Virtual marshalling simulation method and device, computer equipment, readable storage medium and program product

Abstract

This application relates to a virtual train formation simulation method, apparatus, computer equipment, computer-readable storage medium, and computer program product. The method includes: loading a multi-objective optimization model; the multi-objective optimization model is constructed based on constraints of energy consumption, coupler force impact, distance, and acceleration; optimizing each train according to the constraints of the multi-objective optimization model to obtain the corresponding operation control sequence for each train; and determining the target control information for each train based on the operation control sequence. This method can improve the accuracy of the target control information.

Description

Technical Field

[0001] This application relates to the field of rail transit technology, and in particular to a virtual train formation simulation method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of heavy-haul trains and vehicle scheduling technology, heavy-haul trains have shifted from using physical formation to using virtual formation. In order to evaluate the virtual formation, it is necessary to evaluate the results of the virtual formation of heavy-haul trains.

[0003] In traditional technology, the terminal determines the control commands for each vehicle based on speed constraints, and calculates the safe protection speed of the following vehicle corresponding to each preceding vehicle in the virtual train formation based on the control commands. The target control information of the following vehicle is obtained from the safe protection speed. The safe protection speed is the maximum speed at which the following vehicle can safely travel at the current moment. The actual operating speed of the following vehicle cannot exceed this safe protection speed; otherwise, the ATP (Automatic Train Protection) speed monitoring system will send a protection control command to make the train take braking measures.

[0004] However, in traditional simulation methods, the factors considered in determining the control command method for each vehicle based on speed constraints are relatively singular, resulting in poor accuracy of the target control information obtained from the simulation. Summary of the Invention

[0005] Therefore, it is necessary to provide a virtual grouping simulation method, apparatus, computer equipment, computer-readable storage medium, and computer program product to address the aforementioned technical problems.

[0006] In a first aspect, this application provides a virtual grouping simulation method, which is applied to a virtual grouping simulation platform and includes:

[0007] Load a multi-objective optimization model; the multi-objective optimization model is constructed based on energy consumption index constraints, coupler force impact index constraints, distance index constraints, and acceleration index constraints;

[0008] Based on the multi-objective optimization model, the energy consumption index, coupler force impact index, distance index and acceleration index of each train are constrained and optimized to obtain the corresponding operation control sequence of each train;

[0009] The target control information for each train is determined based on the operation control sequence.

[0010] In one embodiment, the step of performing constraint optimization on each train based on a multi-objective optimization model for energy consumption, coupler force impact, distance, and acceleration indicators to obtain the corresponding operation control sequence for each train includes:

[0011] Obtain the current status information of each train;

[0012] Based on the current state information, the future state information of each train in the preset time domain is predicted to obtain the future state information;

[0013] Based on the multi-objective optimization model and the future state information, iterative optimization of energy consumption index, coupler force impact index, distance index and acceleration index is performed to obtain the operation control sequence corresponding to each train.

[0014] In one embodiment, prior to loading the multi-objective optimization model, the method further includes:

[0015] Obtain the preset grouping plan;

[0016] Establish the correlation between the target leading vehicle and the target trailing vehicle in the preset train formation plan; the correlation is used as input to the multi-objective optimization model as the basis for constrained optimization.

[0017] In one embodiment, determining the target control information for each of the trains based on the operation control sequence includes:

[0018] The target position of the target train to be braked is determined based on the operation control sequence; the target position is the braking endpoint after the target train is braked.

[0019] For each target train, a target following train is correspondingly assigned to a target train. The safe operating status of each target following train is calculated based on the target position.

[0020] Target control information is determined based on the aforementioned safe operating status.

[0021] In one embodiment, the method further includes:

[0022] If the train's driving mode is automatic driving mode, the corresponding status information of the train is obtained according to the automatic control system;

[0023] If the train's driving mode is console driving mode, the corresponding status information of the train is obtained according to the console command.

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

[0025] If the train formation mode is non-virtual formation, the control optimization of each train is performed based on the single-objective optimization model and the state information of each train to obtain the operation control sequence corresponding to each train.

[0026] Secondly, this application also provides a virtual grouping simulation device, comprising:

[0027] A loading module is used to load a multi-objective optimization model; the multi-objective optimization model is constructed based on energy consumption index constraints, coupler force impact index constraints, distance index constraints, and acceleration index constraints.

[0028] The first optimization module is used to perform constraint optimization on the energy consumption index, coupler force impact index, distance index and acceleration index of each train according to the multi-objective optimization model, so as to obtain the corresponding operation control sequence of each train.

[0029] The calculation module is used to determine the target control information for each of the trains based on the operation control sequence.

[0030] In one embodiment, the first optimization module is specifically used to obtain the current status information of each train;

[0031] Based on the current state information, the future state information of each train in the preset time domain is predicted to obtain the future state information;

[0032] Based on the multi-objective optimization model and the future state information, iterative optimization of energy consumption index, coupler force impact index, distance index and acceleration index is performed to obtain the operation control sequence corresponding to each train.

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

[0034] The first acquisition module is used to acquire the preset grouping plan;

[0035] The construction module is used to establish the relationship between the target leading vehicle and the target trailing vehicle in the preset formation plan; the relationship is used as input to the multi-objective optimization model as the basis for constraint optimization.

[0036] In one embodiment, the calculation module is specifically used to determine the target position of the target train to be braked based on the operation control sequence; the target position is the braking endpoint after the target train is braked.

[0037] For each target train, a target following train is correspondingly assigned to a target train. The safe operating status of each target following train is calculated based on the target position.

[0038] Target control information is determined based on the aforementioned safe operating status.

[0039] In one embodiment, the device further includes:

[0040] The second acquisition module is used to acquire the corresponding status information of the train according to the automatic control system if the driving mode of the train is automatic driving mode.

[0041] The third acquisition module is used to acquire the corresponding status information of the train according to the console command if the train's driving mode is console driving mode.

[0042] In one embodiment, the device further includes:

[0043] The second optimization module is used to optimize the control of each train according to the single-objective optimization model and the state information of each train if the train formation mode is non-virtual formation, so as to obtain the operation control sequence corresponding to each train.

[0044] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0045] Load a multi-objective optimization model; the multi-objective optimization model is constructed based on energy consumption index constraints, coupler force impact index constraints, distance index constraints, and acceleration index constraints;

[0046] Based on the multi-objective optimization model, the energy consumption index, coupler force impact index, distance index and acceleration index of each train are constrained and optimized to obtain the corresponding operation control sequence of each train;

[0047] The target control information for each train is determined based on the operation control sequence.

[0048] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0049] Load a multi-objective optimization model; the multi-objective optimization model is constructed based on energy consumption index constraints, coupler force impact index constraints, distance index constraints, and acceleration index constraints;

[0050] Based on the multi-objective optimization model, the energy consumption index, coupler force impact index, distance index and acceleration index of each train are constrained and optimized to obtain the corresponding operation control sequence of each train;

[0051] The target control information for each train is determined based on the operation control sequence.

[0052] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0053] Load a multi-objective optimization model; the multi-objective optimization model is constructed based on energy consumption index constraints, coupler force impact index constraints, distance index constraints, and acceleration index constraints;

[0054] Based on the multi-objective optimization model, the energy consumption index, coupler force impact index, distance index and acceleration index of each train are constrained and optimized to obtain the corresponding operation control sequence of each train;

[0055] The target control information for each train is determined based on the operation control sequence.

[0056] The aforementioned virtual train formation simulation method, apparatus, computer equipment, computer-readable storage medium, and computer program product load a multi-objective optimization model. This model is constructed based on constraints related to energy consumption, coupler force impact, distance, and acceleration. The model optimizes the energy consumption, coupler force impact, distance, and acceleration constraints for each train, resulting in a corresponding operational control sequence for each train. The target control information for each train is then determined based on these operational control sequences. This method optimizes the operational control of each train using the constraints of the multi-objective optimization model, ensuring that the trains adapt to constantly changing operating conditions and that the operational control sequences of each train satisfy the constraints of the multi-objective optimization. This improves the accuracy of the train operational control sequences, and consequently, the accuracy of the target control information for each train can be further improved by determining these sequences. Attached Figure Description

[0057] 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.

[0058] Figure 1 This is a flowchart illustrating a virtual grouping simulation method in one embodiment;

[0059] Figure 2 This is a schematic diagram of train onboard information interaction in a virtual formation mode, as shown in one embodiment.

[0060] Figure 3 This is a schematic diagram of train onboard information interaction in a non-virtual formation mode in one embodiment;

[0061] Figure 4 This is an architecture diagram of a virtual marshalling platform in one embodiment;

[0062] Figure 5 This is a schematic diagram of a process for constrained optimization of a train based on a multi-objective optimization model in one embodiment;

[0063] Figure 6 This is a flowchart illustrating the ATO (Automatic Train Operation) control system in a virtual grouping operation platform in one embodiment.

[0064] Figure 7 This is a flowchart illustrating the process of establishing the relationship between a target preceding vehicle and a target following vehicle in one embodiment.

[0065] Figure 8 This is a schematic diagram illustrating the overall operation of the virtual grouping simulation platform in one embodiment;

[0066] Figure 9 This is a schematic diagram illustrating the process of train formation and de-formation using a virtual train formation simulation platform in one embodiment.

[0067] Figure 10 This is a flowchart illustrating the calculation of target control information based on a running control sequence in one embodiment;

[0068] Figure 11 This is a flowchart illustrating the ATP speed monitoring system in a virtual grouping operation platform in one embodiment;

[0069] Figure 12 This is a schematic diagram of the process for obtaining train status information in one embodiment;

[0070] Figure 13 This is a structural block diagram of a virtual grouping simulation device in one embodiment;

[0071] Figure 14 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0072] 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.

[0073] In one embodiment, such as Figure 1 As shown, a virtual grouping simulation method is provided. This embodiment illustrates the application of this method to a virtual grouping simulation platform in a terminal. It is understood that this method can also be applied to a server, and to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0074] Step 102: Load the multi-objective optimization model.

[0075] The multi-objective optimization model is constructed based on constraints of energy consumption index, coupler force impact index, distance index, and acceleration index.

[0076] In this embodiment, the train used for virtual train formation simulation can be a heavy-haul train. For the virtual train formation simulation of heavy-haul trains, the virtual train formation simulation platform, under the monitoring of the ATP speed monitoring system, can implement automatic train operation according to the ATO (Automatic Train Operation) automatic control system, including automatic departure from stations, automatic operation between sections, automatic stopping at stations, and heavy-haul automatic operation functions, thereby simulating the heavy-haul train. The virtual train formation simulation platform monitors each train according to the ATP speed monitoring system.

[0077] In the process of realizing automatic train operation based on the ATO automatic control system, for heavy-haul trains in virtual formation, the virtual formation simulation platform first loads a multi-objective optimization model into the virtual formation simulation platform. In the ATO automatic control system, the multi-objective optimization model is applied to optimize the control of the heavy-haul train, so that the operation of the heavy-haul train reaches the optimal state under multi-objective constraints.

[0078] In a specific embodiment, if a total of N trains are configured in the virtual train formation simulation platform, when the virtual train formation mode is selected, as follows: Figure 2 As shown, trains 1, 2, ..., N will form a convoy in a virtual formation. The onboard equipment of the lead car, car 2, ..., car N represents the onboard equipment of each car within the convoy. The onboard equipment of each train communicates with each other; that is, each following car communicates with the onboard system of its preceding car. The preceding car sends its current position and speed information to the following cars, and the following cars calculate the protection speed based on the information provided by the preceding car. When the virtual formation mode is not selected in the virtual formation simulation platform, such as... Figure 3 As shown, each train departs in sequence, and there is no communication between the onboard equipment; each vehicle communicates with its own onboard system.

[0079] In one exemplary embodiment, such as Figure 4As shown, the virtual train formation simulation platform includes a train driver's cab interface, a CTC (Centralized Traffic Control) dispatching and centralized control system, a data visualization and analysis system, a multi-mass dynamic model of heavy-haul trains, an ATP speed monitoring system, an ATO automatic control system, a Radio Block Center (RBC), an interlocking system, and trackside equipment simulation. The system includes: a train driver's cab interface for displaying vehicle status, configuring train data, and issuing operational commands; a centralized control system (CTC) for direct command and management of train operations, including dispatching, train planning and route control, shunting planning and route control, and CTC display and control functions; a data visualization and analysis system for displaying the current train position, system communication status and content, relevant train configuration parameters, coupler forces between multiple trains, train operation logs, and operational details for different scenarios; a multi-mass dynamics model for heavy-haul trains, treating each train car as a point mass, analyzing the resistance, traction, and braking forces acting on the train, and updating the speed, displacement, and acceleration of each vehicle, and calculating the coupler forces between vehicles; and an ATP speed monitoring system for determining a safe braking model based on actual conditions, addressing the fluctuations of heavy-haul trains. The diverse environmental conditions, such as slopes, long downhill sections, bridges, and tunnels, affect the safety of heavy-haul trains, forming safety protection curves under multiple scenarios. The Automatic Train Operation (ATO) system is used to realize automatic train operation, including automatic departure from stations, automatic operation in sections, automatic stopping at stations, and automatic heavy-haul operation. The Radio Block Center (RBC) provides trains with safe driving permission within its jurisdiction and transmits track information to ensure real-time two-way communication between the train and the RBC and adjacent RBCs, enabling precise train operation control and monitoring across regions. The interlocking system ensures the safe operation of trains on the track by preventing train collisions, entering occupied tracks, or speeding through the mutual constraints of signals, switches, and routes, while providing trains with safe routes. Trackside equipment simulation replaces the role of track circuits and transponders in actual lines, simulating track data, section occupancy, signal and switch status changes, and malfunctions.

[0080] Step 104: Based on the multi-objective optimization model, constrain the energy consumption index, coupler force impact index, distance index and acceleration index of each train to obtain the corresponding operation control sequence of each train.

[0081] In this embodiment, the ATO automatic control system of the virtual train formation simulation platform optimizes the energy consumption index, coupler force impact index, distance index, and acceleration index of each train based on the objective function of the multi-objective optimization model and in combination with the track information and vehicle status information, thereby obtaining the corresponding operation control sequence for each train. The objective function is shown in the following formula (1):

[0082] (1)

[0083] in, Let be the energy consumption of the i-th vehicle. For ideal energy consumption, Let the impact index of the coupling force of the i-th vehicle be . Let be the distance between the i-th car and the car in front. For a safe distance, Let be the acceleration of the i-th vehicle. These are the weighting coefficients.

[0084] In virtual train formation mode, the ATO automatic control system uses the MPC (Model Predictive Control) algorithm to calculate the optimal control commands. The MPC algorithm can calculate a series of control commands based on the current state of the train and predictions of the future, thus obtaining the corresponding operation control sequence for each train.

[0085] Step 106: Determine the target control information for each train based on the operation control sequence.

[0086] In this embodiment, the ATO (Automatic Train Control) system receives a generated operation control sequence, which contains control command information for the train at various times within a future period. The ATO system first parses the operation control sequence, identifying the specific type of each command, such as traction, braking, and cruise commands, and determining the corresponding parameters, such as traction power, braking force, and cruise speed. This operation control sequence is derived based on optimization considerations of train operation energy consumption, coupler force impact, inter-vehicle distance, and acceleration, representing the optimal operating mode for the train under different conditions.

[0087] In one specific embodiment, the ATO (Automatic Train Control) system determines the target control information by combining the train's actual operating status. The train's actual operating status includes its current position, speed, acceleration, and energy consumption, which is obtained through communication with other modules of the onboard system and interaction with the multi-mass model of the heavy-haul train. Taking the train's current speed as an example, if the operation control sequence requires the train to reach a specific target speed at a certain moment, the ATO system calculates the required traction or braking force based on the train's current actual speed, thereby adjusting the speed. Different types of trains have different characteristics in their power and braking systems, and the ATO system adjusts accordingly. For example, for a more powerful train, achieving the same speed change may require a smaller traction or braking adjustment; while for a less powerful train, more precise control of traction and braking is needed. Optionally, in determining the target control information, the ATO system also considers track conditions and safety requirements, i.e., control is performed under the constraints of the ATP (Automatic Train Protection) speed monitoring system. Track conditions include track length, gradient, curvature, etc., which affect the train's running resistance and safety. For example, on uphill sections, trains require greater traction to overcome the effects of gravity; on curves, trains need to appropriately reduce speed to ensure safe passage. Simultaneously, safety is the primary consideration, and the ATO (Automatic Train Control) system adjusts its target control information based on the protective commands and safe braking model from the ATP (Automatic Train Protection) speed monitoring system. If the ATP speed monitoring system issues an emergency braking command, the ATO system adjusts its target control information to parameters relevant to emergency braking to ensure the safety of train operation.

[0088] The data visualization and analysis system incorporates virtual train formation status information, including formation number, train number, position of each train within the formation, maximum coupler force, and communication status, to evaluate the simulation results. Additionally, the driver's cab allows users to perform formation and de-formation operations within the track area where virtual formation is possible.

[0089] In the aforementioned virtual train formation simulation method, the energy consumption index, coupler force impact index, distance index, and acceleration index constraints of the multi-objective optimization model are used to optimize the control of each train, thereby obtaining the corresponding operation control sequence for each train. This ensures that the train always adapts to the constantly changing operating conditions and that the operation control sequence of each train satisfies the constraints of the multi-objective optimization, which can improve the accuracy of the train operation control sequence. Furthermore, the target control information of each train can be determined based on the operation control sequence, which can improve the accuracy of the target control information.

[0090] In one exemplary embodiment, such as Figure 5 As shown, step 104 includes steps 502 to 506. Wherein:

[0091] Step 502: Obtain the current status information of each train.

[0092] In the embodiments of this application, such as Figure 6 As shown, the ATO automatic control system of the virtual train formation simulation platform adopts a multi-threaded parallel mode. The ATO automatic control system communicates with the on-board system of each train to obtain the operating mode (whether it is a virtual train formation) and ATP protection curve command of each train. When it is confirmed that the current trains are in a virtual train formation, the ATO automatic control system confirms that the communication between each train is the communication between the preceding and following trains.

[0093] Specifically, in response to the train start command from the train's driver's console interface, the ATO (Automatic Train Operation) system loads train configuration data, including information such as train type and number of trains. Simultaneously, the ATO system loads track information, such as track length, gradient, and curvature, as these characteristics significantly impact train operating energy consumption and speed. Furthermore, the ATO system obtains the current state information of each train using a multi-mass model of the heavy-haul train. This current state information includes the train's position, speed, acceleration, and energy consumption, serving as the data foundation for multi-objective optimization calculations.

[0094] Step 504: Based on the current state information, predict the future state information of each train within the preset time domain to obtain the future state information.

[0095] In this embodiment, the ATO (Automatic Train Operation) control system predicts the future state of each train within a preset time domain based on the current state information, the dynamic model of each train, and the track information. For example, based on the train's current speed, acceleration, and track gradient information, the ATO control system can predict the train's speed change over a period of time; based on the train's position and the track's curvature information, it can predict the train's trajectory and the required steering control. The train's dynamic model describes the train's motion under different operating conditions, and the track information reflects the external environment of each train's operation. By combining the track information and the dynamic model as the basis for prediction, the future state information of each train within the preset time domain is obtained.

[0096] Step 506: Based on the multi-objective optimization model and future state information, perform constrained iterative optimization of energy consumption index, coupler force impact index, distance index and acceleration index to obtain the corresponding operation control sequence for each train.

[0097] In this embodiment, the ATO automatic control system can use the objective function in step 104 as a constraint of the multi-objective optimization model, and input the future state information corresponding to each train into the multi-objective optimization model. Simultaneously, it uses energy consumption indicators, coupler force impact indicators, distance indicators, and acceleration indicators as constraints to iteratively optimize the train's control parameters (e.g., traction power, braking force, etc.) so that the objective function... The system gradually narrows down the objective function and determines whether it meets the requirements based on preset constraints. If the objective function does not meet the requirements, the ATO (Automatic Train Control) system continuously adjusts the control parameters and recalculates until the objective function converges or reaches the preset number of iterations, thus obtaining the operation control sequence for each train that satisfies the multi-objective constraints. , as the optimal control sequence.

[0098] In this embodiment, the future state within a preset time domain is predicted based on the current state information of the train, taking into account dynamic factors such as track conditions that the train may encounter during operation. This provides a more comprehensive and accurate data foundation for subsequent optimization. Then, using a multi-objective optimization model and future state information, constrained iterative optimization is performed on energy consumption, coupler force impact, distance, and acceleration indicators to obtain the operation control sequence of each train. This operation control sequence comprehensively balances multiple indicators, enabling the train to achieve the best overall operation effect in terms of energy consumption, coupler force impact, inter-train distance, and acceleration. Finally, the target control information is determined using this operation control sequence, improving the accuracy of the target control information.

[0099] In one exemplary embodiment, before performing the simulation, the virtual grouping simulation platform needs to preload relevant information about the virtual grouping, such as... Figure 7 As shown, before step 102, the method further includes steps 702 to 704. Wherein:

[0100] Step 702: Obtain the preset grouping plan.

[0101] In this embodiment, the preset train formation plan is formulated by simulation personnel based on various factors such as actual transportation needs, train operation arrangements, and line conditions. During the operation of the virtual train formation simulation platform, when the train completes the relevant parameter configuration and mode selection and is about to enter the operation or formation operation stage, the virtual train formation simulation platform actively acquires the preset train formation plan. The preset train formation plan contains detailed formation information, such as the number of vehicles and vehicle types in each virtual train formation, and the specific position of each train in the formation. The preset train formation plan is crucial for train operation control and optimization, as it determines the cooperation method between trains, energy distribution, and the setting of safety distances. By acquiring the preset train formation plan, the platform can clearly understand the train formation intention, providing a clear direction for subsequent train state control and multi-objective optimization.

[0102] In a specific embodiment, such as Figure 8 As shown, thread one of the virtual train formation simulation platform first obtains the current train status information from the multi-mass model of the heavy-load train, including speed, displacement, and coupler force. If it is in virtual formation mode, it will also obtain information such as the formation number. Then, it sends this train status information to the required modules. When the simulation user chooses to end the program, the sending stops. Thread two of the virtual train formation simulation platform first puts the train into standby mode to wait for instructions. The simulation user can choose whether to end the program. If not, the virtual train formation simulation platform obtains the train parameters and the preset formation plan (formation mode) and sends them to the onboard equipment. Then the train starts running and determines whether to use automatic driving mode. If automatic driving is used, the train is driven under the monitoring of the ATP speed monitoring system by pressing the control command of the ATO automatic control system, and it is determined whether to receive a command from the driver's console to decide whether to switch to the driving mode under the monitoring of the ATP speed monitoring system according to the console. If automatic driving is not used, the train is driven under the monitoring of the ATP speed monitoring system by pressing the control command of the console. Then it will determine whether the train should stop, whether to perform formation or deformation operations, and enter standby mode according to different situations, continue to determine automatic driving mode, or perform formation or deformation.

[0103] Step 704: Establish the relationship between the target leading vehicle and the target trailing vehicle in the preset formation plan.

[0104] The correlation relationship is used as input to the multi-objective optimization model as the basis for constrained optimization.

[0105] In this embodiment, after the train formation is determined by the preset formation plan, the virtual formation simulation platform clarifies the relationship between the target preceding and following trains within each formation. This relationship involves communication between trains, collaborative control, and constraint settings in the multi-objective optimization model. Furthermore, this relationship is used as input to the multi-objective optimization model as the basis for constraint optimization. That is, when optimizing train operating energy consumption, coupler force impact, train-to-train distance, and acceleration, the virtual formation simulation platform needs to consider the mutual influence and cooperation requirements between the preceding and following trains.

[0106] To establish the relationship between the leading and trailing trains, the virtual train formation simulation platform first determines the leading and trailing trains within each train formation based on a pre-set formation plan. Then, the platform uses a multi-mass model of the heavy-haul train to acquire the state information of the leading and trailing trains, such as speed, displacement, and coupler force. Based on this state information, the platform analyzes the dynamic relationship between the leading and trailing trains, such as the impact of the leading train's speed changes on the trailing train and the required safe distance between them. During the process of establishing this relationship, the platform sets corresponding constraints for each train-leading pair, such as the trailing train's speed not exceeding a certain range from the leading train and the distance between them maintaining a safe level. These constraints are input into a multi-objective optimization model to ensure that the train can operate collaboratively according to the pre-set formation requirements and safety rules during the optimization process.

[0107] In an optional embodiment, such as Figure 9 As shown, for virtual train formation operations, when a train in the virtual train formation simulation platform receives a formation command, the CTC (Centralized Control System) first sends a detailed formation plan to the trains that need to be formed. This formation plan specifies the specific requirements and arrangements for train formation. Then, the trains receiving the formation plan enter the designated formation area to prepare for the formation operation.

[0108] Within the formation area, according to the formation plan, the trains ahead and behind establish car-to-car communication, enabling them to exchange information in real time and ensuring coordinated operation. Establishing car-to-car communication is a crucial step in the formation process, guaranteeing the coordinated operation of the trains. Once car-to-car communication is established, the formation operation is considered complete. At this point, the train begins operation and enters step four of thread two, which involves determining whether the train should use automatic driving mode and other subsequent operational procedures. Simultaneously, the train sends the formation number and the positions of the cars within the formation to the platform for effective management and monitoring. Finally, the RBC (Radio Block Center) treats the entire virtual train formation as a single train unit, issuing a travel permit to allow the train formation to travel safely on the track.

[0109] For the virtual train formation decoupling operation, the decoupling process begins upon receiving the decoupling command. First, the CTC sends a decoupling plan, specifying the details and requirements for train decoupling. Each train within the decoupling formation arrives at its designated decoupling position sequentially according to the plan. Upon arrival at the decoupling position, the trains in front and behind disconnect from each other. Since the number of trains in the formation is n, this disconnection operation is repeated n-1 times to ensure each train can be successfully decoupled. After decoupling, each train begins independent operation, following its own operational strategy. Subsequently, the data visualization system initializes virtual train formation information, clearing previous formation data to prepare for possible subsequent formation operations. Finally, the RBC sends travel permits to each independently operating train, ensuring that each train can travel safely and independently on the track.

[0110] In this embodiment, by acquiring a preset train formation plan and establishing the relationship between the target preceding train and the target following train, the virtual train formation simulation platform can more accurately simulate the coordinated operation of train formations, optimize key indicators such as train operating energy consumption, coupler force impact, train-to-train distance and acceleration, improve the operating efficiency and accuracy of the virtual train formation simulation platform, and provide a reliable reference for train formation optimization and safety control in actual transportation.

[0111] In one exemplary embodiment, the virtual train formation simulation platform ensures the safe operation of each train according to the ATP speed monitoring system, such as... Figure 10 As shown, step 106 includes steps 1002 to 1006. Wherein:

[0112] Step 1002: Determine the target position of the target train to be braked based on the operation control sequence.

[0113] The target location is the braking endpoint after the target train applies the brakes.

[0114] In this embodiment of the application, in the entire train operation control system, the operation control sequence is a set of control instructions for train operation obtained through a multi-objective optimization model and related prediction algorithms. The operation control sequence specifies the operating status of each train at different times, including when to perform traction, braking or maintain cruise state, etc.

[0115] like Figure 11As shown, in the ATP speed monitoring system, after its execution, the system first communicates with the driver (control console) to obtain train configuration data and whether a virtual formation mode has been selected. Next, it enters the stage of acquiring train status information. In virtual formation mode, the following train communicates with the preceding train's onboard system to obtain its status information and with its own vehicle simulation system (i.e., the multi-mass model of the heavy-haul train) to obtain its own status information. In non-virtual formation mode, it only communicates with its own vehicle simulation system to obtain train status information. Afterward, the ATP speed monitoring system communicates with the RBC module, reporting train position, speed, and class conversion information. Finally, it receives MA (Movement Authority) and temporary speed limit information from the RBC. When it is necessary to determine the target position of the train to be braked, the ATP speed monitoring system of the virtual formation simulation platform calculates based on the train's operation control sequence. The target position refers to the braking endpoint of the target train after braking. The operational control sequence includes information such as train speed and acceleration. Combined with the train's dynamic model and current track conditions (e.g., gradient, curves), calculations are used to infer the final stopping position of the target train after braking begins, thus obtaining the target position. Determining this target position is a crucial foundation for ensuring the safe operation of the train, providing a key reference point for assessing the safe operating status of the train following the target.

[0116] Step 1004: For each target train, calculate the safe operating status of the target train based on the target position.

[0117] In this embodiment of the application, for the virtual train formation, the ATP speed monitoring system of the virtual train formation simulation platform uses the "collision with a soft wall" safety protection method for calculation. That is, if the preceding train immediately implements emergency braking at the current moment, the end point of the emergency braking is taken as the target position, the safety protection speed of the current train is calculated, and the calculation result is sent to the ATO automatic control system. The calculation formula is shown in the following formula (2):

[0118] (2)

[0119] in, The vehicle in front is the car. "Car" represents the following car, and "T" represents the stopping time of the following car. This indicates a safety margin. , It is the error in train speed measurement and positioning. It's the position of the rear of the car in front. It's the position of the front of the car behind. , It is the speed and acceleration of the car in front. , It refers to the speed and acceleration of the following vehicle.

[0120] Furthermore, the virtual train formation simulation platform calculates the safe operating status of each target train's corresponding target following car based on the ATP speed monitoring system's target position. This safe operating status can be the speed and acceleration of each following car.

[0121] Step 1006: Determine target control information based on safe operating status.

[0122] In this embodiment, after obtaining the safe operating status of the target train, the ATO (Automatic Train Operation) system of the virtual train formation simulation platform determines the target control information for each train based on the safe operating status. The target control information consists of specific instructions used to actually control the train's operation, such as the magnitude of traction power and braking force.

[0123] The virtual train formation simulation platform, based on the target train's safe operating status parameters such as safe speed and safe acceleration, performs corresponding conversions and calculations to derive specific control parameters that enable the train to achieve and maintain a safe operating state. These control parameters are then sent as target control information to the train's execution system. For example, the ATO (Automatic Train Control) system adjusts the train's operation based on the target control information to ensure safe operation, thereby achieving safety and efficiency throughout the entire train operation. For instance, if calculations determine that the following train needs to reduce its speed to ensure safety, the target control information will include instructions to appropriately reduce traction power or apply a certain amount of force.

[0124] In this embodiment, the safe operating state of each target train is calculated by the target position, which enables the simulation of virtual train formations. The target position of the target train to be braked is determined by the operation control sequence, which improves the accuracy of the simulation of virtual train formations.

[0125] In one exemplary embodiment, such as Figure 12 As shown, the method further includes steps 1202 to 1204. Wherein:

[0126] Step 1202: If the train's driving mode is automatic driving mode, obtain the corresponding status information of the train according to the automatic control system.

[0127] In this embodiment, during train operation, when the train is in automatic driving mode, its operation is primarily controlled by the ATO (Automatic Train Operation) system. The ATO system precisely adjusts the train's speed, acceleration, braking, and other operating parameters according to a preset operating plan and algorithm to achieve efficient and safe train operation. At this time, the virtual train formation simulation platform system needs to obtain the train's corresponding status information from the automatic control system. This status information includes the train's current speed, position, acceleration, remaining battery power, and may also include the working status of various train components, such as the traction system and braking system. The automatic control system collects this information in real time through sensors distributed throughout the train, then aggregates and transmits it to the relevant monitoring and control modules.

[0128] Taking speed information as an example, the train's speed sensors measure its speed in real time and feed the data back to the ATO (Automatic Train Operation) system. Based on this speed information and a pre-set operating curve, the ATO system determines whether the train is operating according to plan. If the speed is too high or too low, the ATO system automatically adjusts the train's traction or braking system to bring the train back to normal operating conditions. Similarly, location information is crucial for the safe operation of the train. By obtaining the train's real-time location through a positioning system, the ATO system can ensure that the train travels on the correct track and maintains a safe distance from other trains.

[0129] Step 1204: If the train's driving mode is console driving mode, obtain the corresponding status information of the train according to the console command.

[0130] In this embodiment, when the train's driving mode is console operation mode, the train's operation is controlled by the operator of the simulated console through issuing commands. The simulator operator manually issues various control commands to the driver's console interface, including acceleration, deceleration, and stopping, based on factors such as the train's operating status, track conditions, and scheduling requirements.

[0131] In console-based train operation mode, the virtual train formation simulation platform obtains the corresponding train status information based on console commands. The train console sends the issued commands to the train's control system, which adjusts the train's operating status accordingly and feeds back the train's current status information to the console, displaying it on the data visualization and analysis system. For example, when the operator issues an acceleration command, the train's traction system increases power, causing the train to accelerate. Simultaneously, train status information, such as speed changes and current magnitude, is transmitted back to the console in real time via the communication system, allowing the operator to determine whether the train is operating normally according to the commands.

[0132] Train status information not only helps operators understand the real-time operation of the train, but also provides a basis for subsequent control decisions. If abnormal situations occur during the execution of commands, such as slow speed increase or poor braking effect, operators can adjust commands in a timely manner based on the feedback status information to ensure the safety and normal operation of the train. This enhances the interactivity between the virtual train formation simulation platform and the user, and enables comprehensive monitoring and efficient management of railway operation status.

[0133] In this embodiment, the train's status information is obtained through multiple driving modes, including the console driving mode and the automatic driving mode. This improves the adaptability of the virtual train formation simulation platform to train simulation in various operating environments, thereby enhancing the accuracy and reliability of the virtual simulation platform.

[0134] In an exemplary embodiment, the virtual train formation simulation platform can also perform simulation calculations for non-virtual train formations. The method further includes step 108, wherein:

[0135] Step 108: If the train formation mode is non-virtual formation, optimize the control of each train according to the single-objective optimization model and the state information of each train to obtain the corresponding operation control sequence of each train.

[0136] In this embodiment, if the train formation mode is not virtual formation, the ATP speed monitoring system of the virtual formation simulation platform adopts a "hard-wall" safety protection method, that is, it calculates the safe protection speed of the train based on the MA end point of the preceding train or the signal ahead, and sends the calculation result to the ATO automatic control system. Specifically, the ATP speed monitoring system of the virtual formation simulation platform optimizes the control of each train based on a single-objective optimization model and the corresponding status information of each train (including speed, position, acceleration, remaining power, and the working status of each system). The single-objective optimization model comprehensively considers factors such as track gradient, curves, speed limits, and the status of the preceding signal to achieve a single objective such as minimum energy consumption, shortest running time, or highest safety. After optimization calculation, the virtual formation simulation platform generates a corresponding operation control sequence for each train, which specifies the train's operating status at different times. The subsequent ATP speed monitoring system, combined with the "hard wall collision" safety protection method, calculates the safety protection speed with the MA end point or the signal ahead as the target position and sends it to ATO. At the same time, it continuously monitors whether the train is speeding. If it is speeding, protective measures are taken. If it is not speeding, the train status information is repeatedly obtained.

[0137] In this embodiment, a single-objective optimization model is used to simulate non-virtual train formations, which improves the comprehensiveness of the virtual train formation simulation platform in simulating virtual train formations, thereby improving the accuracy of simulation calculations and enhancing the accuracy of target control information.

[0138] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0139] Based on the same inventive concept, this application also provides a virtual grouping simulation device for implementing the virtual grouping simulation method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more virtual grouping simulation device embodiments provided below can be found in the limitations of the virtual grouping simulation method described above, and will not be repeated here.

[0140] In one exemplary embodiment, such as Figure 13 As shown, a virtual grouping simulation device 1300 is provided, including: a loading module 1301, a first optimization module 1302, and a calculation module 1303, wherein:

[0141] Loading module 1301 is used to load a multi-objective optimization model; the multi-objective optimization model is constructed based on energy consumption index constraints, coupler force impact index constraints, distance index constraints, and acceleration index constraints;

[0142] The first optimization module 1302 is used to perform constraint optimization on the energy consumption index, coupler force impact index, distance index and acceleration index of each train according to the multi-objective optimization model, so as to obtain the corresponding operation control sequence of each train.

[0143] The calculation module 1303 is used to determine the target control information of each train based on the operation control sequence.

[0144] In one embodiment, the first optimization module 1302 is specifically used to obtain the current status information of each train;

[0145] Based on the current status information, the future status information of each train within the preset time domain is predicted to obtain the future status information;

[0146] Based on a multi-objective optimization model and future state information, constrained iterative optimization of energy consumption index, coupler force impact index, distance index, and acceleration index is performed to obtain the corresponding operation control sequence for each train.

[0147] In one embodiment, the device 1300 further includes:

[0148] The first acquisition module is used to acquire the preset grouping plan;

[0149] The construction module is used to establish the relationship between the target leading vehicle and the target following vehicle in the preset train formation plan; the relationship is used as input to the multi-objective optimization model as the basis for constrained optimization.

[0150] In one embodiment, the calculation module 1303 is specifically used to determine the target position of the target train to be braked based on the operation control sequence; the target position is the braking endpoint after the target train is braked.

[0151] For each target train, the corresponding target train is a target following train. The safe operating status of each target following train is calculated based on the target position.

[0152] Determine target control information based on safe operating status.

[0153] In one embodiment, the device 1300 further includes:

[0154] The second acquisition module is used to acquire the corresponding status information of the train according to the automatic control system if the train's driving mode is automatic driving mode.

[0155] The third acquisition module is used to obtain the corresponding status information of the train based on console commands if the train's driving mode is console driving mode.

[0156] In one embodiment, the device 1300 further includes:

[0157] The second optimization module is used to optimize the control of each train based on the single-objective optimization model and the state information of each train if the train formation mode is non-virtual formation, so as to obtain the corresponding operation control sequence of each train.

[0158] Each module in the aforementioned virtual grouping simulation 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.

[0159] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 14As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces 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 interfaces. 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 stored in the non-volatile storage media. The input / output interfaces are 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 virtual grouping simulation method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a 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.

[0160] Those skilled in the art will understand that Figure 14 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0161] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0162] Load the multi-objective optimization model; the multi-objective optimization model is constructed based on energy consumption index constraints, coupler force impact index constraints, distance index constraints, and acceleration index constraints;

[0163] Based on the multi-objective optimization model, the energy consumption index, coupler force impact index, distance index and acceleration index of each train are constrained and optimized to obtain the corresponding operation control sequence of each train;

[0164] The target control information for each train is determined based on the operation control sequence.

[0165] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0166] Obtain the current status information of each train;

[0167] Based on the current status information, the future status information of each train within the preset time domain is predicted to obtain the future status information;

[0168] Based on a multi-objective optimization model and future state information, constrained iterative optimization of energy consumption index, coupler force impact index, distance index, and acceleration index is performed to obtain the corresponding operation control sequence for each train.

[0169] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0170] Obtain the preset grouping plan;

[0171] Establish the correlation between the target leading vehicle and the target following vehicle in the preset train formation plan; the correlation is used as input to the multi-objective optimization model as the basis for constrained optimization.

[0172] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0173] The target position of the target train to be braked is determined based on the operation control sequence; the target position is the braking endpoint after the target train is braked.

[0174] For each target train, the corresponding target train is a target following train. The safe operating status of each target following train is calculated based on the target position.

[0175] Determine target control information based on safe operating status.

[0176] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0177] If the train's driving mode is automatic driving mode, the corresponding status information of the train is obtained from the automatic control system.

[0178] If the train's driving mode is console driving mode, obtain the corresponding status information of the train according to the console commands.

[0179] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0180] If the train formation mode is non-virtual formation, the control optimization of each train is performed based on the single-objective optimization model and the state information of each train to obtain the corresponding operation control sequence of each train.

[0181] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0182] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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 virtual grouping simulation method, characterized in that, The method is applied to a virtual grouping simulation platform, and the method includes: Load a multi-objective optimization model; the multi-objective optimization model is constructed based on energy consumption index constraints, coupler force impact index constraints, distance index constraints, and acceleration index constraints; Based on the multi-objective optimization model, the energy consumption index, coupler force impact index, distance index and acceleration index of each train are constrained and optimized to obtain the corresponding operation control sequence of each train; The target control information for each train is determined based on the operation control sequence.

2. The method according to claim 1, characterized in that, The process involves constraining and optimizing each train's energy consumption, coupler force impact, distance, and acceleration indices using a multi-objective optimization model to obtain the corresponding operation control sequence for each train, including: Obtain the current status information of each train; Based on the current state information, the future state information of each train in the preset time domain is predicted to obtain the future state information; Based on the multi-objective optimization model and the future state information, iterative optimization of energy consumption index, coupler force impact index, distance index and acceleration index is performed to obtain the operation control sequence corresponding to each train.

3. The method according to claim 1, characterized in that, Before loading the multi-objective optimization model, the method further includes: Obtain the preset grouping plan; Establish the correlation between the target leading vehicle and the target trailing vehicle in the preset train formation plan; the correlation is used as input to the multi-objective optimization model as the basis for constrained optimization.

4. The method according to claim 1, characterized in that, The determination of target control information for each train based on the operation control sequence includes: The target position of the target train to be braked is determined based on the operation control sequence; the target position is the braking endpoint after the target train is braked. For each target train, a target following train is correspondingly assigned to a target train. The safe operating status of each target following train is calculated based on the target position. Target control information is determined based on the aforementioned safe operating status.

5. The method according to claim 1, characterized in that, The method further includes: If the train's driving mode is automatic driving mode, the corresponding status information of the train is obtained according to the automatic control system; If the train's driving mode is console driving mode, the corresponding status information of the train is obtained according to the console command.

6. The method according to claim 1, characterized in that, The method further includes: If the train formation mode is non-virtual formation, the control optimization of each train is performed based on the single-objective optimization model and the state information of each train to obtain the operation control sequence corresponding to each train.

7. A virtual grouping simulation device, characterized in that, The device is used in a virtual grouping simulation platform, and the device includes: A loading module is used to load a multi-objective optimization model; the multi-objective optimization model is constructed based on energy consumption index constraints, coupler force impact index constraints, distance index constraints, and acceleration index constraints. The optimization module is used to perform constraint optimization on the energy consumption index, coupler force impact index, distance index and acceleration index of each train according to the multi-objective optimization model, so as to obtain the corresponding operation control sequence of each train. The calculation module is used to determine the target control information for each of the trains based on the operation control sequence.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. 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 6.

10. A computer program product, comprising a computer program, 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 6.

Images