Cooperative operation curve planning method, system and equipment for virtual marshalling train, medium and product

Abstract

The invention discloses a collaborative operation curve planning method, system and device for a virtual marshalling train, a medium and a product, and relates to the field of rail traffic signal control. The method comprises the steps that a simulation rail line is constructed according to electronic map information, and the actual train dynamic characteristics of all simulation train units are combined, so that the simulation rail line is constructed; constructing a virtual marshalling train simulation operation model comprising a plurality of simulation train units; according to the constraint condition and the operation condition selection mechanism of each simulation train unit, taking the reference operation curve score of the virtual marshalling train as an optimization target, automatically generating an optimal reference operation curve of each simulation train unit, and sending the optimal reference operation curve to the ATO system of the corresponding simulation train unit in real time; and the ATO system of each simulation train unit is made to operate according to the optimal reference operation curve of the ATO system as the target, and based on the mode, the virtual marshalling train cooperative reference operation curve can be generated online in real time, so that virtual marshalling train cooperative control is realized.

Description

Technical Field

[0001] This application relates to the field of rail transit signal control, and in particular to a method, system, equipment, medium and product for cooperative operation curve planning for virtual train formations. Background Technology

[0002] Urban rail transit, as a crucial infrastructure for improving commuting efficiency and alleviating urban traffic congestion, has made significant progress in its construction in recent years. Driven by the current "dual-carbon" strategic goals, the rail transit industry faces higher requirements for energy conservation and emission reduction. Simultaneously, with the rapid expansion of urban rail transit networks, the distribution of train passenger flow in time and space exhibits uneven and dynamically changing characteristics. This places higher demands on the organization and scheduling capabilities of existing transportation resources, especially the efficient allocation of vehicle and line resources and the precise matching of transport capacity with actual passenger flow, which have become urgent problems to be solved.

[0003] Virtual Coupling (VC) technology, as an emerging train operation control mode, offers a feasible solution to the aforementioned problems. This technology enables short-interval operation between physically unconnected train units, mimicking the operational efficiency and service capacity of physically assembled trains. Through online, dynamic, and flexible adjustments to train formation methods and operation plans, VC technology not only improves the utilization efficiency of vehicle and track resources but also provides greater capacity during peak passenger flow periods and effectively reduces empty running rates and energy consumption during off-peak periods. Therefore, the research and application of VC technology, and the construction of a safe and efficient train formation and collaborative control mechanism, are of significant practical importance and application value for achieving energy conservation and emission reduction, lowering operating costs, and supporting the implementation of the "dual-carbon" strategic goals while ensuring service quality. The widespread application of this technology will lay a solid foundation for the green, intelligent, and efficient development of urban rail transit.

[0004] Despite the promising future of virtual train formation technology, its operation control system faces significant challenges, particularly in the planning and acquisition of operating curves. Currently, operating curve planning for virtual train formations is typically based on static track models, with operating curves generated offline in advance. The generation of operating curves considers parameters such as the train's maximum speed, section speed limits, and planned journey time, generating curves for the train's speed, acceleration, and braking within specific sections through pre-calculated offline static calculations. These curves are stored in the onboard control equipment via manual copying, providing a reference for the train's automatic tracking control and ensuring that the train completes its planned journey within the planned time, while also meeting the safety and synchronous operation requirements of virtual train formations. However, existing curve planning methods are usually completed offline, aiming to provide basic operating curves to guide daily train operation. This approach has the following shortcomings: (1) Currently, most train operation curves are planned in advance using static models and stored in the onboard system. This method lacks the ability to respond in real time to the actual operating environment. When the train encounters situations such as changes in speed limits during operation, the traditional operation curve system does not have the ability to interact with this dynamic information in real time. The previously stored curves cannot be updated in time, which prevents the train from operating according to the optimal strategy, potentially leading to energy waste, reduced operating efficiency, and even safety hazards.

[0005] (2) Most of the online train operation curve planning systems in existing research are designed for independently operating trains and do not consider the dynamic coupling characteristics of multi-unit collaborative operation of virtual train formations. They do not have the ability to handle virtual train formations. In virtual formation mode, the operation between train units needs to have a high degree of coordination, including precise following and coordination mechanisms, to ensure that each train unit can be accurately synchronized under different operating conditions and avoid conflicts or errors caused by dynamic changes.

[0006] (3) The current train operation curve is usually generated offline before operation and stored in the train control system. This traditional method lacks online planning capabilities and does not have a mechanism for real-time interaction with the train control system. Once the operating conditions change, the original curve cannot be dynamically updated, and new reference operation curves cannot be issued to the train system in a timely manner, affecting overall efficiency and scheduling flexibility.

[0007] The above three points prevent existing technologies from generating real-time online collaborative reference operation curves for virtual train formations. To meet the requirements for efficient, reliable, and energy-saving operation of virtual train formations, there is an urgent need for an operation curve planning server system with adaptive operating condition selection and algorithm optimization capabilities, and capable of collaborative interaction with the Automatic Train Operation (ATO) system. Summary of the Invention

[0008] The purpose of this application is to provide a method, system, device, medium, and product for collaborative operation curve planning of virtual train formations, in order to solve the problem of the inability to generate collaborative reference operation curves for virtual train formations in real time online.

[0009] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a cooperative operation curve planning method for virtual train formations, including: Construct a simulated track route based on electronic map information; Based on the track data of the simulated track line and combined with the actual train dynamics characteristics of each simulated train unit, a virtual train formation simulation operation model containing multiple simulated train units is constructed; the track data includes gradient, curve radius, speed-limited sections, and section lengths; the simulated train unit includes a lead car and a follower car, and each simulated train unit has independent constraints and operating condition selection mechanisms; Based on the virtual train formation simulation operation model, and according to the constraints and operating condition selection mechanism of each simulation train unit, the optimal reference operating curve of each simulation train unit is automatically generated with the reference operating curve score of the virtual train formation as the optimization objective. The optimal reference operating curve is sent to the ATO system of the corresponding simulated train unit in real time, and each simulated train unit's ATO system is instructed to operate according to its own optimal reference operating curve as the target, so as to realize the collaborative control of the virtual train; the ATO systems of each simulated train unit interact in real time; the virtual train formation includes each simulated train unit.

[0010] Secondly, this application provides a cooperative operation curve planning system for virtual train formations, comprising: The track line modeling module is used to construct simulated track lines based on electronic map information; The virtual train formation simulation modeling module is used to construct a virtual train formation simulation operation model containing multiple simulation train units based on the track data of the simulated track and the actual train dynamics characteristics. The track data includes gradient, curve radius, speed-limited sections, and transponder position sequence. The simulation train unit includes a lead car and a follower car, and each simulation train unit has independent constraints and operating condition selection mechanisms. The curve generation and optimization module is used to automatically generate the optimal reference operating curve for each simulated train unit based on the virtual train formation simulation operation model, according to the constraints and operating condition selection mechanism of each simulated train unit, with the reference operating curve score of the virtual train formation as the optimization objective. The curve management and distribution module is used to send the optimal reference running curve to the ATO system of the corresponding simulated train unit in real time, and to make the ATO system of each simulated train unit run according to its own optimal reference running curve as the target, so as to realize the collaborative control of the virtual train; the ATO systems of each simulated train unit interact in real time; the virtual train formation includes each simulated train unit.

[0011] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described cooperative operation curve planning method for virtual train formations.

[0012] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned cooperative operation curve planning method for virtual train formations.

[0013] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned cooperative operation curve planning method for virtual train formations.

[0014] According to the specific embodiments provided in this application, this application has the following technical effects: Compared to traditional offline-generated static curves, this application constructs a simulated track line based on electronic map information and combines it with actual train dynamics characteristics to build a virtual train formation simulation operation model containing multiple simulated train units. Based on the constraints and operating condition selection mechanism of each simulated train unit, the optimal reference operating curve score of the virtual train formation is used as the optimization objective. The optimal reference operating curve of the simulated train unit is dynamically adjusted according to the real-time operating status of the virtual train formation, responding in real time to changes such as speed limits and journey targets, avoiding the problem of response lag. The optimal reference operating curve is sent to the ATO system of the corresponding simulated train unit in real time. The ATO systems of each simulated train unit interact in real time to perform collaborative control based on the optimal reference operating curve of each simulated train unit, realizing the real-time online generation of the virtual train formation collaborative reference operating curve. That is, each simulated train unit operates according to its own optimal reference operating curve as the target, thereby realizing the collaborative control of the virtual train formation and further ensuring the flexibility and accuracy of train operation. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart of a cooperative operation curve planning method for virtual train formations is provided in one embodiment of this application; Figure 2 A speed-time graph provided for one embodiment of this application; Figure 3 A velocity-position graph provided for one embodiment of this application; Figure 4 A spacing-time curve provided for one embodiment of this application; Figure 5An acceleration-time graph provided for one embodiment of this application; Figure 6 A timing diagram of the virtual train formation cooperative operation curve planning server interaction provided in an embodiment of this application; Figure 7 A schematic diagram of a collaborative operation curve planning server system provided in an embodiment of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] To make the objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] like Figure 1 As shown in the figure, this application provides a cooperative operation curve planning method for virtual train formations, including: S1: Construct a simulated track line based on electronic map information.

[0020] S2: Based on the track data of the simulated track line and combined with the actual train dynamics characteristics of each simulated train unit, a virtual train formation simulation operation model containing multiple simulated train units is constructed; the track data includes gradient, curve radius, speed-limited sections, and section lengths; the simulated train unit includes a lead car and a follower car, and each simulated train unit has independent constraints and operating condition selection mechanisms.

[0021] S3: Based on the virtual train formation simulation operation model, according to the constraints and operating condition selection mechanism of each simulation train unit, and with the reference operation curve score of the virtual train formation as the optimization objective, the optimal reference operation curve of each simulation train unit is automatically generated.

[0022] S4: The optimal reference operating curve is sent to the ATO system of the corresponding simulated train unit in real time, and each simulated train unit's ATO system is instructed to operate according to its own optimal reference operating curve as the target, so as to realize the collaborative control of the virtual train; the ATO systems of each simulated train unit interact in real time; the virtual train formation includes each simulated train unit.

[0023] In an exemplary embodiment, a simulated track line is established based on electronic map information, and a virtual train formation model containing two simulated train units is constructed based on actual train dynamics characteristics. Each simulated train unit has an independent speed constraint and operating condition selection mechanism. S1 specifically includes: First, a corresponding simulated track route is constructed using electronic map information. The electronic map data includes track geometric parameters, such as radius of curvature, gradient, section length, and basic speed limits, used to construct a track topology model consistent with the actual operating environment.

[0024] S2 specifically includes: Based on the track model, a virtual train formation dynamics simulation model containing two simulated train units is constructed. Each simulated train unit is modeled according to the dynamic characteristics of real vehicles, considering key physical properties such as traction, braking force, drag, mass, and speed. The motion state of each virtual train formation simulated train unit is described by the following dynamic equations: in This represents the mass of the i-th simulated train unit. , and These represent the speed, traction force, and braking force of the i-th simulated train unit at time k, respectively. This represents the running resistance of the i-th simulated train unit. Specifically, it is expressed as... ,in and These are the coefficients of the Davis equation. Slope resistance. , It is the simulated train unit i at time k. The slope corresponding to the location. Curve resistance. , It is the radius of curvature of the position of the simulated train unit i at time k.

[0025] The motion of the simulated train unit can be controlled by discrete time steps. Iterative updates are performed. The state of the simulated train unit changes over time step k via position... ,speed and acceleration To describe. The position update formula is: , This indicates the position of the simulated train unit i at time k+1.

[0026] In an exemplary embodiment, before the train enters the designated operating section, the ATO sends a data request containing the departure and arrival station IDs, speed limit information, and planned journey time to the curve planning server on the simulated train unit. Based on this, the curve planning server determines the optimization section and, in conjunction with the key physical parameters during train operation, designs the operating curve scoring function as the objective function, thus establishing a multi-parameter, multi-constraint optimization problem.

[0027] The above optimization problem is solved by combining parameter tuning empirical algorithm and pattern search algorithm, automatically selects the optimal control parameters, and then generates a reference operation curve that meets the operation target.

[0028] S3 specifically includes: Before the train enters the designated operating section, the ATO sends a request to the curve planning server containing parameters such as departure and arrival station IDs, section speed limits, and planned journey time. Upon receiving the request, the curve planning server models the designated operating section as an optimization segment and, combined with the operating status and physical characteristics of the virtual train formation, defines the operating curve optimization problem. The core objective of this process is to generate a set of acceleration sequences that meet the train operation control objectives and optimize the train's operating efficiency.

[0029] 1) Optimize the objective function.

[0030] The objective function is optimized from two dimensions: operational efficiency and coordination accuracy. Three key indicators are selected: journey time, time difference between the front and rear vehicles, and parking accuracy of the front and rear vehicles. These three indicators are normalized to form a unified evaluation system, so that indicators with different dimensions and different ranges of variation can be weighted in the same objective function.

[0031] Let the journey time of a virtual train formation be... The minimum and maximum travel times within the corresponding sample set are respectively and The normalized expression for the journey time is: Since shorter travel time is better, the scoring should be reversed so that smaller values ​​result in higher scores. The following scoring function is used: in, This is the scoring function for journey time.

[0032] Let the stopping times of the current train and the train before it be respectively. and The parking time difference is Let the minimum and maximum values ​​of the parking time difference in the sample be... and The normalization result is: The smaller the parking time difference, the better; therefore, the scoring function for the parking time difference... for: Regarding stopping accuracy, let the current actual stopping position of the train be... The target parking location is The parking error is then... Similarly, let the sample minimum and maximum values ​​of this error be... and Normalized to: The more precise the parking, the higher the score should be; therefore, the scoring function for parking accuracy... for: In summary, the three scoring functions are weighted to form the final objective function, which is the score of the reference running curve of the virtual train. in, And satisfy Each weight can be flexibly adjusted according to the operational strategy, emphasizing either operational efficiency or train formation coordination accuracy. This objective function provides a unified and quantitative evaluation standard, offering a clear optimization objective for subsequent parameter tuning and optimization algorithms, and contributing to the intelligent optimization of the operating curve and the efficient coordinated control of virtual train formations.

[0033] 2) Optimize the constraints of the problem.

[0034] First, the operation of virtual train formations needs to meet the following constraints: track speed limits, train performance limitations, passenger comfort limitations, and minimum tracking distance constraints between adjacent simulated train units. These constraints can be formally expressed as: in Indicates position Speed ​​limits are in place at this location; , These are the minimum braking acceleration and maximum traction acceleration that the simulated train unit can provide, respectively. Let be the acceleration of the i-th simulated train unit at time k; , These represent the lower and upper limits of the train impact rate, respectively, reflecting the constraints on ride comfort. Indicates the length of the simulated train unit; Let be the position of the (i-1)th simulated train unit at time k.

[0035] In addition, minimum tracking distance Depending on the position, speed, and acceleration of the trains ahead and behind, it can be represented as: To ensure safe operation, a safety protection distance function is introduced. And consider the control error margin Therefore, the following should be satisfied: , This indicates the safe protection distance determined by the condition of the train compartment. This is to allow for an error margin in advance, in order to mitigate uncertainties and control deviations during operation.

[0036] To ensure passenger experience and the accuracy of the operational plan, each simulated train unit should complete the entire operating section within a specified time window. Define the train. The planned journey time is The actual journey time is: The constraints are: ,in, This refers to the allowable range of travel time error.

[0037] When multiple units in a train formation need to stop at a station simultaneously, to ensure coordinated passenger boarding and alighting and synchronized control, the stopping time constraints of each unit must be met. For stations... Simulated train unit and The actual parking time is: The parking time difference satisfies: ,in, The allowable error for stopping time is defined. To achieve precise alignment, the actual stopping position of each simulated train unit at the target stopping point should meet certain error limits. Let the train... On the site The target parking location is The actual parking location is Then the parking accuracy constraint is ,in, This is the maximum allowable parking error value.

[0038] After completing the virtual train formation simulation model and track environment construction, the curve planning server system enters the stage of optimizing and generating reference operating curves. The core of S3 is to execute optimization algorithms and automatically select the optimal operating control parameters to generate reference operating curves that meet the cooperative operation objectives. To improve optimization efficiency and solution quality, the system adopts a combination of parameter tuning empirical algorithms and pattern search algorithms, forming a solution strategy that balances global search and local fine-tuning.

[0039] First, the system extracts typical parameter tuning experience based on high-quality cooperative operation curves obtained from a large amount of test data. These empirical parameters include traction and braking time, braking rate, and cruising speed, and a system model was specifically developed for the parking control strategy of the pilot simulation train unit. This parameter tuning experience serves as the initial input, providing a reference starting point for pattern search and significantly improving the convergence efficiency of the algorithm.

[0040] Subsequently, in the constructed simulation environment, the train model initializes its operational state based on electronic maps and vehicle dynamics information, setting key conditions such as the initial positions, speeds, and speed-limited sections of the preceding and following trains, while simultaneously identifying all operational constraints. The system initiates the simulation process, monitoring the train's status in real time and dynamically adjusting the control strategy according to changes in operating conditions. After each simulation run, the system records the complete operational trajectory and extracts key performance indicators such as departure time difference, stopping time difference, journey time, and stopping accuracy of the preceding and following trains.

[0041] Based on this, the algorithm uses the aforementioned key performance indicators as input to the final scoring function F, assigning a score to each trajectory. These key performance indicators include journey time, stopping time difference, and stopping accuracy. The scoring function aims to reflect the overall quality of coordinated operation; a higher score indicates that the trajectory better meets the desired operational objective. The optimization module sets some control parameters from the simulation process as variables to be optimized. Using a pattern search algorithm, it performs multiple rounds of search within the parameter space, gradually converging to the trajectory with the optimal score.

[0042] Ultimately, the system automatically selects the simulation trajectory with the highest overall score and generates a corresponding reference running curve, which serves as the target curve for the virtual train formation during subsequent real-world operation. This process not only ensures the efficiency and safety of the reference running curve but also lays the data foundation for the coordinated control of the train.

[0043] The technical solution of this application will be further illustrated below with specific data.

[0044] Table 1. Actual Line Platform Stop Information

[0045] Table 2. Data on inter-station operation scenarios

[0046] Table 3 Reference Operating Curve Performance Parameters

[0047] As shown in Tables 1-3, reference operating curves are generated based on actual line platform stopping point information, inter-station operation scenario data, and reference operating curve performance parameters. Figures 2-5 As shown, the reference operating curves include speed-time curves, speed-position curves, spacing-time curves, and acceleration-time curves, to coordinate the control of virtual train formation operation.

[0048] In one exemplary embodiment, the curve planning server sends the generated optimal reference running curve data to the ATO system in real time for use during actual train operation. This process supports standardized data interfaces, ensuring seamless integration of curve data with existing train control systems and meeting the requirements of engineering deployment and system integration. S4 specifically includes: like Figure 6 As shown, before a virtual train formation enters its planned operating section, the ATO system proactively sends a running curve request to the curve planning server. After completing optimization calculations, the curve planning server generates an optimal reference running curve covering both the departure and arrival stopping areas, and sends this curve data to the ATO system in real time for use in actual train control. This not only facilitates the application of optimized data to the actual control system but also provides crucial support for the collaborative operation of virtual train formations.

[0049] To achieve efficient integration with the train control system, the generated reference operating curve data adopts a standardized interface design, possessing good compatibility and engineering scalability. The curve data is stored in .txt text format and organized in a structured manner, including speed and position data points for the lead car and following cars. Each data point contains corresponding speed and position values, used by the ATO system to determine the target's operating status in real time. Furthermore, the identification of the station entry phase is marked using a special flag. This flag is embedded in the highest byte of the following car's position field, using byte-level bit operations to indicate whether the current data point is in the station entry state. This design effectively saves transmission space while avoiding the introduction of additional redundant fields, enhancing the compactness of the data structure.

[0050] In terms of communication, the curve planning server and ATO are connected via a physical Ethernet connection. The network layer protocol is IPv4, and the transport layer protocol is UDP to achieve low latency and high transmission efficiency. During transmission, multi-byte information is encoded using Big Endian (most significant byte first) to meet the consistency requirements of the train control system's communication standards. Since curve data typically contains hundreds or even thousands of data points, resulting in a large overall data volume, and the ATO integrated platform has strict limitations on the maximum length of a single data packet, a packet-segmented transmission strategy is adopted, splitting the complete curve file into several data segments for sequential transmission. Each data packet carries necessary transmission control fields, such as the sequence number of the current packet, the total data length, and whether it is the last packet in the batch, ensuring that the receiving end can reassemble the data in order and verify its integrity.

[0051] To improve communication reliability, both the curve planning server and the ATO (Automatic Train Control) implement an error detection mechanism based on CRC (Cyclic Redundancy Check). Each data packet is appended with a corresponding CRC checksum, and the receiving end verifies the data during unpacking. If an error is detected in a data packet during transmission, the packet is discarded. This design simplifies the communication logic while ensuring the stability and accuracy of the data received by the ATO, preventing erroneous curve information from affecting train control behavior.

[0052] Specifically, each data packet sent by the curve planning server to the ATO includes, but is not limited to, the following: the total length of the current packet, the packet sequence number, a flag indicating whether it is the last packet, the identifiers of the departure and arrival parking areas, the planned running time, the number of data points and their specific data content for the lead and follower trains, a ten-byte reserved field, and a CRC checksum. The entire transmission process can be completed within seconds, ensuring that the reference running curve is successfully injected into the ATO system before the train actually enters the section, providing the expected trajectory basis for train control.

[0053] In summary, S4 not only achieves standardized output and system integration of curve planning results, but also ensures that virtual train formations can obtain the optimal reference running curve in a timely and accurate manner before entering the operating section through efficient data structure design, robust network transmission scheme and perfect error detection mechanism, effectively supporting the realization of collaborative operation goals.

[0054] This application enables the dynamic construction of a simulation platform and the generation of optimized reference operating curves based on requests from the ATO system, combined with electronic map information and train dynamics models, before the train enters a designated operating section. The system utilizes an adaptive operating condition selection mechanism, integrating parameter tuning experience algorithms and pattern search algorithms to automatically extract key parameters from the simulation process, construct optimization problems, and employ optimization algorithms to solve for the optimal operating strategy, achieving collaborative operation control among multiple simulated train units. Finally, the generated optimal reference operating curve can be sent to the ATO system in real time, enabling efficient scheduling, precise control, and energy-saving optimization during train operation, significantly improving the intelligent operation level and system responsiveness of virtual train formations. The main innovations and beneficial effects of this invention are summarized as follows: (1) It breaks through the technical limitations of traditional offline static generation of train operation curves and supports the dynamic generation of optimal reference operation curves based on real-time operating conditions, which significantly improves the system's adaptability and response speed. Before the virtual train enters the operating section, the curve planning server can quickly build a simulation model and generate operation curves based on the departure station, arrival station, planned journey time and speed limit information provided by the ATO system, which greatly enhances the real-time performance and intelligence level of the train control system.

[0055] (2) In view of the multi-unit operation characteristics of virtual train formation, a collaborative modeling and optimization mechanism that supports the adaptive operation condition selection of simulated train units is designed. During the simulation process, the simulated train units dynamically adjust their operation strategies according to their own speed constraints. Through refined simulation modeling and operation status updates, the control accuracy of collaborative constraints and synchronous operation between trains is improved, which can effectively avoid the operation conflicts caused by response lag or incoordination of operating conditions under the traditional formation method.

[0056] (3) An optimization strategy combining parameter tuning experience algorithm and pattern search algorithm was introduced. By jointly searching and adjusting the key parameters extracted from the simulation operation, a multi-objective optimization mechanism that takes into account indicators such as train synchronization, journey time, energy efficiency and safety was established. Compared with the traditional method that relies on manual experience or single-objective optimization, the system can achieve multi-dimensional balanced optimization of operating efficiency, punctuality rate and energy saving effect, thereby improving the overall operating performance.

[0057] (4) It possesses excellent system integration and engineering practicality. The designed curve planning server supports standardized interface output and can seamlessly connect with the existing ATO system to realize real-time distribution and dynamic invocation of running curves, simplifying the system deployment process and improving the scalability and maintainability of the application. The system has been deployed and verified in the Hebei CRRC test line, demonstrating good practical value and promising prospects for promotion.

[0058] (5) For the first time in the field of intelligent rail transit scheduling and control, a closed-loop mechanism of "active curve request + collaborative operation optimization + real-time execution" has been realized, and a new control paradigm supporting the collaborative operation of multiple trains in virtual formation has been constructed. This paradigm upgrades the train control system from the traditional "passive execution" control to "collaborative decision-making" control, which not only enhances the flexibility and intelligence of train operation, but also provides key technical support for the construction of future intelligent urban rail transit systems.

[0059] This application provides a cooperative operation curve planning system for virtual train formations, including: The track line modeling module is used to construct simulated track lines based on electronic map information.

[0060] The virtual train formation simulation modeling module is used to construct a virtual train formation simulation operation model containing multiple simulation train units based on the track data of the simulated track and the actual train dynamics characteristics. The track data includes gradient, curve radius, speed-limited sections, and transponder position sequence. The simulation train unit includes a lead car and a follower car, and each simulation train unit has independent constraints and operating condition selection mechanisms.

[0061] The curve generation and optimization module is used to automatically generate the optimal reference operating curve for each simulated train unit based on the virtual train formation simulation operation model, according to the constraints and operating condition selection mechanism of each simulated train unit, and with the reference operating curve score of the virtual train formation as the optimization objective.

[0062] The curve management and distribution module is used to send the optimal reference running curve to the ATO system of the corresponding simulated train unit in real time, and to make the ATO system of each simulated train unit run according to its own optimal reference running curve as the target, so as to realize the collaborative control of the virtual train; the ATO systems of each simulated train unit interact in real time; the virtual train formation includes each simulated train unit.

[0063] In practical applications, the track line modeling module constructs a simulated track line based on electronic map information. It takes the simulated track line data (gradient, curve radius, speed limit section, transponder position sequence, etc.) as input and provides it to the virtual train formation simulation modeling module to determine the operating constraints and dynamic response environment of the simulated train unit.

[0064] In practical applications, the virtual train formation simulation modeling module combines real train dynamics to construct a virtual train formation simulation operation model containing two simulated train units: a lead car and a follower car. The virtual train formation simulation modeling module generates a virtual train formation simulation operation model containing a lead car and a follower car, providing key parameters such as vehicle mass, traction and braking characteristics, and speed constraints. The curve generation and optimization module performs simulation calculations based on these parameters.

[0065] In practical applications, the curve generation and optimization module supports the lead and follower trains in adaptively selecting operating conditions based on their respective speed constraints. It employs parameter tuning experience algorithms and pattern search algorithms to extract key parameters from the simulation process as optimization variables. Using the reference operating curve score of the virtual train formation as the optimization objective, an optimization problem is constructed and solved through optimization algorithms, automatically generating the optimal reference operating curve.

[0066] In practical applications, the curve management and distribution module is responsible for sending the generated optimal reference operating curve to the ATO system in real time for its use. The ATO system receives the optimal reference operating curve from the curve planning server, analyzes the trajectory information it contains, such as time, speed, position, and acceleration, and uses this curve as the target curve for train operation control. The lead car's ATO control unit uses the reference operating curve as a target and calculates the traction and braking force output in real time to ensure that the train's actual operating state (speed, position, acceleration) tracks the reference operating curve as closely as possible. When external disturbances cause deviations, the ATO automatically corrects the traction and braking commands through a closed-loop adjustment strategy to ensure smooth train operation, energy saving, and compliance with travel time constraints. The following car's ATO control unit also operates with its own optimal reference operating curve as a target, while simultaneously acquiring or estimating the lead car's operating state (including speed, position, acceleration, etc.) in real time.

[0067] During operation, the following train dynamically adjusts its traction and braking control inputs based on the deviation between its own reference operating curve and the lead train's status, ensuring safe, efficient, and stable coordinated operation while maintaining safe intervals. Through the coordination of these modules, the curve planning server system ensures that the virtual train formation can operate efficiently and collaboratively.

[0068] This application provides a cooperative operation curve planning system for virtual train formations, namely, a server system for cooperative operation curve planning of virtual train formations based on electronic map information and real train dynamics. Figure 7As shown, the multi-stage in the multi-stage cooperative curve planning model refers to dividing the inter-station operation process of the virtual train formation into multiple operating condition stages. The virtual train formation enters these operating conditions sequentially. Within each time period of each operating condition, the leading train unit iteratively obtains a new state based on the control strategy set for that condition. Then, the following train units calculate their own EBI based on the leading train unit, and then consider the control error to obtain their own speed constraints. Under the speed constraints, they search for their own control strategy to satisfy the speed constraints while meeting the operating objectives of that operating condition. This application uses a cooperative operation curve planning server to generate the optimal reference operation curve online during real-time operation through simulation modeling and optimization algorithms. Real-time interaction is achieved through the ATO system, supporting online download of the reference operation curve. The system can automatically adjust the operating conditions of the simulated train units based on real-time data, achieving efficient cooperative control of the virtual train formation and ensuring precise synchronization of the train under different operating conditions, thereby improving operating efficiency and safety.

[0069] The advantage of this invention lies in its significantly enhanced dynamic adaptability to virtual train formation operation. Compared to traditional offline-generated static curves, this invention can dynamically adjust the train reference running curve based on the real-time operating status of the virtual train formation, responding in real-time to changes in speed limits, journey targets, etc., thus avoiding response lag issues. Real-time interaction with the ATO system further ensures the flexibility and accuracy of train operation. This invention has been deployed in the field and verified through simulation, demonstrating its practical usability.

[0070] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments. The computer device can be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device stores data to be processed. The I / O interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with an external terminal via a network connection. When the computer program is executed by the processor, it implements the above-described methods.

[0071] 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 implement the steps in the above-described method embodiments.

[0072] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0073] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0074] 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.

[0075] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by hardware related to computer program instructions. 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 described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile 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).

[0076] 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, etc., and are not limited to these.

[0077] 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 specification.

[0078] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A cooperative running curve planning method for a virtual marshalling train, characterized in that, The method comprises the following steps: constructing a simulation track line according to electronic map information; constructing a virtual marshalling train simulation running model comprising a plurality of simulation train units according to road data of the simulation track line in combination with actual train dynamics characteristics of each simulation train unit; the road data comprises gradient, curve radius, speed limit section and section length; the simulation train unit comprises a leading train and a following train, and each simulation train unit has independent constraint conditions and running condition selection mechanism; generating an optimal reference running curve of each simulation train unit based on the virtual marshalling train simulation running model according to the constraint conditions and running condition selection mechanism of each simulation train unit with the reference running curve score of the virtual marshalling train as the optimization target; sending the optimal reference running curve to the ATO system of the corresponding simulation train unit in real time, and enabling the ATO system of each simulation train unit to run according to the optimal reference running curve thereof to realize virtual train cooperative control; the ATO systems of the simulation train units interact in real time; the virtual marshalling train comprises the simulation train units.

2. The method for planning coordinated running curve of virtual marshalling train according to claim 1, characterized in that, The actual train dynamics characteristics are described by a dynamics equation; The dynamics equation is: in, This represents the mass of the i-th simulated train unit; , and These represent the speed, traction force, and braking force of the i-th simulated train unit at time k, respectively. Representing the i The running resistance of a simulated train unit. , , and These are the coefficients of the Davis equation; For slope resistance, , For the simulation of train unit i at time k The slope corresponding to the location It is the acceleration due to gravity; For cornering resistance, , Let be the radius of curvature of the position of train unit i at time k.

3. The method for virtual marshalling train oriented cooperative running curve planning according to claim 1, characterized in that, the reference run curve score is: wherein, is a weight coefficient; is a score function for journey time; is a score function for parking time difference; is a score function for parking accuracy.

4. The method for virtual marshalling train oriented cooperative running curve planning according to claim 1, characterized in that, The constraint conditions comprise track line speed limit, train performance limit, ride comfort limit and minimum tracking distance constraint between adjacent simulation train units; The constraint conditions are: wherein, is the speed of the i-th simulated train unit at time k; i k is the speed of the i-th simulated train unit at time k; i is the line speed limit at the position of the i-th simulated train unit at time k; , are the minimum braking acceleration and the maximum traction acceleration that can be provided by the simulated train unit, respectively; is the acceleration of the i-th simulated train unit at time k; , are the lower and upper bounds of the train jerk, respectively, to embody the constraint of ride comfort; is the length of the simulated train unit; is the minimum following distance; is the position of the i-1-th simulated train unit at time k.​​​ 5. The virtual consist train oriented cooperative running curve planning method according to claim 4, characterized in that, The constraint conditions further comprise running time constraint condition, stopping time constraint condition and stopping precision constraint condition; Under the running time constraint, each simulation unit train is set to complete the entire running section within a specified time window; the running time constraint is: ; wherein, is a journey time error tolerance range; is an actual journey time; is a planned journey time; Under the parking time constraint, a synchronization constraint of the parking time of each simulated train unit is satisfied; the parking time constraint is: ; wherein, is a parking time allowable error; is a parking time of a simulated train unit at a station ; and is a parking time of a simulated train unit at a station . Under the parking accuracy constraint condition, the actual parking position of each simulation train unit at the target parking position meets the error limit; the parking accuracy constraint condition is: wherein, is a maximum parking error tolerance value; is a simulation train unit at a target parking position of a station ; is an actual parking position of a simulation train unit at a station .

6. The virtual consist train oriented cooperative running curve planning method according to claim 1, wherein, Enabling the ATO system of each simulation train unit to run according to the optimal reference running curve thereof to realize virtual train cooperative control specifically comprises: enabling the leading train to run according to the optimal reference running curve thereof, calculating traction force and brake force output in real time, so that the actual running state of the leading train tracks the optimal reference running curve of the leading train, and enabling the following train to run according to the optimal reference running curve thereof while estimating the actual running state of the leading train in real time to realize virtual marshalling train cooperative control; the actual running state comprises speed, position and acceleration.

7. A cooperative running curve planning system for a virtual consist train, characterized in that, The method comprises the following steps: constructing a simulation track line according to electronic map information by a track line modeling module; constructing a virtual marshalling train simulation running model comprising a plurality of simulation train units according to road data of the simulation track line in combination with actual train dynamics characteristics by a virtual marshalling simulation train modeling module; the road data comprises gradient, curve radius, speed limit section and balise position sequence; the simulation train unit comprises a leading train and a following train, and each simulation train unit has independent constraint conditions and running condition selection mechanism; generating an optimal reference running curve of each simulation train unit based on the virtual marshalling train simulation running model according to the constraint conditions and running condition selection mechanism of each simulation train unit with the reference running curve score of the virtual marshalling train as the optimization target by a curve generation and optimization module; A curve management and issuing module is configured to send the optimal reference running curve to the ATO system of the corresponding simulation train unit in real time, and to enable the ATO system of each simulation train unit to run as a target according to the optimal reference running curve of itself, so as to realize virtual train cooperative control; the ATO systems of the simulation train units are capable of real-time interaction; and the virtual marshalling train comprises the simulation train units.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and capable of being run on the processor, characterized in that the processor executes the computer program to implement the virtual marshalling train-oriented cooperative running curve planning method of any one of claims 1-6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the virtual marshalling train-oriented cooperative running curve planning method of any one of claims 1-6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the virtual marshalling train-oriented cooperative running curve planning method of any one of claims 1-6. The computer program is executed by the processor to implement the virtual marshalling train-oriented cooperative running curve planning method of any one of claims 1-6.

Images