Train control method, device and equipment and storage medium

Abstract

The invention discloses a train control method, device and equipment and a storage medium. The method comprises the following steps: performing linearization processing on a nonlinear model corresponding to a target high-speed train group to obtain a target dynamic model; performing parameter identification on a linear part and an unmodeled dynamic part in the target kinetic model by adopting different parameter identification methods to obtain a linear identification error; and performing feedback control on the target high-speed train group according to the linear identification error and the target kinetic model. According to the technical scheme, different parameter identification methods can be adopted to identify the dynamical model of the train, so that the target high-speed train group is accurately tracked and controlled according to the identification error and the dynamical model.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicles, and in particular, to a train control method, device, equipment, and storage medium. Background Art

[0002] The train operation control system is one of the key technologies to ensure the safe and punctual operation of trains. With the continuous improvement of requirements such as passenger comfort, the performance requirements for the train operation control system are also getting higher and higher. However, due to the influence of extreme weather during the operation of high-speed trains, as well as the influence of ramp resistance and some non-linear parameters during the operation of high-speed trains, the difficulty of modeling and analyzing high-speed trains and accurately controlling trains is further increased.

[0003] Therefore, how to use different parameter identification methods to identify the dynamic model of trains, and thus perform precise tracking control on the target high-speed train group according to the identification error and the dynamic model, is an urgent problem to be solved at present. Summary of the Invention

[0004] The present invention provides a train control method, device, equipment, and storage medium to perform precise tracking control on a target high-speed train group.

[0005] According to one aspect of the present invention, there is provided a train control method, including:

[0006] Linearize the non-linear model corresponding to the target high-speed train group to obtain a target dynamic model;

[0007] Respectively use different parameter identification methods to identify the parameters of the linear part and the unmodeled dynamic part in the target dynamic model to obtain a linear identification error;

[0008] Perform feedback control on the target high-speed train group according to the linear identification error and the target dynamic model.

[0009] Optionally, linearizing the non-linear model corresponding to the target high-speed train group to obtain a target dynamic model includes:

[0010] Determine the non-linear controlled objects corresponding to each high-speed train in the target high-speed train group, and establish a non-linear model corresponding to the target high-speed train group according to the non-linear controlled objects;

[0011] Perform Taylor expansion on the non-linear model, and obtain the target dynamic model by equivalently transforming the expanded non-linear model into a controlled autoregressive model.

[0012] Optionally, respectively using different parameter identification methods to identify the parameters of the linear part and the unmodeled dynamic part in the target dynamic model to obtain a linear identification error includes:

[0013] Using the first parameter identification method, identify the parameters of the linear part in the target dynamic model to obtain the predicted train speed;

[0014] Determine the target train speed, and use the second parameter identification method to identify the parameters of the unmodeled dynamic part in the target dynamic model to obtain the unmodeled dynamic parameters;

[0015] According to the predicted train speed, the target train speed, and the unmodeled dynamic parameters, obtain the linear identification error.

[0016] Optionally, determining the target train speed includes:

[0017] Obtain the target train traction force of the target high-speed train group at the current moment;

[0018] Take the target train traction force as the input of the train operation control system corresponding to the target high-speed train group, determine the output of the train operation control system, and determine the target train speed according to the output result.

[0019] Optionally, the first parameter identification method is the recursive least squares method with a forgetting factor; the second parameter identification method is the identification method based on the radial basis function network.

[0020] Optionally, obtaining the linear identification error according to the predicted train speed, the target train speed, and the unmodeled dynamic parameters includes:

[0021] Determine the speed deviation between the predicted train speed and the target train speed;

[0022] According to the difference between the speed deviation and the unmodeled dynamic parameters, determine the linear identification error.

[0023] Optionally, performing feedback control on the target high-speed train group according to the linear identification error and the target dynamic model includes:

[0024] According to the linear identification error, return to perform the parameter identification process of the linear part of the target dynamic model to determine the first identification result;

[0025] According to the first identification result, combined with the second parameter identification result of the unmodeled dynamic part in the target dynamic model, re-perform the determination process of the linear identification error to realize the feedback control of the target high-speed train group.

[0026] According to another aspect of the present invention, there is provided a train control device, including:

[0027] A model obtaining module, configured to linearize the nonlinear model corresponding to the target high-speed train group to obtain a target dynamic model;

[0028] An error acquisition module, configured to respectively use different parameter identification methods to identify the parameters of the linear part and the unmodeled dynamic part in the target dynamic model, so as to obtain a linear identification error;

[0029] A control module, configured to perform feedback control on the target high-speed train group according to the linear identification error and the target dynamic model.

[0030] According to another aspect of the present invention, there is provided an electronic device, where the electronic device includes:

[0031] At least one processor; and

[0032] A memory communicatively connected to the at least one processor; wherein,

[0033] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the train control method according to any embodiment of the present invention.

[0034] According to another aspect of the present invention, there is provided a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the train control method according to any embodiment of the present invention is implemented.

[0035] The technical solution of the embodiment of the present invention linearizes the non-linear model corresponding to the target high-speed train group to obtain a target dynamic model; respectively uses different parameter identification methods to identify the parameters of the linear part and the unmodeled dynamic part in the target dynamic model to obtain a linear identification error; and performs feedback control on the target high-speed train group according to the linear identification error and the target dynamic model. By using different parameter identification methods to identify the dynamic model of the train, accurate tracking control can be performed on the target high-speed train group according to the identification error and the dynamic model, reducing the blindness of the crew's operation based on experience.

[0036] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0038] Figure 1A It is a flowchart of a train control method provided in the first embodiment of the present invention;

[0039] Figure 1B It is a schematic flowchart for determining the linear identification error provided in the first embodiment of the present invention;

[0040] Figure 2 It is a flowchart of a train control method provided in the second embodiment of the present invention;

[0041] Figure 3 It is a structural block diagram of a train control device provided in the third embodiment of the present invention;

[0042] Figure 4 It is a schematic structural diagram of an electronic device provided in the fourth embodiment of the present invention. Detailed implementation manners

[0043] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0044] It should be noted that the terms "first", "second", "target", "candidate", "alternate", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0045] Embodiment 1

[0046] Figure 1A It is a flowchart of a train control method provided in the first embodiment of the present invention; Figure 1BFIG. 0 is a schematic flowchart for determining linear identification error provided by Embodiment 1 of the present invention. This embodiment is applicable to identifying the dynamic model of a train using different parameter identification methods, so as to accurately track and control a target high-speed train group according to the identification error and the dynamic model. This method can be executed by a train control device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device, such as a train operation control system corresponding to a high-speed train group. As Figure 1A shown, the train control method includes:

[0047] S101. Linearize the non-linear model corresponding to the target high-speed train group to obtain a target dynamic model.

[0048] Among them, the target high-speed train group refers to a train group composed of at least two high-speed trains. Each high-speed train has an input and an output, the input is the traction force, and the output is the speed. The non-linear model refers to a model that describes the target high-speed train group by representing different high-speed trains in the target high-speed train group as non-linear controlled objects respectively. The target dynamic model refers to a model that can accurately describe the train operation process, and specifically can be a set of linear equations.

[0049] Optionally, linearizing the non-linear model corresponding to the target high-speed train group to obtain a target dynamic model includes: determining the non-linear controlled objects corresponding to each high-speed train in the target high-speed train group, and establishing a non-linear model corresponding to the target high-speed train group according to the non-linear controlled objects; performing Taylor expansion on the non-linear model, and obtaining the target dynamic model by equivalently transforming the expanded non-linear model into a controlled autoregressive model.

[0050] Among them, the non-linear controlled objects correspond one-to-one with each high-speed train in the target high-speed train group. The non-linear controlled objects are often difficult to describe with an accurate mathematical model, so they need to be transformed into an equivalent model. Specifically, the corresponding non-linear controlled objects can be generated according to the dynamic characteristics of different high-speed trains in the target high-speed train group.

[0051] Exemplarily, the non-linear models corresponding to each high-speed train in the target high-speed train group can be expressed by the following formula:

[0052] y(k) = f[y(k - 1)…y(k - n A )u(k - 1)…u(k - 1 - n B )]

[0053] Among them, u(k) and y(k) are the input and output of each controlled object respectively; n A and n B are preset model orders; f(·) ∈ R is an unknown non-linear function.

[0054] Optionally, the non-linear model can be Taylor-expanded around the operating point, and the coefficients are:

[0055]

[0056] where u(k) and y(k) are the inputs and outputs of each controlled object respectively; n A and n B are the preset model orders; ai and bj are the Taylor coefficients.

[0057] Furthermore, by making:

[0058]

[0059] the non-linear model can be equivalent to where is the unmodeled dynamics.

[0060] Furthermore, by regarding the equivalent non-linear model as a controlled auto-regressive model (CARM), it can be rewritten as:

[0061]

[0062] where: y(k + 1) is the speed at the next moment. is the linear part, is the data vector, θ is the parameter vector to be estimated, is the unmodeled dynamics. n A and n B are the preset model orders; represents the parameter part of the dynamic model, and the parameter part specifically includes the linear part parameters and the unmodeled dynamics part. u(k) refers to the traction force at the k-th moment.

[0063] S102. Respectively adopt different parameter identification methods to identify the parameters of the linear part and the unmodeled dynamics part in the target dynamic model, so as to obtain the linear identification error.

[0064] Among them, the parameter identification method refers to the method of identifying the parameters in the dynamic model. The linear identification error refers to the deviation between the identification results of the linear part and the unmodeled dynamics part in the target dynamic model.

[0065] Optionally, different parameter identification methods are respectively used to identify the parameters of the linear part and the unmodeled dynamic part in the target dynamic model to obtain a linear identification error, including: using a first parameter identification method to identify the parameters of the linear part in the target dynamic model to obtain a predicted train speed; determining a target train speed, and using a second parameter identification method to identify the parameters of the unmodeled dynamic part in the target dynamic model to obtain unmodeled dynamic parameters; obtaining a linear identification error according to the predicted train speed, the target train speed, and the unmodeled dynamic parameters.

[0066] Among them, the first parameter identification method is the Forgetting Factor Recursive Least Square (FFRLS); the second parameter identification method is an identification method based on a Radial Basis Function Network (RBFNN). The predicted train speed refers to the train speed identified by using the first parameter identification method, and the target train speed refers to the train speed actually output by the train operation control system. The unmodeled dynamic parameters refer to the parameters identified by using the second parameter identification method.

[0067] Optionally, the Forgetting Factor Recursive Least Square (FFRLS) can be used to identify the parameters of the linear part in the target dynamic model and determine the predicted train speed according to the identification result.

[0068] It should be noted that the dynamic model of a high-speed train can describe the train operation process more accurately. However, due to considering the existence of the coupler buffer system, line road conditions information, and external unknown disturbances, the nonlinearity and complexity of the entire system will increase. The present invention proposes an adaptive RBFNN control strategy based on ideal feedback control, which replaces the adjustment of the neural network weight value by designing a control law for parameters, so as to accelerate the learning speed of the RBFNN, reduce the calculation amount, and obtain accurate unmodeled dynamic parameters.

[0069] It should be noted that the structure of the RBFNN usually has three layers, namely the input layer, the hidden layer, and the output layer. The neuron activation function of the hidden layer is composed of radial basis functions. The array operation unit composed of the hidden layer is called a hidden layer node. Each hidden layer node contains a center vector κ, κ and the input parameter vector z have the same dimension, and the Euclidean distance between the two can be defined as ||z - κ j ||.

[0070] The output of the hidden layer in the neural network is obtained by the non-linear activation function h j (z):

[0071]

[0072] In the formula, β j is a positive scalar representing the width of the Gaussian basis function; m represents the number of hidden layer nodes. The output of the network is solved by the weighted function given by the following formula:

[0073]

[0074] In the formula, w represents the weight value of the network output layer; n represents the number of network output nodes; y represents the output of the neural network. The multi-particle longitudinal dynamics model of high-speed trains can describe the train operation process more accurately. However, due to the consideration of the coupler buffer system, line condition information, and the existence of external unknown disturbances, the nonlinearity and complexity of the entire system will increase. Therefore, the adjustment of the neural network weight value can be replaced by designing the control rate of parameters to accelerate the learning speed of the RBFNN and reduce the calculation amount.

[0075] Exemplarily, the system identification process of the RBF neural network system can include: 1. Input the initial data of the system and set the initial values of the RBF network parameters b j (0), c ji (0), ω j (0) and parameters such as the number m of hidden layer neurons, learning rate η, and momentum factor α. 2. Sample the actual system output y(k), and calculate the network parameter increment Δy m (k) between the current network output y m (k) and the actual system output according to the formula: Δy m (k) = y

[0076] (k) - y(k); 3. Adjust the RBF network structure according to the network parameter increment until the operation of the target high-speed train group ends.

[0077] Exemplarily, the train operation control system can output the target train speed based on the following formula according to the target train traction:

[0078] y(k) = -a 1 y(k - 1 - τ) + b 0 u(k - 1)

[0079] where y(k) represents the train speed at time k, y(k - 1 - τ) represents the train speed at time k - 1 - τ, τ represents the time delay constant, u(k - 1) represents the train traction at time k - 1, and a 1denotes the first parameter, b 0 denotes the second parameter. The first parameter and the second parameter can be identified by the least squares parameter identification method.

[0080] Optionally, according to the predicted train speed, the target train speed, and the unmodeled dynamic parameters, a linear identification error is obtained, including: determining the speed deviation between the predicted train speed and the target train speed; determining the linear identification error according to the difference between the speed deviation and the unmodeled dynamic parameters.

[0081] Exemplarily, see Figure 1B , the traction force of the target train can be represented by u(k), and the output of the train operation control system can be represented by y(k + 1). denotes the parameter part of the dynamic model. The parameter part specifically includes the linear part parameters and the unmodeled dynamic part. The in the linear part can be subjected to parameter identification by the recursive least squares method with a forgetting factor, and the in the unmodeled dynamic part can be subjected to parameter identification by RBFNN. denotes the input after parameter identification by the FFRLS recursive least squares method. denotes the result obtained after RBFNN nonlinear identification. denotes the predicted train speed and the speed deviation between the output y(k + 1) of the train operation control system.

[0082] Specifically, the process of obtaining the identification result after parameter identification by the FFRLS recursive least squares method can be expressed by the following formula:

[0083]

[0084] where the parameter vector can be recursively obtained by the following formula:

[0085]

[0086] where: the forgetting factor λ must be selected as a positive number close to 1, usually not less than 0.9; is the estimated value of the parameter vector; K(k) is the weighted matrix of the prediction error and is the correction coefficient; P(k) is an invertible covariance matrix; I is the identity matrix of the same dimension as P; P(0), are the initial values of the parameters. It can be deduced that:

[0087]

[0088] Among them, ε(k) is the linear identification error.

[0089] S103. Perform feedback control on the target high-speed train group according to the linear identification error and the target dynamic model.

[0090] Optionally, performing feedback control on the target high-speed train group according to the linear identification error and the target dynamic model includes: according to the linear identification error, returning to perform the parameter identification process of the linear part of the target dynamic model to determine the first identification result; according to the first identification result, combining the second parameter identification result of the unmodeled dynamic part in the target dynamic model, re-performing the determination process of the linear identification error to achieve the feedback control of the target high-speed train group.

[0091] The technical solution of the embodiment of the present invention linearizes the nonlinear model corresponding to the target high-speed train group to obtain the target dynamic model; respectively uses different parameter identification methods to identify the parameters of the linear part and the unmodeled dynamic part in the target dynamic model to obtain the linear identification error; performs feedback control on the target high-speed train group according to the linear identification error and the target dynamic model. By using different parameter identification methods to identify the dynamic model of the train, accurate tracking control of the target high-speed train group can be performed according to the identification error and the dynamic model, reducing the blindness of the crew's operation based on experience.

[0092] Embodiment 2

[0093] Figure 2 It is a flowchart of a train control method provided by the second embodiment of the present invention; on the basis of the above embodiment, this embodiment provides a preferred example of train control. The method includes the following processes:

[0094] S201. Determine the nonlinear controlled objects corresponding to each high-speed train in the target high-speed train group, and establish a nonlinear model corresponding to the target high-speed train group according to the nonlinear controlled objects.

[0095] S202. Perform Taylor expansion on the nonlinear model, and obtain the target dynamic model by equivalently transforming the expanded nonlinear model into a controlled autoregressive model.

[0096] S203. Use the first parameter identification method to identify the parameters of the linear part in the target dynamic model to obtain the predicted train speed.

[0097] S204. Obtain the target train traction force of the target high-speed train group at the current moment.

[0098] S205. Use the traction force of the target train as the input to the train operation control system corresponding to the target high-speed train set, determine the output of the train operation control system, and determine the target train speed according to the output result.

[0099] S206. Adopt the second parameter identification method to identify the parameters of the unmodeled dynamic part in the target dynamic model to obtain the unmodeled dynamic parameters.

[0100] S207. Obtain the linear identification error according to the predicted train speed, the target train speed, and the unmodeled dynamic parameters.

[0101] S208. According to the linear identification error, return to execute the parameter identification process of the linear part of the target dynamic model to determine the first identification result.

[0102] S209. According to the first identification result, combined with the second parameter identification result of the unmodeled dynamic part in the target dynamic model, re-perform the determination process of the linear identification error to realize the feedback control of the target high-speed train set.

[0103] The technical solution of the present invention can improve the accurate tracking control ability of the train speed and reduce the blindness of the crew's operation based on experience by using the RBF neural network combined with the least squares method to predict and control the speed output by the vehicle operation model. Specifically, for the complex and changeable operation process of high-speed trains, the parameters change with non-linear time-varying characteristics, and the traditional adaptive control method is difficult to solve the problems of traction equipment speed tracking and control level adjustment in complex situations. The present invention discloses an adaptive control scheme for high-speed train traction equipment, which can improve the accurate tracking control ability of the train speed and reduce the blindness of the crew's operation based on experience. Specifically, the present invention first uses the recursive least squares method with a forgetting factor to identify the unknown parameters of the low-order part of the high-speed train; secondly, uses the RBF neural network to estimate the high-order non-linear term (unmodeled dynamic) part of the high-speed train; finally, combines the least squares method and the RBF neural network to give an implementable way to perform feedback control on the target high-speed train set based on the dynamic model, which not only reduces the labor intensity of the driver but also realizes the safe and stable operation of the high-speed train and improves the accuracy of speed tracking control.

[0104] Embodiment III

[0105] Figure 3It is a structural block diagram of a train control device provided in Embodiment 3 of the present invention; this embodiment is applicable to the situation where different parameter identification methods are used to identify the dynamic model of a train, so that precise tracking control can be performed on a target high-speed train group according to the identification error and the dynamic model. The train control device provided in the embodiments of the present invention can execute the train control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method; the train control device can be implemented in the form of hardware and / or software and is configured in a device with train control functions, such as the train operation control system corresponding to a high-speed train group. As Figure 3 shown, the train control device specifically includes:

[0106] A model obtaining module 301, configured to linearize the nonlinear model corresponding to the target high-speed train group to obtain a target dynamic model;

[0107] An error obtaining module 302, configured to respectively use different parameter identification methods to identify the parameters of the linear part and the unmodeled dynamic part in the target dynamic model to obtain a linear identification error;

[0108] A control module 303, configured to perform feedback control on the target high-speed train group according to the linear identification error and the target dynamic model.

[0109] The technical solution of the embodiment of the present invention linearizes the nonlinear model corresponding to the target high-speed train group to obtain a target dynamic model; respectively uses different parameter identification methods to identify the parameters of the linear part and the unmodeled dynamic part in the target dynamic model to obtain a linear identification error; and performs feedback control on the target high-speed train group according to the linear identification error and the target dynamic model. By using different parameter identification methods to identify the dynamic model of the train, precise tracking control can be performed on the target high-speed train group according to the identification error and the dynamic model, reducing the blindness of the crew's operation based on experience.

[0110] Further, the model obtaining module 301 is specifically configured to:

[0111] Determine the nonlinear controlled objects corresponding to each high-speed train in the target high-speed train group, and establish a nonlinear model corresponding to the target high-speed train group according to the nonlinear controlled objects;

[0112] Perform Taylor expansion on the nonlinear model, and obtain the target dynamic model by equivalently transforming the expanded nonlinear model into a controlled autoregressive model.

[0113] Further, the error obtaining module 302 may include:

[0114] An identification unit, which is used to identify the parameters of the linear part in the target dynamic model by using the first parameter identification method to obtain the predicted train speed;

[0115] A parameter obtaining unit, which is used to determine the target train speed and identify the parameters of the unmodeled dynamic part in the target dynamic model by using the second parameter identification method to obtain the unmodeled dynamic parameters;

[0116] An error obtaining unit, which is used to obtain the linear identification error according to the predicted train speed, the target train speed and the unmodeled dynamic parameters.

[0117] Further, the parameter obtaining unit is specifically used for:

[0118] Obtain the target train traction force of the target high-speed train group at the current moment;

[0119] Take the target train traction force as the input of the train operation control system corresponding to the target high-speed train group, determine the output of the train operation control system, and determine the target train speed according to the output result.

[0120] Further, the first parameter identification method is the recursive least squares method with a forgetting factor; the second parameter identification method is the identification method based on the radial basis function network.

[0121] Further, the error obtaining unit is specifically used for:

[0122] Determine the speed deviation between the predicted train speed and the target train speed;

[0123] Determine the linear identification error according to the difference between the speed deviation and the unmodeled dynamic parameters.

[0124] Further, the control module 303 is specifically used for:

[0125] According to the linear identification error, return to execute the parameter identification process of the linear part of the target dynamic model to determine the first identification result;

[0126] According to the first identification result, combined with the second parameter identification result of the unmodeled dynamic part in the target dynamic model, re-determine the linear identification error to realize the feedback control of the target high-speed train group.

[0127] Embodiment 4

[0128] Figure 4 It is a schematic structural diagram of the electronic device provided in Embodiment 4 of the present invention. Figure 4The structural schematic diagram of an electronic device 10 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0129] As Figure 4 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0130] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0131] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the train control method.

[0132] In some embodiments, the train control method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the train control method described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the train control method by any other suitable means (e.g., by means of firmware).

[0133] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems-on-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0135] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0136] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0137] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0138] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0139] It should be understood that various forms of processes shown above can be used, steps can be reordered, added or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0140] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A train control method, characterized in that: include: The nonlinear model corresponding to the target high-speed train set is linearized to obtain the target dynamic model; Different parameter identification methods are used to identify the parameters of the linear part and the unmodeled dynamic part in the target dynamic model to obtain the linear identification error; Feedback control is performed on the target high-speed train set based on the linear identification error and the target dynamics model.

2. The method according to claim 1, characterized in that: The nonlinear model corresponding to the target high-speed train set is linearized to obtain the target dynamic model, including: Determine the nonlinear controlled object corresponding to each high-speed train in the target high-speed train group, and establish a nonlinear model corresponding to the target high-speed train group according to the nonlinear controlled object; The nonlinear model is Taylor expanded, and the target dynamics model is obtained by converting the expanded nonlinear model into a controlled autoregressive model.

3. The method according to claim 1, characterized in that Different parameter identification methods are used to identify the linear part and the unmodeled dynamic part in the target dynamic model to obtain the linear identification error, including: Using the first parameter identification method, the linear part of the target dynamics model is identified to obtain the predicted train speed; Determine the target train speed, and use the second parameter identification method to perform parameter identification on the unmodeled dynamic part of the target dynamic model to obtain the unmodeled dynamic parameters; The linear identification error is obtained based on the predicted train speed, the target train speed and the unmodeled dynamic parameters.

4. The method according to claim 3, characterized in that Determine the target train speed, including: Obtaining the target train traction of the target high-speed train group at the current moment; The target train traction force is used as the input of the train operation control system corresponding to the target high-speed train group, the output of the train operation control system is determined, and the target train speed is determined according to the output result.

5. The method according to claim 3, characterized in that: in, The first parameter identification method is the recursive least square method with a forgetting factor; the second parameter identification method is an identification method based on a radial basis function network.

6. The method according to claim 3, characterized in that According to the predicted train speed, target train speed and unmodeled dynamic parameters, the linear identification error is obtained, including: determining a speed deviation between a predicted train speed and a target train speed; The linear identification error is determined from the difference between the velocity deviation and the unmodeled dynamic parameters.

7. The method according to claim 1, characterized in that Based on the linear identification error and the target dynamics model, feedback control is performed on the target high-speed train set, including: According to the linear identification error, returning to execute the parameter identification process of the linear part of the target dynamics model to determine the first identification result; According to the first identification result, combined with the second parameter identification result of the unmodeled dynamic part in the target dynamic model, the linear identification error determination process is re-performed to achieve feedback control of the target high-speed train set.

8. A train control device, characterized in that: include: A model acquisition module is used to linearize the nonlinear model corresponding to the target high-speed train set to obtain a target dynamic model; The error obtaining module is used to respectively use different parameter identification methods to perform parameter identification on the linear part and the unmodeled dynamic part in the target dynamic model to obtain a linear identification error; The control module is used to perform feedback control on the target high-speed train group according to the linear identification error and the target dynamic model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the train control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the train control method according to any one of claims 1 to 7 when executed.

Images