A multi-particle collaborative control method, system, device and medium for high-speed trains

Abstract

The present application discloses a multi-particle collaborative control method, system, device and medium for high-speed trains, which relates to the field of high-speed train operation control. The method includes: dividing the carriages of the high-speed train into multiple groups, and constructing a discretized dynamic equation of the high-speed train; performing multi-objective optimization on the control gain and sliding mode surface parameters according to the displacement tracking error and coupler force of the high-speed train within a set time period; based on the optimal control gain, estimating the equivalent coupler force and composite resistance between groups of the high-speed train in real time; determining a non-singular fast terminal sliding mode surface based on the optimal sliding mode surface parameters and the displacement tracking error of the high-speed train; and solving the control input in real time according to the non-singular fast terminal sliding mode surface, the estimated value of the equivalent coupler force between groups, the estimated value of the composite resistance, and the discretized dynamic equation, so as to control the traction and braking forces of the front driving group and the rear driving group in real time. The present application improves the control accuracy, anti-interference ability and safety of the coupler force of the high-speed train.

Description

Technical Field

[0001] The present application relates to the field of high-speed train operation control, and particularly to a multi-particle collaborative control method, system, device and medium for high-speed trains. Background Art

[0002] As the core equipment of modern rail transit, the operation safety, ride comfort and energy efficiency optimization of high-speed trains are the key points of technical research. Taking the CRH380B EMU as an example, this type of train adopts an alternating formation design of motor cars and trailers. Although it can improve the utilization rate of traction power, the non-uniform distribution of power will cause the middle trailers to bear significantly higher dynamic coupler forces than those at both ends. Test data shows that under emergency braking or variable slope conditions, the peak coupler force of the middle car can reach 156.3 kN, far exceeding the 80 kN safety threshold specified in the "Railway Vehicle Strength Design Specification". This will exacerbate the mechanical fatigue of the coupler buffer device, and may even lead to the disconnection of the coupler in severe cases. Currently, solutions such as locally strengthening the coupler buffer device or optimizing the driving curve are usually adopted to alleviate such problems. However, these methods only stay at the level of mechanical structure improvement and operation strategy, and fail to solve the problem of unbalanced force chain transmission under the coupling action of multiple power units from the perspective of dynamic control, resulting in the inability to achieve global optimization of the dynamic distribution of coupler forces.

[0003] In the field of train integrated vehicle collaborative control, sliding mode control is widely used in the coordinated control of multiple power units due to its strong robustness. However, the sampling delay and quantization error in the discretization process will exacerbate the discontinuous switching characteristics of the control signal, resulting in severe oscillation of the traction or braking force output, which is difficult to meet the ride comfort adjustment requirements of high-speed trains. Moreover, the unmodeled dynamic coupling of coupler forces and the spatio-temporal distribution characteristics of resistance will lead to a large deviation in the mean square error of train disturbance estimation.

[0004] Therefore, the current solutions are difficult to achieve collaborative optimization among multiple conflicting objectives such as speed tracking accuracy, coupler force balance and energy consumption efficiency. Especially under complex line conditions, they cannot meet the high safety, high ride comfort and long-life maintenance requirements of high-speed trains. Summary of the Invention

[0005] The purpose of the present application is to provide a multi-particle collaborative control method, system, device and medium for high-speed trains, which can improve the control accuracy, anti-interference ability and safety of coupler forces of high-speed trains.

[0006] To achieve the above purpose, the present application provides the following solutions:

[0007] In the first aspect, the present application provides a multi-particle collaborative control method for high-speed trains, including:

[0008] Divide the carriages of a high-speed train into multiple groups, and construct a discretized dynamic equation for the high-speed train; the multiple groups are respectively a front-drive group, an intermediate group, and a rear-drive group; the state vector of the discretized dynamic equation includes the displacement and velocity of each group; the control inputs of the discretized dynamic equation include the traction braking force of the front-drive group and the traction braking force of the rear-drive group;

[0009] Based on the displacement tracking error and coupler force of the high-speed train within a set time period, perform multi-objective optimization on the control gain and sliding mode surface parameters to obtain the optimal control gain and optimal sliding mode surface parameters;

[0010] Based on the optimal control gain, estimate the equivalent coupler force and composite resistance between groups of the high-speed train in real time to obtain the estimated value of the equivalent coupler force between groups and the estimated value of the composite resistance;

[0011] Based on the optimal sliding mode surface parameters and the displacement tracking error of the high-speed train, determine a non-singular fast terminal sliding mode surface;

[0012] According to the non-singular fast terminal sliding mode surface, the estimated value of the equivalent coupler force between groups, the estimated value of the composite resistance, and the discretized dynamic equation, solve the control input in real time to control the traction braking force of the front-drive group and the traction braking force of the rear-drive group in real time.

[0013] In a second aspect, the present application provides a multi-particle collaborative control system for a high-speed train, including:

[0014] A dynamic equation construction module for dividing the carriages of a high-speed train into multiple groups and constructing a discretized dynamic equation for the high-speed train; wherein, the multiple groups are respectively a front-drive group, an intermediate group, and a rear-drive group; the state vector of the discretized dynamic equation includes the displacement and velocity of each group; the control inputs of the discretized dynamic equation include the traction braking force of the front-drive group and the traction braking force of the rear-drive group;

[0015] A parameter optimization module for performing multi-objective optimization on the control gain and sliding mode surface parameters based on the displacement tracking error and coupler force of the high-speed train within a set time period to obtain the optimal control gain and optimal sliding mode surface parameters;

[0016] A data estimation module for estimating the equivalent coupler force and composite resistance between groups of the high-speed train in real time based on the optimal control gain to obtain the estimated value of the equivalent coupler force between groups and the estimated value of the composite resistance;

[0017] A sliding mode surface determination module for determining a non-singular fast terminal sliding mode surface based on the optimal sliding mode surface parameters and the displacement tracking error of the high-speed train;

[0018] A control module, configured to solve a control input in real time according to the nonsingular fast terminal sliding mode surface, the estimated value of the equivalent coupler force between groups, the estimated value of the composite resistance, and the discretized dynamic equation, so as to control the traction and braking forces of the front drive group and the traction and braking forces of the rear drive group in real time.

[0019] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the above-mentioned multi-particle cooperative control method for high-speed trains.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned multi-particle cooperative control method for high-speed trains is implemented.

[0021] According to the specific embodiments provided by the present application, the present application has the following technical effects:

[0022] The present application provides a multi-particle cooperative control method, system, device, and medium for high-speed trains. By dividing the carriages of a high-speed train into a front drive group, an intermediate group, and a rear drive group, and constructing a discretized dynamic equation of the high-speed train to characterize the dynamic constraints of the coupler force, multi-objective optimization of the control gain and sliding mode surface parameters is performed according to the displacement tracking error and coupler force of the high-speed train within a set time period, balancing the tracking accuracy of the train and the coupler force of the carriages. A nonsingular fast terminal sliding mode surface is designed to eliminate the singularity of traditional sliding mode control and accelerate the convergence speed. During the solution process of the control input, dynamic compensation for disturbances is performed through the estimated value of the equivalent coupler force between groups and the estimated value of the composite resistance, improving the control accuracy, anti-interference ability, and safety of the coupler force of the high-speed train. Description of the Drawings

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0024] Figure 1 It is an application environment diagram of a multi-particle cooperative control method for high-speed trains in an embodiment of the present application.

[0025] Figure 2 It is a flowchart of a multi-particle cooperative control method for high-speed trains provided in an embodiment of the present application.

[0026] Figure 3 It is a block diagram of a multi-particle cooperative control method for high-speed trains provided in an embodiment of the present application.

[0027] Figure 4 Schematic diagram of the motor car - trailer chain - type discrete multi - particle model constructed in an embodiment of the present application.

[0028] Figure 5 Technical roadmap of a multi - particle cooperative control method for high - speed trains provided in an embodiment of the present application.

[0029] Figure 6 Schematic diagram of the functional modules of a multi - particle cooperative control system for high - speed trains provided in an embodiment of the present application. Detailed implementation manners

[0030] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present application.

[0031] To make the above - mentioned objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the drawings and specific implementation manners.

[0032] The multi - particle cooperative control method for high - speed trains provided in the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. In addition, in some embodiments, the multi - particle cooperative control method for high - speed trains can also be implemented independently by the server 104 or the terminal 102.

[0033] Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in - vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head - mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0034] In an exemplary embodiment, as Figure 2 and Figure 3As shown, a multi-particle collaborative control method for high-speed trains is provided. This method is executed by a computer device, which can be specifically executed by a computer device such as a terminal or a server alone, or jointly executed by a terminal and a server. In the embodiments of the present application, taking the application of this method to Figure 1 server 104 in

[0035] as an example, the method includes the following steps 201 to 205.

[0036] In view of the existing research, this application analyzes the problems of uneven coupler force distribution, underactuated characteristics, and disturbance sensitivity of high-speed multiple units. Considering an 8-car formation CRH380B high-speed train, where the motor car drive units are located in cars 1, 3, 6, and 8, and the trailer units are located in cars 2, 4, 5, and 7. The motion of each car satisfies:

[0037] ;

[0038] where is the mass of the th car, is the acceleration of the th car, is the traction braking force of the th car, is the coupler force of the th car, , is the coupler stiffness coefficient of the th car, is the coupler damping coefficient of the th car, is the displacement of the th car, is the displacement of the th car, is the velocity of the th car, is the velocity of the th car, is the combined resistance of the th car, , is the unmodeled disturbance of the th car, , , is the Basic resistance coefficient of the carriages.

[0039] Define the state vector , the input vector , and the linearized model can be obtained: .

[0040] Among them, is the system matrix, and the input matrix , .

[0041] The input matrix The rank of represents the number of independent control channels. For CRH380B trains: , while the degree of freedom of the system is 16. Obviously, , so in the common multi-particle modeling of high-speed trains, the dimension of its control input < the dimension of the system state, thus presenting an underactuated characteristic, resulting in excessive coupler forces between the 3rd and 5th carriages of the train.

[0042] In view of the underactuated characteristic presented by the CRH380B high-speed train during operation, this application divides the high-speed train into a front drive group, an intermediate group, and a rear drive group, and establishes a discretized dynamic equation including the dynamic constraint of the coupler force.

[0043] As Figure 4 shown, first, a motor-trailer chain-type discrete multi-particle model is constructed. The motor carriages are represented by solid wheels, and the trailer carriages are represented by hollow wheels. That is, in the CRH380B high-speed train, the 1st, 3rd, 6th, and 8th carriages are motor carriages, and the 2nd, 4th, 5th, and 7th carriages are trailer carriages. The first three carriages are taken as the front drive group , the middle two carriages are taken as the intermediate group , and the last three carriages are taken as the rear drive group for modeling. To are 8 carriages, is the resistance received by the high-speed multiple unit, is the coupler force between carriages, is the output control force, v is the forward direction of the train.

[0044] On the basis of analyzing the underactuated characteristic in traditional high-speed trains, the front drive group of the train is designed , including the 1st - 3rd carriages, with a mass , and the control input is , that is, k the traction and braking force of the front drive group at time, the intermediate group includes the 4th - 5th carriages, with a mass , and has no direct control input. The rear drive group , includes the 6th - 8th carriages, with a mass , the control input is , that is k the traction braking force of the rear drive group after is used as the virtual control quantity and mapped to the control inputs of the front drive group and the rear drive group through the dynamic coupling relationship. , , where is the control input of the front drive group after mapping, is the control input of the rear drive group after mapping, is k the displacement of the front drive group at and the intermediate group the vehicle coupling force between them. The specific calculation formula is , d is the coupler stiffness coefficient, is the damping coefficient, is k the displacement of the front drive group at is k the displacement of the intermediate group at is k the velocity difference form of the front drive group at is k the velocity difference form of the intermediate group at is k the vehicle coupling force between the intermediate group at and the rear drive group at . c is the basic resistance coefficient, is the velocity difference form of the rear drive group.

[0045] Define the state vector , is the displacement of the front drive group, is the velocity of the front drive group, is the displacement of the intermediate group, is the velocity of the intermediate group, is the displacement of the rear drive group, is the velocity of the rear drive group. The control input is extended to , and the input matrix is adjusted to: .

[0046] Since , the newly established model is completely controllable and can solve the underactuated characteristics existing in traditional modeling. Thus, it can be obtained that at the sampling period , the discretized train dynamics equation is:

[0047] ;

[0048] Among them, is the mass of the front drive group, is the mass of the middle drive group, is the mass of the rear drive group, is k the acceleration difference form of the front drive group at time , is the position at time T is the sampling period, is the acceleration difference form of the middle drive group at time is the acceleration difference form of the rear drive group at time is the traction braking force of the front drive group at time is the traction braking force of the rear drive group at time is k the combined resistance of the front drive group at time is k the combined resistance of the middle drive group at time is k the combined resistance of the rear drive group at time , i =1 represents the front drive group, i =2 represents the middle drive group, i =3 represents the rear drive group.

[0049] In addition, the discretized train dynamics equation can also be expressed by the following formula:

[0050] .

[0051] Step 202, according to the displacement tracking error and coupler force of the high-speed train within the set time period, perform multi-objective optimization on the control gain and sliding mode surface parameters to obtain the optimal control gain and optimal sliding mode surface parameters.

[0052] In a specific application example, the black-winged kite algorithm is used to perform multi-objective optimization on the control gain and sliding mode surface parameters to balance the speed tracking accuracy of the train and the coupler force between carriages, and achieve the multi-objective balance of tracking accuracy and suppression of coupler force. The optimization objective function of the black-winged kite algorithm is:

[0053] ;

[0054] Among them, is the objective function value, is k the first weight coefficient at time is kThe second weight coefficient at the moment, is k The third weight coefficient at the moment, is the number of moments within the set time period, is k The displacement tracking error of the i th group at the moment, is k The equivalent coupler force between groups of the i th group at the moment, is k The actual coupler force value at the moment, is the target coupler force value to be achieved. The weight coefficient dynamic adjustment rule is: , determines the decay rate of is the normalized time scale to ensure that the weight adjustment is completed within a finite time; update the search for the optimal parameter set .

[0055] Step 203, based on the optimal control gain, estimate the equivalent coupler force between groups and the combined resistance of the high-speed train in real time, and obtain the estimated value of the equivalent coupler force between groups and the estimated value of the combined resistance.

[0056] In a specific application example, the Kalman filter algorithm is used to estimate the equivalent coupler force between groups and the combined resistance of the high-speed train in real time. To solve the problem of dynamic estimation of the coupler force and combined resistance in the high-speed train dynamics equation, an adaptive extended Kalman filter algorithm is proposed to achieve accurate modeling of the dynamic compensation of the high-speed train disturbance. The acceleration of the train is estimated in real time through the Kalman filter algorithm, and based on this acceleration value, the air resistance and external disturbance are estimated, and the estimated values are fed back to the control input for feedforward compensation.

[0057] For each group, define a four-dimensional state vector (expanded state vector ) including displacement, velocity, equivalent coupler force, and combined resistance: , and obtain the discrete state equation based on the dynamic characteristics of the high-speed train as: .

[0058] Among them, is the error state transition matrix, , is the coupler force dynamic decay coefficient, reflecting the energy dissipation characteristics of the coupler buffer device, is the input matrix, , is k the control matrix at the moment, is k the process noise at the moment.

[0059] For the displacement of each group and velocity , the observation equation is: , where is the observation matrix, is the observation noise, is the observation result.

[0060] Update the state transition matrix and the observation matrix according to the dynamic equation, and iteratively output the perturbation estimation value through time update and measurement update. The state prediction and update steps of the adaptive Kalman filtering algorithm include:

[0061] (1) State prediction: ; where is the state prediction result. is k the state estimation value at time -1.

[0062] (2) Covariance prediction: ; where is the covariance prediction result, is k the state error covariance at time -1, is the process noise covariance.

[0063] (3) Kalman gain calculation: ; where is the Kalman gain prediction result, is the measurement noise covariance matrix.

[0064] (4) State correction: .

[0065] (5) Covariance correction: ; I is the identity matrix.

[0066] (6) To cope with the disturbances of the high - speed train under variable working conditions, design the dynamic update rule of the adaptive process noise covariance as: ; where is the initial process noise, is the adaptive update adjustment factor.

[0067] Step 204: Determine the non - singular fast terminal sliding mode surface based on the optimal sliding mode surface parameters and the displacement tracking error of the high - speed train.

[0068] In a specific application example, by defining a composite sliding mode surface containing a discrete cumulative term of velocity error and a non - linear power term, solve the control input to eliminate the singularity of the traditional sliding mode control and accelerate the system convergence speed. The non - singular fast terminal sliding mode surface is:

[0069] ;

[0070] Among them, is k the non-singular fast terminal sliding mode surface of the i th is k the displacement tracking error of the i th , is k the displacement of the i th is k the target displacement at is m the displacement tracking error of the i th is the sampling period, is the sliding mode surface parameter, representing the integral term coefficient of the i th and are the exponential parameters in the sliding mode surface design, used to characterize the sensitivity of the accumulation term to the error, , ensuring that when the sliding mode surface is at , the singular phenomenon is avoided.

[0071] Step 205, according to the non-singular fast terminal sliding mode surface, the estimated value of the equivalent coupler force between groups, the estimated value of the composite resistance, and the discretized dynamic equation, solve the control input in real time to control the traction and braking forces of the front drive group and the rear drive group in real time.

[0072] In a specific application example, the following formula is used to solve the control input:

[0073] ;

[0074] Among them, is k the traction and braking force of the i th is the mass of the front drive group, is the sampling period, is k the target speed at is k the differential form of the speed of the front drive group at is k the non-singular fast terminal sliding mode surface of the i th and are the control gains, , represents the proportional gain of the i th group, represents the switching gain of the i th group, which are respectively used to accelerate the convergence rate of the sliding mode surface and suppress the unmodeled disturbances and errors of the system. is the saturation function, is the boundary layer thickness, , by replacing the traditional function with the saturation function to suppress high-frequency chattering. is k the estimated value of the equivalent coupler force between groups of the i th group at time is k the estimated value of the composite resistance of the i th group at time

[0075] In addition, to verify the global stability of this application, a composite energy function including the sliding mode surface error, coupler force deviation, and disturbance estimation error is constructed based on the discrete Lyapunov function theory, and the stability constraint conditions are derived to ensure the convergence and robustness under the optimal control law and disturbance compensation.

[0076] For the front drive group , the middle group , and the rear drive group , the global energy function is defined as:

[0077] ;

[0078] where is the global energy value, and the sliding mode surface energy term characterizes the dynamic convergence of the tracking error. is the state estimation error energy term, is k the state estimation error at time , is a positive definite matrix used to quantify the estimation deviations of displacement, velocity, coupler force, and resistance. is the coupler force tracking error term, .

[0079] The stability condition is: ; is the difference between the global energy values at time k +1 and k time, is a scalar, is a positive scalar used to adjust the weight of the state estimation error term in the Lyapunov stability analysis.

[0080] According to the global asymptotic stability condition of the Lyapunov function, if there exists a symmetric positive definite matrix and a scalar , the matrix inequality needs to be satisfied; where is the sliding mode coupling term.

[0081] The difference calculation formula of the energy function is: .

[0082] Where is the difference between the nonsingular fast terminal sliding mode surfaces at the k +1 moment and the k moment.

[0083] According to the formula of the nonsingular fast terminal sliding mode surface in step 204, we can get: , substituting it into the above difference equation and amplifying, we get: .

[0084] According to the adaptive covariance update rule in step 203, ensure that .

[0085] Combining the optimal control gain and the optimal sliding mode surface parameters in step 202, we can get: ;

[0086] That is, when and , , global asymptotic stability can be achieved.

[0087] In this application, aiming at the problems of uneven coupler force distribution, underactuated characteristics and disturbance sensitivity existing in existing high-speed EMUs, a discretized train dynamics equation is constructed to characterize the dynamic constraints of the coupler force; a distributed nonsingular fast terminal sliding mode control law is designed to eliminate the singularity of traditional sliding mode control and accelerate the convergence speed; the Kalman filter algorithm is used to estimate and compensate the influence of air resistance and track disturbance in real time; the black-winged kite algorithm is used to optimize the sliding mode parameters to balance the tracking accuracy of the train and the coupler force of the carriages; a composite energy function is constructed based on the Lyapunov function theory to prove the global stability. Therefore, the present invention can effectively enhance the robustness of high-speed trains under complex disturbances and is applicable to the cooperative control scenario of multiple power units. By designing a deep fusion of adaptive Kalman filtering and intelligent optimization algorithms, the problems of coupler force imbalance, disturbance sensitivity and insufficient control accuracy under the underactuated characteristics of high-speed trains are solved, the robustness of high-speed trains under complex disturbances is effectively enhanced, and the safety of the coupler force, control accuracy and anti-disturbance ability of high-speed trains are improved.

[0088] Such as Figure 5As shown, this application addresses four key issues in high-speed trains: ① An accurate control model needs to be built to meet the requirements of control and monitoring; ② A safety control algorithm suitable for the high-speed train control system needs to be designed; ③ The coupler force of high-speed EMUs needs to be effectively monitored; ④ External disturbances need to be compensated to improve control quality. Solutions are proposed as follows: ① Study the discretized dynamic equation; ② Study the fast terminal sliding mode control law; ③ Study the Kalman filter algorithm to reconstruct the train coupler force; ④ Study the black-winged kite algorithm to optimize the sliding mode parameter strategy. Based on the established model, the non-singular fast terminal sliding mode control method in the discrete domain and the extended Kalman compensation model are eliminated, and a high-speed train safety control strategy is designed. Further, to verify the feasibility of this application, the stability of the constructed energy function is analyzed based on the Lyapunov function theory, and simulation processing is carried out using matlab software to obtain experimental results.

[0089] The following provides a simulation process.

[0090] (1) Simulation model construction: Based on the Simulink environment, build a discretized dynamic equation, with the input being the control force , and the output being the displacements of each group, the speeds , and the equivalent coupler force between groups . The relevant parameters are dynamically loaded through matlab scripts.

[0091] (2) Control algorithm deployment: Implement the design of the control law using the MATLAB Function Block, with the inputs , , and the output , and update , online. Implement the state prediction and update of the Kalman filter algorithm through the Stateflow module, with the inputs and , and the outputs and .

[0092] (3) Optimization and verification: Call the MATLAB global optimization toolbox, and according to the established objective function, iteratively optimize the sliding mode parameter set , with the termination condition being , the relative change rate , automatically calculate through the script, and verify the Lyapunov stability.

[0093] Based on the same inventive concept, an embodiment of the present application further provides a multi-particle cooperative control system for a high-speed train for implementing the multi-particle cooperative control method of the high-speed train involved above. The implementation solution provided by this system for solving problems is similar to the implementation solution recorded in the above method. Therefore, the specific limitations in one or more embodiments of the multi-particle cooperative control system for a high-speed train provided below can refer to the limitations on the multi-particle cooperative control method of the high-speed train in the above text, and will not be repeated here.

[0094] In an exemplary embodiment, as Figure 6 shown, a multi-particle cooperative control system for a high-speed train is provided, including: a dynamic equation construction module 601, a parameter optimization module 602, a data estimation module 603, a sliding mode surface determination module 604, and a control module 605.

[0095] The dynamic equation construction module 601 is used to divide the carriages of the high-speed train into multiple groups and construct a discretized dynamic equation of the high-speed train. Among them, the multiple groups are respectively a front drive group, an intermediate group, and a rear drive group. The state vector of the discretized dynamic equation includes the displacement and velocity of each group. The control input of the discretized dynamic equation includes the traction braking force of the front drive group and the traction braking force of the rear drive group.

[0096] The parameter optimization module 602 is used to perform multi-objective optimization on the control gain and the sliding mode surface parameters according to the displacement tracking error and the coupler force of the high-speed train within a set time period, and obtain the optimal control gain and the optimal sliding mode surface parameters.

[0097] The data estimation module 603 is used to estimate the equivalent coupler force between groups and the composite resistance of the high-speed train in real time based on the optimal control gain, and obtain the estimated value of the equivalent coupler force between groups and the estimated value of the composite resistance.

[0098] The sliding mode surface determination module 604 is used to determine a non-singular fast terminal sliding mode surface based on the optimal sliding mode surface parameters and the displacement tracking error of the high-speed train.

[0099] The control module 605 is used to solve the control input in real time according to the non-singular fast terminal sliding mode surface, the estimated value of the equivalent coupler force between groups, the estimated value of the composite resistance, and the discretized dynamic equation, so as to control the traction braking force of the front drive group and the traction braking force of the rear drive group in real time.

[0100] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0101] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which, when executed by a processor, implements the steps in the above method embodiments.

[0102] In an exemplary embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in the above method embodiments.

[0103] 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 for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0104] In this application, all actions of obtaining signals, information, or data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the device is located and obtaining authorization from the owner of the corresponding device.

[0105] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing 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 method embodiments. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. 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), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0106] In each of the embodiments provided in this application, the database involved may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., without limitation. In each of the embodiments provided in this application, the processor may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without limitation.

[0107] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope described in this specification.

[0108] Specific examples are used in this article to elaborate on the principles and implementation manners of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A multi-particle collaborative control method for high-speed trains, characterized in that, Including: Dividing the carriages of a high-speed train into multiple groups, and constructing a discretized dynamic equation of the high-speed train; the multiple groups are respectively a front drive group, an intermediate group, and a rear drive group; the state vector of the discretized dynamic equation includes the displacement and velocity of each group; the control inputs of the discretized dynamic equation include the traction braking force of the front drive group and the traction braking force of the rear drive group; Performing multi-objective optimization on the control gain and sliding mode surface parameters according to the displacement tracking error and coupler force of the high-speed train within a set time period, to obtain the optimal control gain and the optimal sliding mode surface parameters; Based on the optimal control gain, estimating the equivalent coupler force and composite resistance between groups of the high-speed train in real time, to obtain the estimated value of the equivalent coupler force between groups and the estimated value of the composite resistance; Determining a non-singular fast terminal sliding mode surface based on the optimal sliding mode surface parameters and the displacement tracking error of the high-speed train: ； Among them, is k the non-singular fast terminal sliding mode surface of the i th group at time is k the displacement tracking error of the i th group at time is m the displacement tracking error of the i th group at time is the sampling period, is the sliding mode surface parameter, representing the integral term coefficient of the i th group, and are the exponential parameters in the sliding mode surface design, used to characterize the sensitivity of the accumulation term to the error, , i =1 represents the precursor group, i =2 represents the intermediate group, i =3 represents the successor group; According to the non-singular fast terminal sliding mode surface, the estimated value of the equivalent coupler force between groups, the estimated value of the composite resistance, and the discretized dynamic equation, solving the control input in real time to control the traction braking force of the front drive group and the traction braking force of the rear drive group in real time.

2. The multi-particle collaborative control method for high-speed trains according to claim 1, wherein The discretized dynamic equation is: ； Wherein, is the mass of the front set, is the mass of the middle set, is the mass of the rear set, is k the acceleration difference form of the front set at time , is the position at time T is the sampling period, is the acceleration difference form of the middle set at time is the acceleration difference form of the rear set at time is the traction braking force of the front set at time is the traction braking force of the rear set at time is the inter-vehicle coupling force between the front set and the middle set at time , d is the coupler stiffness coefficient, is the damping coefficient, is k the displacement of the front set at time is k the displacement of the middle set at time is k the velocity difference form of the front set at time is k the velocity difference form of the middle set at time is k the inter-vehicle coupling force between the middle set and the rear set at time , is the velocity difference form of the rear set, c is the basic resistance coefficient, is k the combined resistance of the front set at time is k the combined resistance of the middle set at time is k the combined resistance of the rear set at time.

3. The multi-particle collaborative control method for high-speed trains according to claim 1, wherein Performing multi-objective optimization on the control gain and sliding mode surface parameters according to the displacement tracking error and coupler force of the high-speed train within a set time period, to obtain the optimal control gain and the optimal sliding mode surface parameters, specifically including: Performing multi-objective optimization on the control gain and sliding mode surface parameters according to the displacement tracking error and coupler force of the high-speed train within a set time period by using the black-winged kite algorithm, to obtain the optimal control gain and the optimal sliding mode surface parameters.

4. The multi-particle collaborative control method for high-speed trains according to claim 3, characterized in that The optimization objective function of the black-winged kite algorithm is: ； Among them, is the objective function value, is k the first weight coefficient at time is k the second weight coefficient at time is k the third weight coefficient at time is the number of time points within the set time period, is k the displacement tracking error of the i th group at time is k the equivalent coupler force between groups of the i th group at time is k the actual coupler force value at time is the target coupler force value to be achieved, i = 1 indicates the front drive group, i = 2 indicates the middle group, i = 3 indicates the rear drive group.

5. The multi-particle collaborative control method for high-speed trains according to claim 1, characterized in that Based on the optimal control gain, estimating the equivalent coupler force and composite resistance between groups of the high-speed train in real time, to obtain the estimated value of the equivalent coupler force between groups and the estimated value of the composite resistance, specifically including: Based on the optimal control gain, using the Kalman filter algorithm to estimate the equivalent coupler force and composite resistance between groups of the high-speed train in real time, to obtain the estimated value of the equivalent coupler force between groups and the estimated value of the composite resistance.

6. The multi-particle collaborative control method for high-speed trains according to claim 1, characterized in that Solving the control input by using the following formula: ； Among them, is k the tractive braking force of the i th group at time is the mass of the front-wheel drive group, is the sampling period, is k the target speed at time is k the velocity difference form of the front-wheel drive group at time is k the non-singular fast terminal sliding mode surface of the i th group at time and are the control gains, represents the proportional gain of the i th group, represents the switching gain of the i th group, is the boundary layer thickness, is k the estimated value of the equivalent coupler force between groups of the i th group at time is k the estimated value of the combined resistance of the i th group at time i = 1 represents the front-wheel drive group, i = 2 represents the middle group, i = 3 represents the rear-wheel drive group.

7. A multi-particle collaborative control system for high-speed trains, applied to the multi-particle collaborative control method for high-speed trains described in any one of claims 1-6, characterized in that, The multi-particle collaborative control system of the high-speed train includes: A dynamic equation construction module, configured to divide the carriages of a high-speed train into multiple groups, and construct a discretized dynamic equation of the high-speed train; wherein, the multiple groups are respectively a front drive group, an intermediate group, and a rear drive group; the state vector of the discretized dynamic equation includes the displacement and velocity of each group; the control inputs of the discretized dynamic equation include the traction braking force of the front drive group and the traction braking force of the rear drive group; A parameter optimization module, configured to perform multi-objective optimization on the control gain and sliding mode surface parameters according to the displacement tracking error and coupler force of the high-speed train within a set time period, to obtain the optimal control gain and the optimal sliding mode surface parameters; A data estimation module, configured to estimate the equivalent coupler force and composite resistance between groups of the high-speed train in real time based on the optimal control gain, to obtain the estimated value of the equivalent coupler force between groups and the estimated value of the composite resistance; A sliding mode surface determination module, configured to determine a non-singular fast terminal sliding mode surface based on the optimal sliding mode surface parameters and the displacement tracking error of the high-speed train; A control module, configured to solve for a control input in real time according to the nonsingular fast terminal sliding mode surface, the estimated value of the equivalent coupler force between groups, the estimated value of the composite resistance, and the discretized dynamic equation, so as to control the traction and braking forces of the front-wheel group and the traction and braking forces of the rear-wheel group in real time.

8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the multi-particle collaborative control method for high-speed trains according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the multi-particle collaborative control method for high-speed trains according to any one of claims 1-6.

Images