wherein:

[0032] The status monitoring module is used to respond to the decoupling command for the target train, obtain the working status of the turnout mechanism, and obtain the running status of the target train and the following train respectively; the following train is the train behind the target train.

[0033] The constraint determination module is used to determine safety constraints based on the working state and the respective operating states of the target train and the following train; the safety constraints are used to constrain the distance between the following train and the target train at the beginning and end of the target train decoupling phase.

[0034] The control module is used to determine control commands for the target train and the following train respectively based on the safety constraints and the respective operating states of the target train and the following train. The control commands are used to apply traction or braking force to the train.

[0035] The verification module is used to verify the effectiveness of the control command using the respective train models of the target train and the following train, and to obtain the verification result; the train model represents the impact of the control command on the operating state of the train.

[0036] The execution module is configured to execute the control commands for the target train and the following train respectively, if the verification result is valid.

[0037] Thirdly, this application also provides a vehicle including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the virtual formation and dynamic unforming method for heavy-haul trains as described in any of the first aspects above.

[0038] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the virtual formation and dynamic unforming method for heavy-load trains as described in any of the first aspects above.

[0039] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the virtual formation and dynamic unforming method for heavy-load trains as described in any of the first aspects above.

[0040] The aforementioned method for dynamic de-staging of heavy-haul trains via virtual formation involves a de-staging command indicating that the target train is about to begin de-staging. Based on the real-time operating status of the turnout mechanism and the respective operating states of the target train and its following trains, more accurate safety constraints can be determined in real time. Simultaneously, control commands are generated for both the target and following trains based on these safety constraints, enabling safety control between them before and after de-staging to prevent collisions. Furthermore, after the effectiveness of each control command is verified using the corresponding train model for each train, the target and following trains execute the verified and reliable control commands, thereby enhancing safety between trains during the de-staging process. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram of a train formation in one embodiment;

[0043] Figure 2 This is a flowchart illustrating the dynamic decomposition and reassembly of a virtual train formation in one embodiment.

[0044] Figure 3 This is a flowchart illustrating the process of determining safety item constraints in one embodiment;

[0045] Figure 4 This is a structural block diagram of a dynamic decoding device in one embodiment;

[0046] Figure 5 This is an internal structural diagram of a computer device inside a vehicle in one embodiment. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0048] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0049] The virtual train formation and dynamic unforming method for heavy-haul trains provided in this application can be applied to train formations comprising multiple trains for unforming and controlling the formation. For example... Figure 1 The diagram shown is a schematic of a train formation, specifically including train 1, train 2, train 3... train N. In a railway network, the switch mechanism can switch between multiple rails and is used to change a train's travel path from one rail to another.

[0050] The virtual formation and dynamic unforming method for heavy-haul trains provided in this application is executed by a control unit. In one possible implementation, the control unit is any train in the train formation. This requires equipping each train with communication equipment so that adjacent trains can communicate with each other to obtain the information they need. Furthermore, each train is equipped with independent computer equipment to process the required data, and each train can be configured with its own independent dynamic model so that each train can predict its own operating status. During the unforming process, dynamic unforming is achieved through information exchange between adjacent trains.

[0051] In another possible implementation, each train is equipped with communication equipment, and each train's communication equipment can communicate with the server. The server is configured with the dynamic model of each train. The server receives the data sent by each train and processes it centrally. By distributing instructions to each train, the server centrally schedules the operation status of each train, thereby achieving dynamic decompilation and recompilation.

[0052] A server can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0053] In one exemplary embodiment, such as Figure 2 As shown, a method for dynamic ungrouping and regrouping of virtual train formations for heavy-haul trains is provided, including the following steps 10-50, wherein:

[0054] Step 10: In response to the uncoupling command for the target train, obtain the working status of the turnout mechanism, and obtain the operating status of the target train and the following train respectively; the following train is the train behind the target train.

[0055] In this embodiment, each train in the train formation has a corresponding transport route, and therefore each has an independent turnout mechanism. That is, the turnout mechanism at which each train is decoupled is predetermined; each train is associated with a decoupling position corresponding to the turnout mechanism required for its track change. For any train, changing track via the turnout mechanism requires reducing its speed to ensure a smooth and safe decoupling process. Therefore, for safety reasons, trains needing decoupling must prepare to slow down before their corresponding decoupling position to adjust their speed when passing through the turnout mechanism.

[0056] In one possible implementation, the control unit can be a server. Each train in the train formation can report its real-time location in real time. The server obtains the real-time location of each train in the train formation, determines the remaining journey of each train based on the real-time location of each train and the corresponding decoupling location of each train, and then identifies the train with the remaining journey less than or equal to a preset threshold as the target train and generates a decoupling instruction for the target train.

[0057] In another possible implementation, the control unit can be each train; for each train, the train itself can determine its remaining journey based on its real-time position and the corresponding decoupling position, and when the remaining journey is less than or equal to a preset threshold, the train is identified as the target train, and a decoupling instruction is generated and executed for the train (target train).

[0058] The working status of the turnout mechanism includes information such as temperature, load stress, and wear degree; the working status of the turnout mechanism is related to the time required to adjust the turnout; for example, if the current load stress of the turnout mechanism is large, the stress should be released first before adjusting the turnout mechanism to switch to another rail, which requires more time to adjust the turnout mechanism.

[0059] The following train refers to the train adjacent to the target train. Since adjacent trains can communicate with each other, the target train can request to obtain the operating status of the following train. The operating status includes parameters such as operating speed, acceleration, and the maximum braking distance at the operating speed, as well as the current real-time position.

[0060] Step 20: Determine the safety constraints based on the working status and the respective operating status of the target train and the following train.

[0061] In this embodiment, the safety constraint is used to constrain the distance between the following train and the target train at the beginning and end of the decoupling and rejoining of the target train. Since this application scenario targets the decoupling and rejoining of heavy-haul freight trains, which are characterized by large overall mass, high inertia, and difficulty in braking and deceleration; and since the speed of the train passing through the turnout mechanism needs to be controlled before the target train is decoupled, in order to control the distance between the following train and the target train, it is necessary to dynamically determine the safety constraint based on the time required for the turnout mechanism to adjust; how to determine the time required for the turnout mechanism to adjust (the actual adjustment time) based on the working state of the turnout mechanism will be explained in more detail in subsequent embodiments.

[0062] Step 30: Based on the safety constraints and the respective operating statuses of the target train and the following train, determine the control commands for the target train and the following train.

[0063] In this embodiment, the control command is used to apply traction or braking force to the train. The safety constraints include the desired interval distance before disassembly and the safe distance after disassembly. The desired interval distance refers to the minimum distance that the following train should maintain between the target train and the target train when the target train begins to enter the turnout mechanism for disassembly. The safe distance refers to the minimum distance that the target train and the following train should maintain when the target train has completely passed through the turnout mechanism and the disassembly is complete. These two distances included in the safety constraints together limit the safety between the target train and the following train before and after the disassembly process, thus preventing collisions.

[0064] Step 40: Using the train models of the target train and the following train respectively, verify the effectiveness of the control commands and obtain the verification results; the train model represents the impact of the control commands on the train's operating status.

[0065] Step 50: If the verification result is valid, execute the control commands for the target train and the following train respectively.

[0066] In the embodiments of this application, the train model corresponding to any train is a multi-mass dynamic model constructed based on the train's own characteristics. The input data of this model are control commands (parameters of traction or braking force) and real-time operating status; its output data is the predicted operating status of the train in future cycles. For the target train and the following train, their respective train models are used to process their respective control commands and real-time operating status to determine the predicted operating status of the target train and the following train, respectively.

[0067] Furthermore, based on the estimated operating status of the target train and the following train, it is determined whether the target train and the following train will meet the safety constraints in the future. If it is determined that the target train and the following train will meet the safety constraints in the future, the verification result is deemed valid. If it is determined that the target train and the following train will not meet the safety constraints in the future, the verification result is deemed invalid.

[0068] Once the verification results are confirmed to be valid, the target train and the following train are then controlled to execute their respective control commands, thereby achieving safe decoupling and uncoupling of the target train.

[0069] In the aforementioned method for dynamic de-staging of heavy-haul trains using virtual formation, the de-staging command indicates that the target train is about to begin de-staging. Based on the real-time operating status of the turnout mechanism and the respective operating statuses of the target train and its following trains, more accurate safety constraints for both the target and its following trains can be determined in real time. Simultaneously, control commands are generated for both the target and following trains based on these safety constraints, enabling safety control between them before and after de-staging to prevent collisions. Furthermore, after the effectiveness of each control command is verified using the corresponding train model for each train, the target and following trains execute the verified and reliable control commands, thereby enhancing safety between trains during the de-staging process.

[0070] In one embodiment, for any train, the train model corresponding to the train is a multi-mass point dynamic model constructed based on its own characteristics; wherein, the own characteristics include, but are not limited to, the train's mass distribution, traction force, braking force, overall resistance, braking characteristics and inertial delay.

[0071] Specifically, the acceleration of each car is calculated based on its mass, traction force, braking force, and overall resistance, quantifying the train's mass distribution, braking characteristics, and inertial delay. In essence, the "multi-mass point dynamics model" refers to modeling each car (or "mass point") in the train independently, considering factors such as mass, traction force, braking force, and resistance to calculate the motion state (e.g., acceleration, velocity) of each car. The motion of each car is determined by its own dynamic characteristics, while also being influenced by other cars; for example, the overall inertial effect of the train and the transmission of traction force.

[0072] The multi-mass point dynamics model is specifically used to accurately describe the inertial forces experienced by each carriage in a train during operation, the traction force output by the traction system, the braking force generated by the braking system according to control commands, and the comprehensive resistance composed of air resistance, track gradient, and track curvature. Each train is considered an independent mass point, and its dynamic equations are constructed based on Newton's second law. The traction force characteristics are determined according to the train's traction curve and are subject to power limitations; the braking force calculation incorporates the real-time relationship between brake cylinder pressure and brake shoe friction coefficient, and considers the long braking distance of heavy-load trains; the resistance calculation integrates the air resistance coefficient, the current track gradient, and the additional resistance caused by the curve radius.

[0073] Each train model operates in real time through its corresponding onboard computing unit, receiving traction or braking commands (and real-time operating status) as input and estimated operating status as output. The train model's parameters are loaded from the train's configuration file during system initialization and are calibrated online using data from various sensors configured on the train during operation, ensuring that the train model accurately reflects the dynamic characteristics of heavy-haul trains, which have large mass and high inertia.

[0074] Specifically, the train model corresponding to each train is represented by formula (1):

[0075] Formula (1); where, Let the mass of the i-th carriage be... Let be the speed of the i-th carriage. The derivative of velocity, i.e., acceleration; Let be the traction force acting on the i-th carriage. Let be the braking force exerted on the i-th carriage. Let be the running resistance experienced by the i-th carriage.

[0076] In one embodiment, such as Figure 3 As shown, in step 20, safety constraints are determined based on the working status and the respective operating statuses of the target train and the following train. Specifically, this may include steps 21-23, where:

[0077] Step 21: Based on the load information, temperature information, and wear degree of the turnout mechanism, correct the basic switching time of the turnout mechanism to obtain the actual switching time.

[0078] Specifically, the operating status of the turnout mechanism includes load information, temperature information, and wear level. Temperature information includes, but is not limited to, the temperature data of the turnout switch rails, the turnout drive unit, and the turnout sleepers. The wear level is determined based on historical wear data. Based on the real-time operating status of the turnout mechanism, load and wear corrections are applied to the basic switching time to obtain a more accurate and conservative actual switching time that matches the current actual load-bearing capacity and health condition of the turnout. The actual switching time represents the minimum time required to switch the turnout to a state where the target train can be decoupled.

[0079] Specifically, the actual switching time is determined by the turnout switching time adaptive model, which can be represented by formula (2); , formula (2).

[0080] in, This refers to the actual conversion time. Based on conversion time, This refers to the train weight factor determined based on the target train mass. The wear correction amount is determined based on the degree of wear, and k is the load factor.

[0081] Step 22: Determine the desired interval distance based on the actual conversion time, communication lag time, mechanical lag time, and the running status of the following train.

[0082] Specifically, the actual switching time of the dynamically adjusted turnout mechanism, the communication lag time caused by information transmission in the control system of the target train, and the mechanical lag time of the train's actuator are added together, multiplied by the current instantaneous speed of the following train, and a fixed safety margin is added on this basis to obtain the expected interval distance that meets the requirements for safe decoupling.

[0083] Specifically, the calculation logic of the expected interval distance can be expressed by formula (3);

[0084] Formula (3); where, The desired interval distance, In order to keep up with the speed of the train, This refers to the actual conversion time. For communication lag time, For mechanical lag time, This is a fixed safety margin; the safety margin can be set to 10 meters.

[0085] Step 23: Determine the maximum braking distance based on the operating status of the following train, and determine the safe driving distance based on the actual switching time, redundancy distance, and the operating status of the following train.

[0086] Specifically, based on the following train's travel distance during the turnout switching time, the following train's maximum braking distance at the current speed, and the safety protection distance, the safe driving distance after the decoupling is dynamically calculated; the calculation logic of the safe driving distance can be expressed by formula (4):

[0087] Formula (4); where, This is the maximum deceleration of the train (considering mass distribution and braking system response). The safe protection distance can be set to 5 meters.

[0088] Specifically, the safety constraints are updated once per detection cycle; the detection cycle can be set to 100 milliseconds to ensure adaptation to changes in the train's operating status.

[0089] In one embodiment, step 30 involves determining control commands for the target train and the following train based on safety constraints and the respective operating states of the target train and the following train. Specifically, this may include solving the objective function using the safety constraints and the respective operating states of the target train and the following train to obtain the control commands for the target train and the following train.

[0090] Specifically, the objective function is used to minimize the deviation between the actual interval and the expected safe interval between trains, minimize the deviation between the train speed and the turnout speed limit, and minimize the energy consumption caused by control commands; among them, the train models of the target train and the following trains, as well as the turnout speed limit, are used as constraints in the solution process.

[0091] The specific control logic is as follows: the target train accelerates appropriately before passing through the turnout mechanism to increase the distance between it and the following train. The following train begins to decelerate smoothly according to the expected separation interval calculated dynamically. The controllers configured on the target train and / or the following train solve a finite-time domain optimization objective function in each control cycle (200 milliseconds). During the solution process, the train model and the decoupled safe driving distance are treated as hard or soft constraints to generate the optimal control command (traction or braking).

[0092] Specifically, the deviation between the actual interval and the expected safe interval between trains is defined based on the actual position, safety margin, and displacement correction amount predicted by the train model of the target train and the following train, and can be expressed by formula (5). Based on the difference between the speed of the following train and the speed limit of the separating turnout, and by introducing acceleration tracking error to reflect the inertial effect, the deviation between the train speed and the turnout speed limit is determined; the deviation between the train speed and the turnout speed limit can be expressed by formula (6).

[0093] , formula (5);

[0094] , formula (6);

[0095] in, and These are the actual positions of the target train and the following train, respectively. The static desired separation interval, This refers to the inertial compensation amount (such as braking distance correction) based on train model predictions. The maximum permissible speed within the switch separation range. To follow the actual acceleration of the train, For the desired acceleration, These are the weighting coefficients.

[0096] When the target train approaches the turnout structure corresponding to the decoupling position, the distributed cooperative control system is activated. The target train and the following train exchange operating statuses in real time through onboard communication equipment. The controllers of each train in the train formation perform rolling optimization based on the following factors: the train model serves as the predictive model, and safety constraints serve as hard constraints. The control objectives include maintaining the desired interval distance, smoothly adjusting speed, and reducing control energy consumption to ensure the safe and efficient operation of the entire train formation, especially the safety between the target train about to be decoupled and the following train. A distributed multi-agent framework is configured among the trains in the train formation. This framework means that each train in the formation is independently configured with an agent. Each agent, based on its own operating status, the operating status of neighboring trains, and global safety objectives, performs calculations and decisions through its own controller, thereby achieving decentralized cooperative control without the need for a central controller or server.

[0097] In one embodiment, step 40 verifies the validity of the control command, and the verification result includes: predicting the position and speed trajectory of the target train and the following train in the future within each control cycle, and comparing the predicted trajectory with the expected interval distance in the latest determined safety constraint conditions. If it is predicted that the safety interval constraint may be violated at any time in the future, the verification result is determined to be characterized as failure.

[0098] Specifically, control commands for the target train and the following train are input into their respective train models to obtain the estimated operating states for each. Based on the operating states and estimated operating states of the target train and the following train, the estimated interval distance and estimated travel distance between them are determined. Then, based on the estimated interval distance, estimated travel distance, expected interval distance, and safe travel distance, the verification results are determined.

[0099] Furthermore, in the case where the verification result representation is invalid, a safety weight is added to the objective function to update the objective function and update the respective operating states of the target train and the following train; the safety weight is used to reduce the speed and / or acceleration of the following train; using the safety term constraints and the updated operating states of the target train and the following train, the updated objective function is solved to update the control commands for the target train and the following train.

[0100] During the decoupling process targeting the train, the safety monitoring module verifies the generated control commands in real time. Based on the current train status and commands issued by the control system, this module predicts the train trajectory within the next 30 seconds and compares it with the dynamic safety interval. If the prediction indicates a potential violation of safety constraints, the system immediately initiates countermeasures: first, it attempts to add safety weights to the control algorithm, recalculate the control commands, and re-verify them; if the risk still cannot be eliminated, a tiered alarm is triggered, and a control strategy is immediately activated within the current control cycle until the potential risk is eliminated.

[0101] Control strategies include, but are not limited to: increasing the weight of safety constraint terms in the objective function to force the controller to prioritize safety requirements, switching to a more conservative set of control parameters, or sending coordination requests to adjacent trains to jointly implement a more drastic deceleration strategy.

[0102] Switching to a more conservative set of control parameters means that each train can adjust its control strategy as needed to address potential safety risks. In a possible example: Suppose at some point the system predicts that the safe separation between the train ahead and the train behind may be insufficient. To ensure safety, the following train might "switch" to a more conservative set of control parameters. Specifically, the following train might reduce its acceleration or increase its braking force to ensure that the expected separation distance with the train ahead is not violated. In this case, the control system will ensure safety by adjusting the set of control parameters (e.g., reducing acceleration or increasing braking force).

[0103] In this embodiment, the framework of the distributed multi-agent system is as follows:

[0104] Intelligent Agent: Each train in the train formation is equipped with an independent intelligent agent, and each intelligent agent is equipped with a local controller and has autonomous decision-making capabilities;

[0105] Information interaction mechanism: Real-time sharing of operating status among intelligent agents is achieved through onboard communication equipment or trackside equipment configured in each vehicle, forming a decentralized collaborative network without the need for centralized command by a central controller;

[0106] Global safety objective fusion: Each agent calculates the optimal control command through its local controller based on its own vehicle state, the state of neighboring trains, and global safety constraints (such as turnout speed limits and safety constraints).

[0107] Model predictive control (MPC) cooperative controller:

[0108] Dynamics model integration: Based on the multi-mass dynamics model (train model) of the carriage level established in step one, predict the position and velocity trajectory of each vehicle in the next N steps (prediction time domain), and quantify the influence of traction force, braking force and comprehensive resistance on the motion state.

[0109] The train dynamics model can be simplified from a multi-mass point model to a segmented lumped mass model, or an equivalent model identified based on historical data can be adopted, and model errors can be compensated by increasing the safety margin.

[0110] Optimize the construction of the objective function:

[0111] Deviation minimization: Minimize the deviation between the actual interval of the trains in the queue and the expected safe interval calculated in step two to ensure longitudinal safety distance; minimize the deviation between the speed of each train and the speed limit of the turnout to avoid the risk of speeding;

[0112] Energy consumption optimization: Minimize the energy consumption of control commands (traction / braking) to improve the economy of the decoding process;

[0113] Hard / soft handling of constraints:

[0114] Hard constraints: The expected separation interval, the safe distance for train operation at the end of the decomposition and the turnout speed limit calculated in step two are embedded into the MPC optimization problem as inviolable constraints to ensure that the control commands strictly meet the safety requirements.

[0115] Soft constraints introduce slack variables into the objective function to flexibly handle constraints, preventing unsolvable optimization problems. They also adjust the priority of safety and efficiency through weighting coefficients. Specifically, by introducing slack variables, soft constraints relax some constraints in the optimization problem, allowing for certain deviations in some situations and preventing unsolvable problems. Slack variables make originally strict constraints more flexible, allowing for a certain degree of error, while weighting coefficients balance the priority of different objectives. For example, by adjusting the weights between safety and efficiency, the optimization algorithm can flexibly optimize other objectives, such as energy consumption or transportation efficiency, while meeting safety requirements. This method enables the optimization process to find the optimal solution in practical applications, ensuring the safety and efficiency of system operation even if some constraints cannot be strictly satisfied.

[0116] The virtual train formation and dynamic de-formation method for heavy-haul trains provided in this application, through the synergy of a multi-mass point dynamic model and adaptive turnout monitoring and actual conversion time calculation, can accurately predict the braking delay and travel distance changes caused by the large mass and high inertia of heavy-haul trains. Simultaneously, it can sense in real time the potential extension of turnout conversion time due to heavy load impact. This makes the system's set safety interval no longer a fixed theoretical value, but a dynamic safety red line closely tied to the real-time status of the train and turnouts, effectively avoiding rear-end collisions or turnout derailments caused by delayed response or untimely turnout conversion.

[0117] The distributed multi-agent system framework treats each train as an independent agent, coordinating through local computing and mutual communication. This architecture is naturally suitable for heavy-load train formations consisting of multiple power cars or complex disassembly and reassembly scenarios, solving the technical bottleneck of the inability to extend the simple front-to-rear control model in related technologies, and providing core technical support for more flexible transportation organization modes in the future.

[0118] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0119] Based on the same inventive concept, this application also provides a dynamic ungrouping device for implementing the above-mentioned dynamic ungrouping method for virtual formation of heavy-haul trains. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more dynamic ungrouping device embodiments provided below can be found in the limitations of the dynamic ungrouping method for virtual formation of heavy-haul trains above, and will not be repeated here.

[0120] In one exemplary embodiment, such as Figure 4 As shown, a dynamic decompression device 400 is provided, including a state monitoring module 401, a constraint determination module 402, a control module 403, a verification model 404, and an execution module 405, wherein:

[0121] The status monitoring module 401 is used to respond to the uncoupling command for the target train, obtain the working status of the turnout mechanism, and obtain the running status of the target train and the following train respectively; the following train is the train behind the target train.

[0122] The constraint determination module 402 is used to determine safety constraints based on the working status and the respective operating status of the target train and the following train. The safety constraints are used to constrain the distance between the following train and the target train at the beginning and end of the target train decoupling process.

[0123] The control module 403 is used to determine the respective control commands for the target train and the following train based on the safety constraints and the respective operating status of the target train and the following train. The control commands are used to apply traction or braking force to the train.

[0124] The verification module 404 is used to verify the effectiveness of the control commands using the respective train models of the target train and the following train, and to obtain the verification results; the train model represents the impact of the control commands on the train's operating state.

[0125] The execution module 405 is used to execute control commands for the target train and the following train respectively, provided that the verification result is valid.

[0126] In the aforementioned dynamic train decoupling device 400, the decoupling command indicates that the target train is about to begin decoupling. Based on the real-time operating status of the turnout mechanism and the respective operating statuses of the target train and the following train, more accurate safety constraints for the target train and its following train can be determined in real time. Simultaneously, control commands are generated for the target train and the following train based on the safety constraints, enabling safety control between the target train and the following train before and after the decoupling process, thereby preventing collisions. Furthermore, after the effectiveness of each control command is verified using the corresponding train model for each train, the target train and the following train execute the verified and reliable control commands, thus improving the safety between trains during the decoupling process.

[0127] In one embodiment, the operating status includes load information, temperature information, and wear degree of the turnout mechanism; the safety constraints include the expected interval distance before disassembly and the safe travel distance after disassembly; the constraint determination module 402 is specifically used for:

[0128] Based on the load information, temperature information, and wear degree of the turnout mechanism, the basic switching time of the turnout mechanism is corrected to obtain the actual switching time;

[0129] The desired interval distance is determined based on the actual conversion time, communication lag time, mechanical lag time, and the operating status of the following train.

[0130] The maximum braking distance is determined based on the operating status of the following train, and the safe driving distance is determined based on the actual switching time, redundancy distance, and the operating status of the following train.

[0131] In one embodiment, the train model is a multi-mass dynamic model constructed based on the train's mass distribution, traction force, braking force, combined resistance, braking characteristics, and inertial delay.

[0132] In one embodiment, the control module 403 is specifically used for:

[0133] By utilizing safety constraints and the respective operating states of the target train and the following train, the objective function is solved to obtain control commands for the target train and the following train.

[0134] The objective function is used to minimize the deviation between the actual interval and the expected safe interval between trains, minimize the deviation between the train speed and the turnout speed limit, and minimize the energy consumption caused by control commands. The train models of the target train and the following trains, as well as the turnout speed limit, are used as constraints in the solution process.

[0135] In one embodiment, the verification module 404 is specifically used for:

[0136] The control commands for the target train and the following train are input into their respective train models to obtain the estimated operating status for the target train and the following train.

[0137] Based on the respective operating status and estimated operating status of the target train and the following train, determine the estimated interval distance and estimated travel distance between the target train and the following train;

[0138] The verification results are determined based on the estimated interval distance, the estimated driving distance, the expected interval distance, and the safe driving distance.

[0139] In one embodiment, the dynamic decompression device 400 further includes an update module, specifically used for:

[0140] If the verification results are invalid, a safety weight is added to the objective function to update the objective function and update the operating states of the target train and the following train respectively; the safety weight is used to reduce the speed and / or acceleration of the following train.

[0141] By utilizing safety constraints and the updated operating states of the target train and the following train, the updated objective function is solved to update the control commands for the target train and the following train.

[0142] In one embodiment, the dynamic decoding device 400 further includes a monitoring module, specifically used for:

[0143] Obtain the real-time location of each train in the train formation;

[0144] The remaining journey of each train is determined based on its real-time location and its corresponding decoupling location.

[0145] Trains with remaining journey time less than or equal to a preset threshold are identified as target trains, and decoupling instructions are generated for the target trains.

[0146] Each module in the aforementioned dynamic decompilation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0147] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for the dynamic ungrouping and regrouping of virtual train formations. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0148] Those skilled in the art will understand that Figure 5The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0149] In one exemplary embodiment, a vehicle is provided, the vehicle being equipped with a computer device including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement any of the steps in the above embodiments of the virtual formation and dynamic unforming method for heavy-load trains.

[0150] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements any of the steps in the above embodiments of the virtual formation and dynamic unforming method for heavy-load trains.

[0151] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the steps in the above embodiments of the virtual formation and dynamic unforming method for heavy-load trains.

[0152] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0153] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0154] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0155] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for dynamic virtual formation and unforming of heavy-haul trains, characterized in that, The method includes: In response to the uncoupling command for the target train, the working status of the turnout mechanism is obtained, and the operating status of the target train and the following train are obtained respectively; the following train is the train behind the target train. Based on the working status and the respective operating statuses of the target train and the following train, safety constraints are determined; these safety constraints are used to constrain the distance between the following train and the target train at the beginning and end of the target train's decoupling phase. Based on the safety constraints and the respective operating states of the target train and the following train, control commands are determined for the target train and the following train, and the control commands are used to apply traction or braking force to the train. The effectiveness of the control command is verified using train models of both the target train and the following train, and the verification results are obtained; the train model represents the impact of the control command on the train's operating state. If the verification result is valid, execute the control commands for the target train and the following train respectively.

2. The method according to claim 1, characterized in that, The operating status includes load information, temperature information, and wear degree of the turnout mechanism; the safety constraints include the expected interval distance before decoupling and the safe train distance after decoupling; determining the safety constraints based on the operating status and the respective operating statuses of the target train and the following train includes: Based on the load information, temperature information, and wear level of the turnout mechanism, the basic switching time of the turnout mechanism is corrected to obtain the actual switching time; The desired interval distance is determined based on the actual conversion time, communication lag time, mechanical lag time, and the operating status of the following train. The maximum braking distance is determined based on the operating status of the following train, and the safe driving distance is determined based on the actual switching time, the redundancy distance, and the operating status of the following train.

3. The method according to claim 2, characterized in that, The train model is a multi-mass point dynamic model constructed based on the train's mass distribution, traction force, braking force, combined resistance, braking characteristics, and inertial delay.

4. The method according to claim 2 or 3, characterized in that, The step of determining control commands for the target train and the following train based on the safety constraints and the respective operating states of the target train and the following train includes: Using the safety constraints and the respective operating states of the target train and the following train, the objective function is solved to obtain the control commands for the target train and the following train; The objective function is used to minimize the deviation between the actual interval between trains and the desired safe interval, minimize the deviation between the train speed and the turnout speed limit, and minimize the energy consumption caused by the control command; wherein the train model of the target train and the following train, as well as the turnout speed limit, are used as constraints in the solution process.

5. The method according to claim 4, characterized in that, The effectiveness of the control command is verified using the train models of the target train and the following train, and the verification results are obtained, including: The control commands for the target train and the following train are input into their respective train models to obtain the estimated operating status for the target train and the following train. Based on the respective operating status and estimated operating status of the target train and the following train, the estimated interval distance and estimated travel distance between the target train and the following train are determined; The verification result is determined based on the estimated interval distance, the estimated driving distance, the expected interval distance, and the driving safety distance.

6. The method according to claim 5, characterized in that, The method further includes: If the verification result is invalid, a safety weight is added to the objective function to update the objective function, and the operating states of the target train and the following train are updated respectively; the safety weight is used to reduce the speed and / or acceleration of the following train. Using the safety constraints and the updated operating states of the target train and the following train, the updated objective function is solved to update the control commands for the target train and the following train.

7. The method according to claim 1, characterized in that, The method further includes: Obtain the real-time location of each train in the train formation; Based on the real-time location of each train and the corresponding decoupling location of each train, the remaining journey of each train is determined; Trains with remaining journey time less than or equal to a preset threshold are identified as target trains, and decompilation instructions are generated for the target trains.

8. A dynamic decoding / uncoding device, characterized in that, The device includes a status monitoring module, a constraint determination module, a control module, a verification model, and an execution module, wherein: The status monitoring module is used to respond to the decoupling command for the target train, obtain the working status of the turnout mechanism, and obtain the running status of the target train and the following train respectively; the following train is the train behind the target train. The constraint determination module is used to determine safety constraints based on the working state and the respective operating states of the target train and the following train; the safety constraints are used to constrain the distance between the following train and the target train at the beginning and end of the target train decoupling phase. The control module is used to determine control commands for the target train and the following train respectively based on the safety constraints and the respective operating states of the target train and the following train. The control commands are used to apply traction or braking force to the train. The verification module is used to verify the effectiveness of the control command using the respective train models of the target train and the following train, and to obtain the verification result; the train model represents the impact of the control command on the operating state of the train. The execution module is configured to execute the control commands for the target train and the following train respectively, provided that the verification result is valid.

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

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images