Virtual marshaling high-speed train control method, device and equipment based on predictive sliding mode

Abstract

The present application discloses a method, device and equipment for controlling a virtual marshaling high-speed train based on predictive sliding mode, which relates to the field of automatic control of high-speed train operation. The method includes constructing a tracking error dynamics model and a longitudinal dynamics model including a time-varying function; constructing a logarithmic terminal sliding mode surface; constructing a second-order exponential sliding mode convergence law; constructing a predictive sliding mode model for predicting the sliding mode surface, and obtaining a deformation model based on the predictive sliding mode model; constructing a second-order logarithmic terminal predictive sliding mode controller based on the longitudinal dynamics model of the virtual marshaling high-speed train, the tracking error dynamics model, the logarithmic terminal sliding mode surface, the deformation model and the second-order exponential sliding mode convergence law. The second-order logarithmic terminal predictive sliding mode controller is used to control the operation of the virtual marshaling high-speed train. The present application ensures that the virtual marshaling high-speed train can still ensure reliable and safe consistent tracking operation under numerous interference and constraint conditions.

Description

Technical Field

[0001] The present application relates to the field of automatic control of high-speed train operation, and in particular to a method, device and equipment for controlling a virtual marshaling high-speed train based on a predictive sliding mode. Background Art

[0002] In recent years, with the advancement of informatization, autonomous train tracking technology has become possible. Multiple trains can now track and control short distances, and if the vehicle's traction and braking performance allows, even operations similar to physical train formations can be achieved, known as virtual formations. However, factors such as the uncertainty of train kinematic parameters, track constraints, and sudden internal and external interference can pose safety risks to train formations. Therefore, ensuring that virtual formations of high-speed trains can maintain reliable and safe consistent tracking despite these numerous interferences and constraints is crucial. Summary of the Invention

[0003] The purpose of this application is to provide a virtual marshaling high-speed train control method, device and equipment based on predictive sliding mode, which can ensure that the virtual marshaling high-speed train can still maintain reliable and safe consistent tracking operation under many interference and constraint conditions.

[0004] To achieve the above objectives, the present application provides the following solutions: In a first aspect, the present application provides a virtual marshaling high-speed train control method based on predictive sliding mode, comprising: constructing a virtual marshaling high-speed train longitudinal dynamics model; the virtual marshaling high-speed train longitudinal dynamics model includes a time-varying function.

[0005] Construct a dynamic model of tracking error of virtual marshaling high-speed train.

[0006] Construct a logarithmic terminal sliding surface.

[0007] Construct a second-order exponential sliding mode reaching law.

[0008] Constructing a predictive sliding mode model for predicting the sliding surface, and obtaining a deformation model based on the predictive sliding mode model;

[0009] A second-order logarithmic terminal predictive sliding mode controller is constructed based on the longitudinal dynamic model of a virtual marshaling high-speed train, the tracking error dynamic model of a virtual marshaling high-speed train, the deformation model, the logarithmic terminal sliding surface and the second-order exponential sliding mode reaching law. The second-order logarithmic terminal predictive sliding mode controller is used to control the operation of the virtual marshaling high-speed train.

[0010] In the second aspect, the present application provides a virtual marshaling high-speed train control device based on predictive sliding mode, including: a virtual marshaling high-speed train longitudinal dynamics model construction module, used to construct a virtual marshaling high-speed train longitudinal dynamics model; the virtual marshaling high-speed train longitudinal dynamics model includes a time-varying function.

[0011] The module for constructing the tracking error dynamics model of a virtual marshaling high-speed train is used to construct the tracking error dynamics model of a virtual marshaling high-speed train.

[0012] Logarithmic terminal sliding surface construction module, used to construct the logarithmic terminal sliding surface.

[0013] The second-order exponential sliding mode reaching law construction module is used to construct the second-order exponential sliding mode reaching law.

[0014] The predictive sliding mode model building module is used to build a predictive sliding mode model for predicting the sliding mode surface and obtain a deformation model based on the predictive sliding mode model.

[0015] A control law construction module is used to construct a second-order logarithmic terminal prediction sliding mode controller based on the longitudinal dynamic model of the virtual marshaling high-speed train, the tracking error dynamic model of the virtual marshaling high-speed train, the deformation model, the logarithmic terminal sliding mode surface and the second-order exponential sliding mode reaching law. The second-order logarithmic terminal prediction sliding mode controller is used to control the operation of the virtual marshaling high-speed train.

[0016] In a third aspect, the present application provides a computer device comprising: 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-mentioned method for controlling a virtual high-speed train based on predictive sliding mode.

[0017] According to the specific embodiments provided in this application, the present application has the following technical effects: This application provides a method, device and equipment for controlling a virtual marshaling high-speed train based on predictive sliding mode. At present, the fact that advanced control algorithms such as optimal control, neural network control, adaptive control, and fuzzy control have been successfully applied in other fields has led some scholars to apply advanced control algorithms to the control of virtual marshaling high-speed trains and achieve good control effects. Among them, sliding mode control (SMC) is widely used to achieve train speed tracking due to its advantages such as fast response speed and strong robustness. However, traditional SMC has problems such as slow convergence speed and severe chattering phenomenon, while terminal sliding mode control (TSMC) has been widely used because of its faster convergence speed and ability to converge to the sliding mode surface within a limited time. At the same time, high-order sliding mode control (HOSMC), as an extension of SMC, can effectively suppress the "chattering" phenomenon while maintaining robustness. During the actual operation of marshaled trains, external uncertainty interference will seriously affect the stability of system operation. Although the above methods can cope with interference to a certain extent, it is still difficult to ensure consistent tracking and system reliability under complex interference and constraint conditions, resulting in the virtual marshaled high-speed train being unable to ensure reliable and safe consistent tracking operation under many interference and constraint conditions. This application constructs a longitudinal dynamic model of a virtual marshaled high-speed train including a time-varying function to enhance the system's ability to resist external interference, which can solve this problem. Constructing a logarithmic terminal sliding surface can achieve faster convergence speed and converge to the sliding surface within a limited time, thereby improving tracking accuracy and robustness. Constructing a second-order exponential sliding mode convergence law can effectively suppress the "jittering" phenomenon. A predictive sliding mode model is constructed to predict the sliding surface, and a deformation model is obtained based on the predictive sliding mode model. By predicting the future sliding mode surface, the control system can better cope with external uncertainty interference and improve its anti-interference ability. A second-order logarithmic terminal predictive sliding mode controller is constructed based on the longitudinal dynamic model, deformation model, logarithmic terminal sliding mode surface and second-order exponential sliding mode reaching law of the virtual marshaling high-speed train. The virtual marshaling high-speed train is controlled based on this controller, which can ensure that the virtual marshaling high-speed train can still maintain reliable and safe consistent tracking operation under many interference and constraint conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A flowchart of a virtual marshaling high-speed train control method based on predictive sliding mode is provided in one embodiment of the present application.

[0020] Figure 2 This is a schematic diagram of a virtual marshaling high-speed train control method based on predictive sliding mode provided in one embodiment of the present application.

[0021] Figure 3 This is the composition and topology diagram of the virtual marshaling high-speed train.

[0022] Figure 4 This is the force analysis diagram of the train movement process.

[0023] Figure 5 Graph for the second-order logarithmic terminal predictive sliding mode control scheme.

[0024] Figure 6 This is the displacement tracking error diagram of the virtual marshaling high-speed train.

[0025] Figure 7 This is the speed tracking error diagram of the virtual marshaling high-speed train.

[0026] Figure 8 This is a comparison chart of the speed tracking curve of the first high-speed train in the virtual marshaling.

[0027] Figure 9 Sliding surface for virtual high-speed train formation Result graph.

[0028] Figure 10 This is the output result diagram of the virtual marshaling high-speed train control.

[0029] Figure 11 This is a block diagram of a virtual marshaling high-speed train control device based on predictive sliding mode provided in one embodiment of the present application.

[0030] Figure 12 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0032] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0033] In an exemplary embodiment, a virtual marshaling high-speed train control method based on predictive sliding mode is provided, specifically a virtual marshaling high-speed train control method based on predictive sliding mode based on second-order logarithmic terminal predictive sliding mode (abbreviated as SLTPSMC), such as Figure 1 and Figure 2 As shown, the process includes the following steps 201 to 205.

[0034] Step 201: Construct a longitudinal dynamic model of a virtual high-speed train; the longitudinal dynamic model of the virtual high-speed train includes a time-varying function.

[0035] Step 202: Construct a virtual high-speed train tracking error dynamics model.

[0036] Step 203: Construct a logarithmic terminal sliding surface.

[0037] Step 204: Construct a second-order exponential sliding mode reaching law.

[0038] Step 205: constructing a predictive sliding mode model for predicting the sliding surface, and obtaining a deformation model based on the predictive sliding mode model.

[0039] Step 206: Based on the virtual marshaling high-speed train longitudinal dynamics model, the virtual marshaling high-speed train tracking error dynamics model, the deformation model, the logarithmic terminal sliding mode surface and the second-order exponential sliding mode reaching law, a second-order logarithmic terminal predictive sliding mode controller is constructed. The second-order logarithmic terminal predictive sliding mode controller is used to control the operation of the virtual marshaling high-speed train. The control scheme is shown in FIG. Figure 5 .

[0040] In another exemplary embodiment of the present application, a virtual high-speed train longitudinal dynamics model is constructed, specifically: the composition and topology of the virtual high-speed train are as follows: Figure 3 ,This topology structure indicates that the unit train receives the running status information of the preceding train to calculate the displacement and speed difference between the two adjacent unit trains in motion, and achieves the local control target by minimizing the difference between the adjacent unit trains. Combined with the train running conditions, the force analysis of the train motion process is as follows Figure 4 According to Newton's laws of kinematics, the traction, braking force, basic resistance, additional resistance, and disturbances experienced by the train during operation are comprehensively analyzed. Based on the composition and topology of the virtual marshaling high-speed train and the train operation conditions, the train operation process is comprehensively analyzed according to Newton's laws of kinematics, and the longitudinal dynamic model of the virtual marshaling high-speed train is established as Equation (1).

[0041] (1).

[0042] Where, Indicates the number of the virtual high-speed train Trains ( ), and Indicates the Trains in Displacement and velocity at a moment; and express and The first derivative of Indicates the number of the virtual high-speed train The mass of the train, Indicates the number of the virtual high-speed train The traction rotation mass coefficient of the train; Indicates the number of the virtual high-speed train Trains in Always in control; Indicates the Trains in The fundamental resistance of the moment, ,in 、 and is the Davis coefficient, which may vary due to different vehicle models and line conditions; is the slope of the ramp in thousandths, represents the gravity coefficient; Indicates the additional resistance of the curve, , is the empirical coefficient; is the radius of the curved track; represents the additional resistance of the tunnel, , is the tunnel friction coefficient, is the tunnel length; Represents a time-varying function, specifically at time The external interference received by the train is uncertain because the train will be affected by factors such as uneven track surface and gusts of wind during travel. Therefore, a time-varying function ( ) is used to represent the external interference that the high-speed train is subjected to during its operation.

[0043] For ease of writing, Equation (1) is rewritten as the standard state space equation, namely Equation (2).

[0044] (2).

[0045] Where, and Representative The displacement and speed of the train, and express and The first derivative of ; To include The known items of basic resistance and additional resistance of train; For the The inverse of the mass of a train; d (t) is the disturbance power of the train The uncertain external interference term.

[0046] In another exemplary embodiment of the present application, a tracking error dynamics model for virtual high-speed trains is constructed. Specifically, when virtual high-speed trains operate in a coordinated manner, the first train tracks the target speed curve, while subsequent trains track the speed of the previous train's tail, operating in a lead-follow mode. For the first train, the tracking error dynamics model is defined as Equation (3).

[0047] (3).

[0048] The dynamic model of the tracking error between the following vehicle and the preceding train is given by Equation (4).

[0049] (4).

[0050] in, greater than 1, and Represents the first train in The displacement error and velocity error at the moment, and Represents the first train in Displacement and velocity at a moment; and Respectively represent The target displacement and target speed at the moment, 、 Representing the Trains in Displacement error and velocity error at each moment; 、 Respectively represent Trains in The displacement and speed of the moment, Indicates the Trains in the speed of the moment; is the initial moment of virtual group operation, Indicates the basic safety distance, Indicates the The length of the train, Represents safety margin.

[0051] For two virtual marshaling high-speed trains running at a short interval, a collision may occur if the preceding unit train applies emergency braking. Therefore, considering the emergency braking and the response time of the train issuing the braking command, the anti-collision constraint is considered as follows: .

[0052] in, , Indicates that the Zth train is The displacement of time, Indicates the The train length of the train, Indicates the response time of issuing a braking command, and Respectively represent Car and Trains in The speed of time, and Respectively represent Car and The emergency braking rate of the train, Indicates the minimum safe interval; when the distance between the leading and trailing trains is less than the minimum safe interval, the trailing train will immediately trigger emergency braking to stop to ensure train operation safety requirements.

[0053] In another exemplary embodiment of the present application, an integral term is introduced into the non-singular terminal sliding surface to obtain a non-singular terminal integral sliding surface, specifically: in the traditional sliding function Based on the state error of displacement and velocity 、 , the sign function and the natural logarithm function are introduced to construct the logarithmic terminal sliding surface, as shown in Equation (5). This nonlinear sliding surface can make the system tracking error converge to zero along the sliding surface in a finite time, solving the problem that the traditional sliding mode method cannot make the system state error converge to zero in a finite time.

[0054] (5).

[0055] in, Indicates the number of the virtual high-speed train Trains in The logarithmic terminal sliding surface at time , Indicates the number of the virtual high-speed train Trains in The displacement tracking error at time t, express The first sliding surface gain is a positive parameter to be designed, In( ) represents the natural logarithmic function, express The first constant parameter, which has no practical significance and is designed according to performance requirements, is a positive real number. express The second sliding surface gain positive parameter to be designed in is Indicates the number of the virtual high-speed train Trains in The velocity tracking error at the moment, express The second constant parameter, which is designed based on performance requirements and has no practical significance, is a positive real number. sgn() represents the sign function. ; When the system is close to the sliding surface, the main control role is played by part; and when it is stable on the sliding surface, Plays a major controlling role, and The value of determines the actual weight of the sliding surface in the two stages. Generally, a larger value to improve the speed, and after the steady state The value will have a significant impact on the system displacement error.

[0056] In another exemplary embodiment of the present application, since the chattering problem of sliding mode control seriously affects the control accuracy of the system, it is necessary to improve the sliding mode reaching law and construct a second-order sliding mode exponential reaching law, as shown in formula (6). This is a special case where the first-order derivative is not zero and the second-order derivative is zero. By removing the sign function of high-frequency switching, the system output is smoother, so that a continuous control law can be obtained. When the system reaches the sliding surface, ,have Therefore, it is stable at the equilibrium point and does not produce a chattering with an amplitude, so the system can effectively enter the sliding mode stage and avoid chattering.

[0057] (6).

[0058] in, represents the second-order exponential sliding mode reaching law of the i-th train in the virtual high-speed train at time t, express The first reaching law gain coefficient of for The parameters in are of no practical significance and are negative real numbers. represents the logarithmic terminal sliding surface of the i-th train in the virtual high-speed train at time t, express The second reaching law gain coefficient of | | represents the absolute value, and Both are the rate of increase of switching gain, and both are positive real numbers. The larger the value, the more obvious the effect of suppressing system chattering. However, it will also affect the convergence speed of the system. Moreover, if the value is too large, it will affect the stability of the system.

[0059] Derivative of formula (5) yields formula (7). It represents the first-order derivative of the logarithmic terminal sliding surface of the i-th train in the virtual high-speed train formation at time t. The specific form is:

[0060] (7).

[0061] in, express The first derivative of express The first derivative of .

[0062] In another exemplary embodiment of the present application, a predictive sliding model for predicting a sliding surface is constructed, and a deformation model is obtained based on the predictive sliding model, which specifically includes steps one to three.

[0063] Step 1: Construct a predictive sliding model for predicting the sliding surface. Prediction time The sliding mode function model is the prediction sliding mode model as shown in formula (8). By predicting the sliding surface, the control system can plan and adjust the control strategy in advance to ensure that the system state reaches the desired sliding surface within a predetermined timeframe. This proactive control helps reduce system response delays and improve control efficiency. Furthermore, sliding mode control is inherently robust, meaning it is insensitive to changes in system parameters and external disturbances. By predicting the future sliding surface, the control system can better cope with these uncertainties, further enhancing system stability and robustness.

[0064] (8).

[0065] in, represents the logarithmic terminal sliding surface of the i-th train in the virtual high-speed train at time t+T, for The first derivative of .

[0066] Step 2: Construct the objective function of the predictive sliding mode model. Construct the objective function of the predictive sliding mode model is formula (9).

[0067] (9).

[0068] in, is the train displacement, is the running time, For control, Forecast time.

[0069] Step 3: Based on the objective function, the predictive sliding mode model is processed to obtain the deformation model. According to the objective function shown in formula (9), to achieve optimal control, formula (10) must be satisfied.

[0070] (10).

[0071] Substituting Equation (9) into Equation (10), the equation that satisfies the conditions can be transformed into Equation (11).

[0072] (11).

[0073] From formula (11), we can see that if we want to satisfy You need to meet , which means that the speed error of the system needs to be kept at 0, which is difficult to achieve, so we choose to meet the former condition. , Formula (8) can be transformed into Formula (12), and Formula (12) is a deformation model.

[0074] (12).

[0075] In another exemplary embodiment of the present application, a second-order logarithmic terminal prediction sliding mode controller is constructed based on the virtual formation high-speed train longitudinal dynamics model, the virtual formation high-speed train tracking error dynamics model, the deformation model, the logarithmic terminal sliding mode surface and the second-order exponential sliding mode reaching law, specifically including steps (1) to (5).

[0076] Step (1): Substituting the expression (7) into the left side of formula (12), the formula is transformed into formula (13).

[0077] (13).

[0078] Step (2): Extracted to the left side of Equation (13), it can be transformed into Equation (14).

[0079] (14).

[0080] Step (3): At the same time, according to the tracking error dynamics model, we can get The expression is: , and let the term on the right side of equation (14) be , then the formula is transformed into formula (15).

[0081] (15).

[0082] when hour, That is , for The first derivative of the target curve velocity at time t.

[0083] Step (4): Substitute equation (1) in the manual into the left side of equation (15) and transform the equation to obtain equation (16).

[0084] (16).

[0085] Step (5): Divide the left side of equation (16) by Move all the terms to the right side of the equation, substitute the expression of B, that is, the right side of the equal sign of equation (14), into it, and also substitute the logarithmic terminal sliding mode surface (equation (5)) and the second-order exponential sliding mode reaching law (equation (6)) into it, then The expression is as follows:

[0086] (17).

[0087] in, Indicates the number of the virtual high-speed train Trains in The first-order derivative of the velocity at the moment is used to optimally solve the objective function and finally construct a second-order logarithmic terminal predictive sliding mode controller.

[0088] This application also provides an embodiment of controller stability proof, which specifically includes the following steps. For the convenience of formula derivation, time t is omitted below.

[0089] Define the Lyapunov function as equation (18).

[0090] (18).

[0091] in, represents the i-th Lyapunov function, represents the non-singular terminal integral sliding mode surface of the i-th train in the virtual high-speed train formation.

[0092] From this we can get formula (19).

[0093] (19).

[0094] in, express The first derivative of express The first derivative of express The first derivative of represents the displacement tracking error of the i-th train, represents the speed tracking error of the i-th train, express The first derivative of .

[0095] Substituting equation (17) into equation (19), we obtain equation (20).

[0096] (20).

[0097] The stability of the controller is analyzed from the following two situations.

[0098] Case 1): : At this time, the form of formula (21) remains unchanged as formula (22).

[0099] (twenty two).

[0100] because and is a negative real number to be designed, so there exists .

[0101] Case 2): : Now we can get formula (23).

[0102] (twenty three).

[0103] because and and They are all positive numbers so they still exist .

[0104] In summary in and For any value, ,according to , , LaSalle invariant set principle, when hour, , according to the terminal sliding characteristics, , Therefore, it is proved that the controller satisfies the Lyapunov stability condition, and therefore it can be concluded that Equation (18) is stable. This application is applicable to the tracking control of a virtual marshaling high-speed train on a target running curve.

[0105] This application establishes a longitudinal dynamic model and a tracking error dynamic model of a virtual marshaling high-speed train based on the composition and topological structure of the virtual marshaling high-speed train and the operating characteristics of the unit train; taking into account numerous interference and constraint conditions, a second-order logarithmic terminal predictive sliding mode control method is used to accurately track the target operating speed curve of the train, which can realize the tracking of the target operating curve during the operation of the virtual marshaling high-speed train, realize the safe and reliable consistent tracking operation of the virtual marshaling high-speed train, and meet the safety protection control requirements of the virtual marshaling high-speed train.

[0106] The second-order logarithmic terminal predictive sliding mode controller constructed in this application has the characteristics of high tracking accuracy, fast system response speed and strong ability to reduce vibration.

[0107] This application also provides an example to illustrate the effectiveness of the predictive sliding mode-based virtual marshaling high-speed train control method provided in this application. This experiment was conducted on the train model described by Equations (1) and (2). The three selected train models were Harmony CRH380B high-speed trains with a train mass of 473.63 tons.

[0108] This application will mainly analyze the train displacement and speed The tracking effect, the response time and speed of the train system under the second-order logarithmic terminal prediction sliding mode control method, and the output of the controller. The implementation experiment of this application will be completed in the Simulink environment in Matalaab.

[0109] Figure 6 and Figure 7 The displacement tracking error diagram and speed tracking error diagram of the virtual marshaling high-speed train are respectively used to analyze the actual tracking effect of the controller. It can be seen that under the SLTPSMC control method proposed in this application, the three trains all show the characteristics of small average displacement and speed tracking errors and high tracking accuracy. When the operating environment and the train operating status change, the error can also be stabilized in a short time, showing good tracking accuracy.

[0110] Figure 8 The enlarged part is a partial enlarged view of the first train starting to start, showing the situation of train 1 starting to track the target curve under different control methods, and showing the response time of the system tracking the target curve under different control methods. Figure 8 From the enlarged part of the figure, it can be seen that the introduction of logarithmic terminal sliding mode control significantly improves the response time of the system tracking the target curve. SLTPSMC is better than Prediction Sliding Mode Control (PSMC) and has faster response speed and shorter response time.

[0111] from Figure 9 It can be seen that the sliding surface The dynamic changes of the sliding mode control system, the ultimate ideal state of the sliding surface is to stabilize at The equilibrium position and no longer leaves, from Figure 9 It can be seen that the SLTPSMC method is consistent with the steady-state sliding surface When the operating environment and train running status change, the sliding surface can also tend to be stable in a short time and remain close to it.

[0112] Figure 10 The change in control force corresponding to a virtual high-speed train is depicted. For virtual high-speed train control systems, controller stability is paramount. Maintaining controller stability requires eliminating chattering. The SLTPSMC control system, which incorporates a second-order exponential sliding mode reaching law, exhibits excellent performance and effectively mitigates controller chattering.

[0113] Multiple simulation results show that when the second-order exponential terminal predictive sliding mode control method is used to track the target operating curve of a virtual high-speed train, accurate tracking of the position and speed of the virtual high-speed train is achieved. At the same time, the response speed of the control system is improved and the controller chattering is effectively weakened, providing a new method for constructing a predictive sliding mode controller for train speed tracking control.

[0114] Based on the same inventive concept, the embodiments of the present application also provide a virtual marshaling high-speed train control device based on a predictive sliding mode for implementing the aforementioned virtual marshaling high-speed train control method based on a predictive sliding mode. The implementation solution provided by the device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the virtual marshaling high-speed train control device based on a predictive sliding mode provided below can be found in the above-mentioned limitations of the virtual marshaling high-speed train control method based on a predictive sliding mode, and will not be repeated here.

[0115] In an exemplary embodiment, Figure 11 As shown, a virtual marshaling high-speed train control device based on predictive sliding mode is provided, including: a virtual marshaling high-speed train longitudinal dynamics model construction module A1, used to construct a virtual marshaling high-speed train longitudinal dynamics model; the virtual marshaling high-speed train longitudinal dynamics model includes a time-varying function.

[0116] The virtual marshaling high-speed train tracking error dynamics model construction module A2 is used to construct the virtual marshaling high-speed train tracking error dynamics model.

[0117] The logarithmic terminal sliding surface construction module A3 is used to construct the logarithmic terminal sliding surface.

[0118] The second-order exponential sliding mode reaching law construction module A4 is used to construct the second-order exponential sliding mode reaching law.

[0119] The predictive sliding mode model building module A5 is used to build a predictive sliding mode model for predicting the sliding mode surface, and obtain a deformation model based on the predictive sliding mode model.

[0120] The control law construction module A6 is used to construct a second-order logarithmic terminal prediction sliding mode controller based on the longitudinal dynamic model of the virtual marshaling high-speed train, the tracking error dynamic model of the virtual marshaling high-speed train, the deformation model, the logarithmic terminal sliding mode surface and the second-order exponential sliding mode reaching law. The second-order logarithmic terminal prediction sliding mode controller is used to control the operation of the virtual marshaling high-speed train.

[0121] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 12 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an 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 is used to store virtual marshaling high-speed train control data based on predictive sliding mode. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a virtual marshaling high-speed train control method based on predictive sliding mode is implemented.

[0122] Those skilled in the art will understand that Figure 12 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application and does not constitute a limitation on the computer device to which the solution of the present application is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the above-mentioned method embodiments when executing the computer program.

[0123] 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, stored data, displayed data, 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 relevant data must comply with relevant regulations.

[0124] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, 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 may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0125] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0126] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, 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.

[0127] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A virtual marshaling high-speed train control method based on predictive sliding mode, characterized in that: The virtual marshaling high-speed train control method based on predictive sliding mode includes: Constructing a virtual marshaling high-speed train longitudinal dynamics model; the virtual marshaling high-speed train longitudinal dynamics model includes a time-varying function; Construct a dynamic model of tracking error of virtual marshaling high-speed trains; Construct logarithmic terminal sliding surface; Construct a second-order exponential sliding mode reaching law; Constructing a predictive sliding mode model for predicting the sliding surface, and obtaining a deformation model based on the predictive sliding mode model; A second-order logarithmic terminal prediction sliding mode controller is constructed based on the longitudinal dynamic model of the virtual marshaling high-speed train, the tracking error dynamic model of the virtual marshaling high-speed train, the deformation model, the logarithmic terminal sliding mode surface and the second-order exponential sliding mode reaching law. The second-order logarithmic terminal prediction sliding mode controller is used to control the operation of the virtual marshaling high-speed train; the second-order logarithmic terminal prediction sliding mode controller is: in, For the first time in the virtual marshaling high-speed train Trains in Always in control, Indicates the number of the virtual high-speed train The mass of the train, Indicates the number of the virtual high-speed train The traction rotation mass coefficient of the train, express The first reaching law gain coefficient of for There are no practical parameters in Indicates the number of the virtual high-speed train Trains in The logarithmic terminal sliding surface at time , express The second reaching law gain coefficient of | | represents the absolute value, express The first sliding surface gain positive parameter to be designed in is express The first constant parameter has no practical significance. Indicates the number of the virtual high-speed train Trains in The displacement tracking error at time t, express The first derivative of represents the second-order exponential sliding mode reaching law of the i-th train in the virtual high-speed train at time t, express The second constant parameter has no practical significance. Indicates the number of the virtual high-speed train Trains in The velocity tracking error at the moment, represents the symbolic function, represents the prediction time, express The second sliding surface gain positive parameter to be designed in is Indicates the number of the virtual high-speed train Trains in The first derivative of the velocity at time , represents the basic resistance of the i-th train in the virtual high-speed train formation, represents the gravity coefficient, Indicates the slope of the ramp in thousandths. Indicates the additional resistance of the curve, represents the additional resistance of the tunnel, Indicates the external interference to the virtual train. hour, That is , for The derivative of the target curve velocity at time t.

2. The method for controlling a virtual marshaling high-speed train based on predictive sliding mode according to claim 1, characterized in that: The logarithmic terminal sliding surface is: ;in, represents the logarithmic terminal sliding surface of the i-th train in the virtual high-speed train at time t, Indicates the number of the virtual high-speed train Trains in The displacement tracking error at time t, express The first sliding surface gain is a positive parameter to be designed, In( ) represents the natural logarithmic function, express The first constant parameter has no practical significance. express The second sliding surface gain positive parameter to be designed in is Indicates the number of the virtual high-speed train Trains in The velocity tracking error at the moment, express The second constant parameter, sgn(), which has no actual meaning, represents the sign function.

3. The method for controlling a virtual marshaling high-speed train based on predictive sliding mode according to claim 1, characterized in that: The deformation model is obtained based on the predictive sliding mode model, which specifically includes: Construct the objective function of the predictive sliding mode model; The predictive sliding mode model is processed based on the objective function to obtain the deformation model.

4. The method for controlling a virtual marshaling high-speed train based on predictive sliding mode according to claim 3, characterized in that: The deformation model is: ,in, for The first derivative of represents the second-order exponential sliding mode reaching law of the i-th train in the virtual high-speed train at time t, represents the logarithmic terminal sliding surface of the i-th train in the virtual high-speed train at time t, and T represents the prediction time.

5. The method for controlling a virtual marshaling high-speed train based on predictive sliding mode according to claim 1, characterized in that: The second-order exponential sliding mode reaching law is: in, represents the second-order exponential sliding mode reaching law of the i-th train in the virtual high-speed train at time t, express The first reaching law gain coefficient of for There are no practical parameters in represents the logarithmic terminal sliding surface of the i-th train in the virtual high-speed train at time t, express The second reaching law gain coefficient of .

6. A virtual marshaling high-speed train control device based on predictive sliding mode, characterized in that: The virtual marshaling high-speed train control device based on predictive sliding mode includes: A virtual marshaling high-speed train longitudinal dynamics model construction module is used to construct a virtual marshaling high-speed train longitudinal dynamics model; the virtual marshaling high-speed train longitudinal dynamics model includes a time-varying function; A module for constructing a tracking error dynamics model of a virtual marshaling high-speed train is used to construct a tracking error dynamics model of a virtual marshaling high-speed train; Logarithmic terminal sliding surface construction module, used to construct the logarithmic terminal sliding surface; Second-order exponential sliding mode reaching law construction module, used to construct the second-order exponential sliding mode reaching law; A predictive sliding mode model building module is used to build a predictive sliding mode model for predicting the sliding mode surface and obtain a deformation model based on the predictive sliding mode model; A control law construction module is used to construct a second-order logarithmic terminal prediction sliding mode controller based on the virtual marshaling high-speed train longitudinal dynamics model, the virtual marshaling high-speed train tracking error dynamics model, the deformation model, the logarithmic terminal sliding mode surface and the second-order exponential sliding mode reaching law. The second-order logarithmic terminal prediction sliding mode controller is used to control the operation of the virtual marshaling high-speed train; the second-order logarithmic terminal prediction sliding mode controller is: in, For the first time in the virtual marshaling high-speed train Trains in Always in control, Indicates the number of the virtual high-speed train The mass of the train, Indicates the number of the virtual high-speed train The traction rotation mass coefficient of the train, express The first reaching law gain coefficient of for There are no practical parameters in Indicates the number of the virtual high-speed train Trains in The logarithmic terminal sliding surface at time , express The second reaching law gain coefficient of | | represents the absolute value, express The first sliding surface gain positive parameter to be designed in is express The first constant parameter has no practical significance. Indicates the number of the virtual high-speed train Trains in The displacement tracking error at time t, express The first derivative of represents the second-order exponential sliding mode reaching law of the i-th train in the virtual high-speed train at time t, express The second constant parameter has no practical significance. Indicates the number of the virtual high-speed train Trains in The velocity tracking error at the moment, represents the symbolic function, represents the prediction time, express The second sliding surface gain positive parameter to be designed in is Indicates the number of the virtual high-speed train Trains in The first derivative of the velocity at time , represents the basic resistance of the i-th train in the virtual high-speed train formation, represents the gravity coefficient, Indicates the slope of the ramp in thousandths. Indicates the additional resistance of the curve, represents the additional resistance of the tunnel, Indicates the external interference to the virtual train. hour, That is , for The derivative of the target curve velocity at time t.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the virtual marshaling high-speed train control method based on predictive sliding mode according to any one of claims 1 to 5.

Images