Adaptive high-speed train tracking operation control method and system considering driving scenarios

Abstract

The application provides an adaptive high-speed train tracking operation control method and system considering driving scenes, belongs to the technical field of train operation control, acquires train operation state data, and carries out data statistics and processing; a pre-trained driving style recognition model is used to process and classify train driving feature data, and driving style recognition results are obtained; the most relevant driving feature parameters and corresponding parameter values of the driving style are obtained according to the MIC algorithm; model predictive control and online driving style recognition are combined according to the driving feature parameters and corresponding parameter values, different driving modes and driving style trains are controlled by using an MPC model, and adaptive group operation of high-speed trains is realized. The application improves the flexibility and adaptability of high-speed train formation group trains, and realizes an adaptive control mode facing multiple scenes and multiple modes.

Description

Technical Field

[0001] This invention relates to the field of train operation control technology, and specifically to an adaptive high-speed train tracking operation control method and system that takes into account driving scenarios. Background Technology

[0002] As the brain and central nervous system of the high-speed railway system, the Train Control System (TCS) plays a crucial role in ensuring the safe and efficient operation of trains. Currently, typical train control systems used in high-speed railways include CTCS-3 (China Train Control System), CTCS-2, ETCS (European Train Control System), ATC (Automatic Train Control System), and other fixed-section control modes. To meet the ever-increasing passenger demand, the train density of high-speed railways is constantly increasing. With this increasing density, existing headways are approaching the system's design limits. Therefore, fixed-section control technology is insufficient to meet the need for further improvements in operational efficiency. Currently, high-speed train group operation is an important technical means to further shorten train headways and improve operational efficiency. It is a core and key aspect of railway development both domestically and internationally.

[0003] The theory and practice of virtual train formation are under active development and research. Virtual train formation uses car-to-car communication technology to replace existing physical couplers to achieve train formation operation. During train formation operation, the virtual train formation can be regarded as a single train, with each subsequent train following the preceding train while maintaining a certain tracking distance. Virtual train formation technology can monitor and maintain the tracking distance between trains with minimal infrastructure intervention, and compared to traditional train control methods, it significantly shortens the tracking distance between trains, improving the operational efficiency of existing lines. By forming or detaching trains during operation, i.e., using virtual formation to create train platoons, line capacity can be further increased.

[0004] Unlike moving block systems, virtual train formation offers a new approach to improving operational efficiency. Designing a real-time control algorithm to rationally resolve conflicts between multiple objectives is a challenging issue in the field of cooperative control of virtual coupled train systems. Over the years, numerous positive attempts have been made in the cooperative control of high-speed train control systems. Among these attempts, Model Predictive Control (MPC) algorithms can handle contradictions between multiple constraints and have unique advantages in dealing with certain types of multi-objective control problems. Although many studies have significantly improved the performance of MPC systems, enhancing control accuracy and stability, most current train control systems use only a fixed set of parameters. However, using a fixed set of parameters may not meet the driving style requirements and driving mode selections across a wide range of scenarios (e.g., for very conservative or very aggressive driving states). Therefore, it is necessary to further improve the flexibility and adaptability of MPC in train formation. Current research and simulations typically assume that the leading train has a deterministic single behavior pattern, which simplifies the complexity of train behavior and spacing control. Although railway operations are highly organized and strictly planned according to train timetables, real-time changes in the behavior patterns of leading trains, including temporary or random adjustments to planned speed curves, require subsequent trains to adaptively adjust their behavior and spacing. This adaptability highlights the flexibility of model predictive control (MPC) methods in train platooning and demonstrates the system's ability to handle complex transport environments and dynamic conditions.

[0005] Therefore, for high-speed railway train formation tracking control, how to design a control system to meet different driving modes and styles, while satisfying the requirements of following, comfort and accuracy, so as to provide a better driving experience for different driving modes and styles of high-speed railway train automatic driving systems, is a question that still needs further research. Summary of the Invention

[0006] The purpose of this invention is to provide an adaptive high-speed train tracking operation control method and system that takes into account driving scenarios, so as to solve at least one of the technical problems existing in the background art.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides an adaptive high-speed train tracking operation control method considering driving scenarios, comprising:

[0009] Acquire train operation status data and perform data statistics and processing;

[0010] The train driving feature data is processed and classified using a pre-trained driving style recognition model to obtain driving style recognition results;

[0011] The driving feature parameters and their corresponding values ​​that are most correlated with driving style are obtained based on the MIC algorithm.

[0012] Based on driving characteristic parameters and their corresponding values, model predictive control and online driving style recognition are combined. The MPC model is used to control trains with different driving modes and styles, thereby achieving adaptive group operation of high-speed trains.

[0013] As a further limitation of the first aspect of the present invention, the training of the driving style recognition model includes: extracting historical trajectory data and driving feature data of the tracked train, including the acceleration of the vehicle, the spatial distance between the vehicle and the preceding vehicle, the time distance between the vehicle and the preceding vehicle, the relative speed between the vehicle and the preceding vehicle, and the acceleration feature variable of the vehicle, and using a Gaussian mixture model to recognize the driver style.

[0014] As a further limitation of the first aspect of the present invention, the MIC algorithm is used to calculate the correlation between feature variables and driving style; wherein, MIC evaluates the mutual information of continuous variables by applying optimal data binning technology, and measures the linear or nonlinear correlation between two variables, and the mutual information of two discrete vectors is defined as:

[0015]

[0016] MI D It is the mutual information of two discrete vectors x and y, p(x,y) is the joint probability mass function of x and y, and p(x) and p(y) are the marginal mass functions of x and y.

[0017] As a further limitation of the first aspect of the present invention, in the MPC adaptive control stage, the corresponding optimal driving mode and driving style are selected based on the driving style mode and time series mode given by the data preprocessing layer and the feature extraction layer.

[0018] As a further limitation of the first aspect of the present invention, the objective function of the control model is:

[0019]

[0020] The constraints are:

[0021] s i (k+1)=s i (k)+v i (k)T s ,

[0022] v i (k+1)=v i (k)+(u i (k)-w i(k)-g i (k))T s ,

[0023] d safe ≥0,

[0024] 0≤v i (k)≤v max ,

[0025] 0≤v i (k)≤v lim (s k ),

[0026] -u br ≤u i (k)≤u dr ,

[0027] -j max ≤j i (k)≤j max ,

[0028]

[0029] where:

[0030] d i (k)=s i-1 (k)-s i (k)-L,

[0031]

[0032] In the objective function formula, the first term is the tracking interval d between the following vehicle and the preceding vehicle. i (k) size and expected interval d des (k) represents the distance difference, and the second term controls the speed v of the following vehicle. i (k) Approaching the speed of the vehicle in front, the third term controls the acceleration u of the vehicle behind. i The change of (k); K D K v K u These are the weighting coefficients; the expected interval d. des (k), maximum train speed v max Maximum acceleration of the train u dr Maximum acceleration j of the train max It is related to the train's control mode, driving style classification, and operating conditions; d safe (k) Safety distance, d0 is a constant; v max v is the maximum speed of the train. lim (s k ) for the train at s k Speed ​​limits at the location of the line; di (k) represents the real-time spatial distance between this vehicle and the vehicle being tracked.

[0033] As a further limitation of the first aspect of the present invention, after performing group control for one control cycle, predictive control is performed for the next cycle, and predictive control output is cyclically performed. Considering that in actual driving, there may be situations where the train triggers braking or changes in trajectory characteristics due to changes in driving state or communication interruption between vehicles and between vehicles and the ground, it is necessary to compare the continuously output predictive control results with the newly acquired historical trajectory, and adjust the algorithm online according to the different comparison results.

[0034] Secondly, the present invention provides an adaptive high-speed train tracking operation control system that takes into account driving scenarios, comprising:

[0035] The acquisition module is used to acquire train operation status data and perform data statistics and processing.

[0036] The recognition module is used to process and classify train driving feature data using a pre-trained driving style recognition model to obtain driving style recognition results;

[0037] The calculation module is used to obtain the driving feature parameters most correlated with driving style and their corresponding parameter values ​​based on the MIC algorithm;

[0038] The control module combines model predictive control and online driving style recognition based on driving characteristic parameters and their corresponding values. It uses the MPC model to control trains with different driving modes and styles, thereby enabling adaptive group operation of high-speed trains.

[0039] Thirdly, the present invention provides a non-transitory computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the adaptive high-speed train tracking operation control method considering driving scenarios as described in the first aspect.

[0040] Fourthly, the present invention provides a computer device including a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor invokes the program instructions to execute the adaptive high-speed train tracking operation control method considering driving scenarios as described in the first aspect.

[0041] Fifthly, the present invention provides an electronic device comprising: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions for implementing the adaptive high-speed train tracking operation control method considering driving scenarios as described in the first aspect.

[0042] The beneficial effects of this invention are: to further improve the flexibility and adaptability of high-speed train platoons, and to propose a high-speed train control model based on a novel combination of MPC and driving style. Instead of using fixed and uniform parameters and models for the design of the control system, this invention matches and selects the corresponding control mode and driving style of the following train in real time according to the actual driving state and driving mode of the preceding train. This achieves an adaptive control method for multiple scenarios and modes, improves the adaptability and effectiveness of the control method, and solves the problem of adaptive and efficient tracking operation control of high-speed train platoons in different scenarios.

[0043] The advantages of additional aspects of the invention will be set forth more clearly in the following description or will be learned by practice of the invention. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart of the adaptive high-speed train tracking operation control algorithm considering driving scenarios, as described in an embodiment of the present invention. Detailed Implementation

[0046] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0047] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0048] It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as here.

[0049] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, and / or groups thereof.

[0050] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0051] To facilitate understanding of the present invention, the present invention will be further explained and described below with reference to the accompanying drawings and specific embodiments. However, the specific embodiments do not constitute a limitation on the embodiments of the present invention.

[0052] Those skilled in the art should understand that the accompanying drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily essential for implementing the present invention.

[0053] This invention addresses the problem of high-speed railway train trajectory prediction and train group tracking control, further improving the flexibility and adaptability of MPC in train platooning. It proposes a high-speed train control model based on a combination of MPC and driving style, aiming to achieve adaptive control for multiple scenarios and modes, thereby enhancing the adaptability and relevance of the control method.

[0054] First, the driving characteristics of high-speed trains are analyzed. The operating status of high-speed trains is highly uncertain due to the influence of the operating environment and system performance. Drivers control the train within the speed allowed by the Automatic Train Protection (ATP) system. However, due to the dynamic changes in line capacity demand and the complex and varied operating environment, drivers exhibit diverse driving styles and significant trajectory differences. Based on the behavior and attitudes of high-speed train drivers and actual driving conditions, driving styles are categorized according to common scenarios encountered in actual railway train driving. Then, driving style recognition based on a Gaussian Mixture Model (GMM) is used to discriminate the current scenario and driving state of the tracked train, clarifying multiple driving characteristics of the driver within a short period. This enables the identification of driving characteristics during high-speed train tracking operations, providing input for future short-term train trajectory prediction.

[0055] By combining model predictive control and online driving style recognition, and based on accurate driving style classification, driving characteristic parameter results, and trajectory prediction results in the early stage, a train group operation control method based on model predictive control (MPC) is proposed. This model can design control systems that meet different driving modes and driving styles for different scenarios, and realize adaptive selection of driving style and control model for tracking trains. At the same time, it meets the requirements of following performance, comfort, and accuracy, providing a better driving experience for high-speed railway train automatic driving systems with different driving modes and styles, so as to meet the style and preference of different train driving scenarios.

[0056] After performing group control for one control cycle, predictive control is performed for the next cycle, and the predictive control output is cyclically repeated. However, considering that in actual driving, temporary situations may occur due to changes in driving status or communication interruptions between vehicles or between vehicles and the ground, causing the train to trigger braking or change its trajectory characteristics, it is necessary to compare the continuously output predictive control results with the newly acquired historical trajectory, and adjust the algorithm online according to the different comparison results to achieve online adjustment of adaptive group operation control for high-speed trains.

[0057] Example 1

[0058] In this embodiment 1, an adaptive high-speed train tracking and operation control system considering driving scenarios is first provided, including: an acquisition module for acquiring train operation status data and performing data statistics and processing; an identification module for processing and classifying train driving feature data using a pre-trained driving style identification model to obtain driving style identification results; a calculation module for obtaining the driving feature parameters with the highest correlation to driving style and their corresponding parameter values ​​according to the MIC algorithm; and a control module for combining model predictive control and online driving style identification based on the driving feature parameters and their corresponding parameter values, using the MPC model to control trains with different driving modes and driving styles, thereby realizing adaptive group operation of high-speed trains.

[0059] In this embodiment, based on the above system, an adaptive high-speed train tracking operation control method considering driving scenarios is implemented, including: acquiring train operation status data and performing data statistics and processing; processing and classifying train driving feature data using a pre-trained driving style recognition model to obtain driving style recognition results; obtaining the driving feature parameters with the highest correlation to driving style and their corresponding parameter values ​​according to the MIC algorithm; combining model predictive control and online driving style recognition based on the driving feature parameters and their corresponding parameter values, and using the MPC model to control trains with different driving modes and driving styles to achieve adaptive group operation of high-speed trains.

[0060] like Figure 1 As shown, the adaptive high-speed train tracking operation control method considering driving scenarios provided by the present invention includes the following process steps:

[0061] The first step is to acquire train operation status data and perform data statistics and processing. The second step is to use a pre-trained driving style recognition model to process and classify the train driving feature data to obtain driving style recognition results. The third step is to use the MIC algorithm to obtain the driving feature parameters with the highest correlation to the driving style and their corresponding parameter values. The fourth step is to combine model predictive control and online driving style recognition, and use the MPC model to control trains with different driving modes and driving styles to achieve adaptive group operation of high-speed trains.

[0062] In this embodiment, the driving style recognition model is trained based on a Gaussian Mixture Model (GMM). The specific training method and steps are as follows:

[0063] Step 1: Data preparation stage, combining real high-speed train operation data to collect and process historical trajectories;

[0064] Organize driving characteristic data: train speed, relative speed, spatial interval, time interval, acceleration, jerkiness and other characteristic variables, and use the above variables and their statistics (maximum value, minimum value, average value) in the driving style classification in step 2.

[0065] Step 2: Driving style recognition stage. Driving style is identified through the driving style recognition model. Based on the Gaussian mixture model unsupervised clustering algorithm, the optimal clustering label of the preceding vehicle is obtained according to the manually labeled features. The label contains three styles: aggressive, moderate and conservative.

[0066] Historical trajectory data and driving characteristic data of the train tracked in Step 1 are extracted, and unsupervised clustering driving style recognition is performed. This is primarily achieved using historical data between the current train and the tracked train, including features such as the current train's acceleration, spatial distance between the current and tracked trains, temporal distance between the current and tracked trains, relative speed between the current and tracked trains, and jerk of the current train. A Gaussian Mixture Model (GMM) is then used to identify the driver's style. The GMM can be represented as a weighted sum of sub-Gaussian components, with each cluster modeled according to a different Gaussian distribution function.

[0067] For a given observed variable X = {x}, the GMM can be described as the following combined distribution function:

[0068]

[0069] Where k is the total number of sub-Gaussian models, α k The weights for each Gaussian mixture model represent the proportion of each Gaussian model in the entire model; their values ​​reflect the degree of influence of the current model on the overall model. α k Satisfying condition α k >0 and It is the probability density function of the k-th Gaussian distribution. It is the collective term for the parameters of the Gaussian distribution, μ k , Let be the mean and variance of a Gaussian distribution, respectively, which satisfy the following probability density expression:

[0070] Solving for the parameters of a Gaussian mixture model (GMM) requires the use of maximum likelihood estimation. The GMM model can be trained using the Expectation-Maximization (EM) maximum likelihood estimation algorithm. This algorithm iteratively calculates the maximization of the cost function, obtaining an approximate parameter set θ* of the Gaussian mixture model that satisfies the following formula:

[0071]

[0072] Step 3: Driving style feature extraction stage. Based on the MIC method, basic features highly correlated with group labels are evaluated to identify feature variables with a high degree of correlation with driving style. These include expected train intervals, expected train speeds, relative speeds, minimum safe distances, maximum and minimum speeds, and accelerations.

[0073] Feature extraction primarily involves analyzing the correlation between driving style and driving characteristic variables, extracting variables with a high correlation to driving style, and using these key correlated variables in the training of the train adaptive control model. Since different feature variables within the train driver's driving style have varying degrees of correlation with the driving style itself, the MIC algorithm is used to calculate the correlation between feature variables and driving style to reduce the dependence of the driving style recognition layer on these feature variables and eliminate irrelevant feature variables. MIC can evaluate the mutual information of continuous variables by applying optimal data binning techniques, measuring the linear or nonlinear correlation between two variables. The mutual information of two discrete vectors is defined as:

[0074]

[0075] MI D It represents the mutual information of two discrete vectors, where p(x,y) is the joint probability mass function of x and y. p(x) and p(y) are the marginal mass functions of x and y, respectively.

[0076] Step 4: MPC Adaptive Control Stage. Based on the driving style mode and time series mode given by the data preprocessing layer and feature extraction layer, the corresponding optimal driving mode and driving style are selected. The MPC control parameters are calculated according to Step 3.

[0077] The objective function of the control model is:

[0078]

[0079] The constraints are:

[0080] s i (k+1)=s i (k)+v i (k)T s ,

[0081] v i (k+1)=v i (k)+(u i (k)-w i (k)-g i (k))T s ,

[0082] d safe ≥0,

[0083] 0≤vi (k)≤v max ,

[0084] 0≤u i (k)≤v lim (s k ),

[0085] -u br ≤u i (k)≤u dr ,

[0086] -j max ≤j i (k)≤j max ,

[0087]

[0088] where:

[0089] d i (k)=s i-1 (k)-s i (k)-L,

[0090]

[0091] In the objective function formula, the first term is the tracking interval d between the following vehicle and the preceding vehicle. i (k) size and expected interval d des (k) represents the distance difference, and the second term controls the speed v of the following vehicle. i (k) Approaching the speed of the vehicle in front. The third term controls the acceleration u of the vehicle behind. i The change of (k) should be as smooth as possible. D K v K u These are the weight coefficients for the three objective terms. t+N p u represents the model prediction duration. i (k), w i (k), g i (k) represent the train's traction acceleration, unit basic resistance, and unit additional resistance, respectively; a br T represents the maximum braking force per unit. s Indicates the sampling interval; j max Indicates the maximum acceleration of the train; L represents the length of the train;

[0092] Expected interval d des (k), maximum train speed v max Maximum acceleration of the train u dr Maximum acceleration j of the train maxIt depends on the train's control mode, driving style classification, and operating conditions, and needs to be discussed on a case-by-case basis.

[0093] d safe (k) Safety distance is the safety constraint that ensures the two trains will not collide after emergency braking at any time t=k. d0 is a constant. Considering that there may be errors in the actual position of the trains, a safety redundancy can be set, such as d0=10m.

[0094] v max v is the maximum speed of the train. lim (s k ) for the train at s k Speed ​​limits at certain locations along the route.

[0095] d i (k) represents the real-time spatial distance between the vehicle and the vehicle being tracked, which must satisfy the constraint that the distance is greater than or equal to the minimum safe distance.

[0096] MPC adaptive control modes include two main categories: V2V communication mode and moving block control mode. The V2V communication mode is further divided into three subcategories: aggressive, moderate, and conservative. The moving block control mode is divided into two subcategories: relative braking and moving braking modes.

[0097] Information such as train expected interval, expected train speed, relative speed, safety distance, maximum and minimum speed and acceleration in the control parameters are determined according to steps 2 and 3.

[0098] Step 5: Online Adjustment of Train Control Mode

[0099] After performing group control for one control cycle, predictive control is performed for the next cycle, and the predictive control output is cyclically repeated. However, considering that in actual driving, temporary situations may occur due to changes in driving status or interruptions in communication between vehicles or between vehicles and the ground, which may cause the train to trigger braking or change its trajectory characteristics, it is necessary to compare the continuously output predictive control results with the newly acquired historical trajectory, and adjust the algorithm online according to the different comparison results, repeating steps 2 and 3.

[0100] Example 2

[0101] This embodiment 2 provides a non-transitory computer-readable storage medium for storing computer instructions. When these computer instructions are executed by a processor, they implement the adaptive high-speed train tracking operation control method considering driving scenarios as described above. The method includes:

[0102] Acquire train operation status data and perform data statistics and processing;

[0103] The train driving feature data is processed and classified using a pre-trained driving style recognition model to obtain driving style recognition results;

[0104] The driving feature parameters and their corresponding values ​​that are most correlated with driving style are obtained based on the MIC algorithm.

[0105] Based on driving characteristic parameters and their corresponding values, model predictive control and online driving style recognition are combined. The MPC model is used to control trains with different driving modes and styles, thereby achieving adaptive group operation of high-speed trains.

[0106] Example 3

[0107] This embodiment 3 provides a computer device, including a memory and a processor, wherein the processor and the memory communicate with each other, and the memory stores program instructions that can be executed by the processor. The processor calls the program instructions to execute the adaptive high-speed train tracking operation control method considering driving scenarios as described above, the method including:

[0108] Acquire train operation status data and perform data statistics and processing;

[0109] The train driving feature data is processed and classified using a pre-trained driving style recognition model to obtain driving style recognition results;

[0110] The driving feature parameters and their corresponding values ​​that are most correlated with driving style are obtained based on the MIC algorithm.

[0111] Based on driving characteristic parameters and their corresponding values, model predictive control and online driving style recognition are combined. The MPC model is used to control trains with different driving modes and styles, thereby achieving adaptive group operation of high-speed trains.

[0112] Example 4

[0113] This embodiment 4 provides an electronic device, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions for implementing the adaptive high-speed train tracking operation control method considering driving scenarios as described above. The method includes:

[0114] Acquire train operation status data and perform data statistics and processing;

[0115] The train driving feature data is processed and classified using a pre-trained driving style recognition model to obtain driving style recognition results;

[0116] The driving feature parameters and their corresponding values ​​that are most correlated with driving style are obtained based on the MIC algorithm.

[0117] Based on driving characteristic parameters and their corresponding values, model predictive control and online driving style recognition are combined. The MPC model is used to control trains with different driving modes and styles, thereby achieving adaptive group operation of high-speed trains.

[0118] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0119] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0120] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0121] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment, whereby a series of operational steps are performed to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0122] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that, based on the technical solutions disclosed in the present invention, various modifications or variations that can be made by those skilled in the art without creative effort should be included within the scope of protection of the present invention.

Claims

1. An adaptive high-speed train tracking operation control method considering driving scenarios, characterized in that, include: Acquire train operation status data and perform data statistics and processing; The train driving feature data is processed and classified using a pre-trained driving style recognition model to obtain driving style recognition results; The driving feature parameters and their corresponding values ​​that are most correlated with driving style are obtained based on the MIC algorithm. Based on driving characteristic parameters and their corresponding values, model predictive control and online driving style recognition are combined. The MPC model is used to control trains with different driving modes and styles, achieving adaptive group operation of high-speed trains. In the MPC adaptive control stage, based on the driving style patterns and time series patterns provided by the data preprocessing layer and feature extraction layer, the optimal driving mode and style are selected. The objective function of the control model is: The constraints are: In the objective function formula, the first term controls the tracking interval between the following vehicle and the preceding vehicle. Size and expected interval The distance difference, the second item is controlling the speed of the following vehicle. Approaching the speed of the vehicle in front, the third option controls the acceleration of the vehicle behind. Changes; , , These are the weighting coefficients and the expected interval, respectively. Maximum speed of train Maximum acceleration of the train Maximum acceleration of the train It is related to the train's control mode, driving style classification, and operating conditions; Safe distance, It is a constant; The maximum speed of the train. For the train in Speed ​​limits at certain points along the route; This represents the real-time spatial distance between this vehicle and the vehicle being tracked.

2. The adaptive high-speed train tracking operation control method considering driving scenarios according to claim 1, characterized in that, The training of the driving style recognition model includes: extracting historical trajectory data and driving feature data of the tracked train, including the acceleration of the vehicle, the spatial distance between the vehicle and the preceding vehicle, the time distance between the vehicle and the preceding vehicle, the relative speed between the vehicle and the preceding vehicle, and the acceleration feature variables of the vehicle. A Gaussian mixture model is used to identify the driver's style.

3. The adaptive high-speed train tracking operation control method considering driving scenarios according to claim 1, characterized in that, The MIC algorithm is used to calculate the correlation between feature variables and driving style. MIC evaluates the mutual information of continuous variables by applying optimal data binning techniques, measuring the linear or nonlinear correlation between two variables. The mutual information of two discrete vectors is defined as follows: in They are two discrete vectors and mutual information, yes and The joint probability mass function, and yes and The edge quality function.

4. The adaptive high-speed train tracking operation control method considering driving scenarios according to claim 1, characterized in that, After performing group control for one control cycle, predictive control is performed for the next cycle, and the predictive control output is cyclically repeated. Considering that in actual driving, there may be situations where the train triggers braking or changes in trajectory characteristics due to changes in driving status or communication interruptions between vehicles or between vehicles and the ground, it is necessary to compare the continuously output predictive control results with the newly acquired historical trajectory, and adjust the algorithm online according to the different comparison results.

5. An adaptive high-speed train tracking operation control system considering driving scenarios, characterized in that, include: The acquisition module is used to acquire train operation status data and perform data statistics and processing. The recognition module is used to process and classify train driving feature data using a pre-trained driving style recognition model to obtain driving style recognition results; The calculation module is used to obtain the driving feature parameters most correlated with driving style and their corresponding parameter values ​​based on the MIC algorithm; The control module combines model predictive control and online driving style recognition based on driving characteristic parameters and their corresponding values. It utilizes the MPC model to control trains with different driving modes and styles, achieving adaptive group operation of high-speed trains. In the MPC adaptive control phase, based on the driving style patterns and time series patterns provided by the data preprocessing layer and feature extraction layer, it selects the corresponding optimal driving mode and style. The objective function of the control model is: The constraints are: In the objective function formula, the first term controls the tracking interval between the following vehicle and the preceding vehicle. Size and expected interval The distance difference, the second item is controlling the speed of the following vehicle. Approaching the speed of the vehicle in front, the third option controls the acceleration of the vehicle behind. Changes; , , These are the weighting coefficients and the expected interval, respectively. Maximum speed of train Maximum acceleration of the train Maximum acceleration of the train It is related to the train's control mode, driving style classification, and operating conditions; Safe distance, It is a constant; The maximum speed of the train. For the train in Speed ​​limits at certain points along the route; This represents the real-time spatial distance between this vehicle and the vehicle being tracked.

6. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, which, when executed by a processor, implement the adaptive high-speed train tracking operation control method considering driving scenarios as described in any one of claims 1-4.

7. A computer device, characterized in that, The system includes a memory and a processor, which communicate with each other. The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the adaptive high-speed train tracking operation control method considering driving scenarios as described in any one of claims 1-4.

8. An electronic device, characterized in that, include: The electronic device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions that implement the adaptive high-speed train tracking operation control method considering driving scenarios as described in any one of claims 1-4.

Images