A speed control method for urban rail transit trains based on intelligent VRFT

Abstract

The present invention relates to a method for controlling the speed of an urban rail transit train based on intelligent VRFT, the method comprising the following steps: step S101, collecting a set of input and output data of the urban rail transit train speed control system; step S102, initializing the parameters of the PID controller and the parameters of the virtual reference model by using an intelligent optimization algorithm; step S103, calculating the intelligent VRFT fitness value of each particle according to the PID and the virtual reference model; step S104, optimizing and solving the optimal PID controller parameters by using an intelligent optimization algorithm; step S105, connecting the optimized optimal PID controller to the urban rail transit train speed control system to realize the control of the train speed. Compared with the prior art, the present invention has the advantages of solving the problem that it is difficult to establish an accurate mathematical model of the urban rail transit speed system in practice, solving the problem of the difficulty in selecting the adjustment parameters of the virtual reference model in the VRFT method, saving a lot of time and energy needed in the modeling process, etc.

Description

Technical Field

[0001] The invention relates to a rail transit signal system, and in particular to an urban rail transit train speed control method based on intelligent VRFT. Background Art

[0002] As urban rail transit develops faster and faster, the requirements for train comfort and energy efficiency are getting higher and higher, and the control of train speed has become a hot topic. At present, the research directions are mainly focused on PID control, neural network control, fuzzy control, etc., among which PID control (a general term for proportional, integral, and differential control) is one of the most widely used control algorithms to date. PID control is one of the earliest developed control strategies. Due to its simplicity, good robustness and high reliability, it is widely used in industrial process control, especially for deterministic control that can establish accurate mathematical models. However, the train object mechanism is complex and the precise mathematical object cannot be identified. PID control based on the mathematical model of train speed is difficult to achieve the expected control effect.

[0003] However, the data-driven control method does not require the establishment of an accurate train speed model. In particular, the virtual reference feedback tuning VRFT (Virtual Reference Feedback Tuning) method only requires a set of input and output data of the train speed to complete the controller design. The selection of virtual reference model parameters in the VRFT method determines whether a theoretically optimal controller can be designed. However, there is a lack of effective methods and theoretical basis for selecting the controller structure and the parameters of the virtual reference model. Therefore, how to solve the problem of the difficulty in selecting controller parameters and virtual reference model parameters, and apply them to urban rail transit train speed control to achieve effective control of train speed, has become a technical problem that needs to be solved. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and provide a method for controlling the speed of urban rail transit trains based on intelligent VRFT.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] According to a first aspect of the present invention, a method for controlling the speed of an urban rail transit train based on an intelligent VRFT is provided, the method comprising the following steps:

[0007] Step S101, collecting a set of input and output data of the urban rail transit train speed control system;

[0008] Step S102, initializing the PID controller parameters and the parameters of the virtual reference model using an intelligent optimization algorithm;

[0009] Step S103, calculating the intelligent VRFT fitness value of each particle according to the PID and the virtual reference model;

[0010] Step S104, using an intelligent optimization algorithm to optimize and solve the optimal PID controller parameters;

[0011] Step S105, connecting the optimized PID controller to the urban rail transit train speed control system to achieve control of the train speed.

[0012] As a preferred technical solution, a set of input and output data in step S101 is {u i ,y i}, where i=1,2,…,N,u i represents the input data of the speed control of the i-th train, y i represents the output data of the i-th train speed control system, and N represents the input and output data length.

[0013] As a preferred technical solution, the intelligent VRFT method in step S103 is specifically as follows:

[0014] According to the controlled object P(z -1 ) a set of input and output data {u i, y i} Calculate the virtual reference signal r vir , where P(z -1 ) represents the urban rail transit train speed object;

[0015] Controller C(z -1 ) Ensure that the input is e vir When u vir As close as possible to the input data u of the controlled object, so that the output of the controlled object is y, the controller parameters are identified by the least squares method so that the sum of the squares of the controller output calculated based on the reference signal and the actual output collected is minimized, where the input data u and the virtual reference error signal e vir Select a suitable filter L(z) for filtering as shown in formula (1), the VRFT method objective function J VRFT The calculation process of is shown in formula (2), and the expression of incremental PID discretization C(z -1 ) is shown in formula (3), where k p , k i , k d They are the proportional adjustment coefficient, integral adjustment coefficient, and differential adjustment coefficient of the PID controller respectively;

[0016]

[0017]

[0018]

[0019] where u L (i) is the input of the real input data after passing through the filter, u vir (i) is the virtual reference input, e L vir (i) is the signal error after passing through the filter, M -1 (z -1 ) is the inverse expression of the VRFT reference model, L(z) is the expression of the filter, and z represents the Z transform of the expression;

[0020] The reference model M(z -1 )Select expression (4), where A is the adjustment parameter of the reference model, d is the time delay of the controlled object, M(z -1 ) directly determines the control performance of the PID controller; the intelligent VRFT method simultaneously optimizes the controller parameters and the reference model adjustment parameters to improve the controller performance. The intelligent VRFT fitness function is expressed as expression (5), where k is the proportion of the reference model adjustment parameters;

[0021]

[0022] J iVRFT N (θ) = J VRFT +k×A (5)

[0023] Combining Equation 3 and Equation 4, the virtual reference output u in Equation 2 is vir The calculation expression of is shown in formula 6:

[0024]

[0025] where u vir (z -1 ) is the virtual reference input expression, and y is the actual output;

[0026] u vir The expression is further expressed as formula 7:

[0027]

[0028] are the PID controller parameters k p , k i , k d The corresponding coefficients are shown in equations 8-10. The indices of the three coefficients are determined by the sampled output data and the reference model adjustment parameter A;

[0029]

[0030]

[0031]

[0032] As a preferred technical solution, the intelligent optimization algorithm in step S102 adopts a particle swarm optimization algorithm PSO.

[0033] As a preferred technical solution, the particle swarm optimization algorithm PSO takes the adjustment parameter A of the virtual reference model and the PID controller parameters kp, ki, and kd as optimization objects, uses Formula 5 as the fitness function, and optimizes and solves the optimal PID controller parameters.

[0034] As a preferred technical solution, each particle in the particle swarm optimization algorithm (PSO) algorithm is a potential optimal solution. The speed and position are used to reflect the characteristics of each particle. In each iteration, each particle is updated by the current position and the speed of the particle. The speed of the particle is dynamically adjusted according to the individual optimal solution and the global optimal solution, and the optimal solution is found through continuous iteration.

[0035] As a preferred technical solution, the calculation formula of the PSO algorithm is as follows:

[0036]

[0037]

[0038] Where V i k+1 represents the velocity of the particle at the k+1th iteration; V i k represents the current velocity of the particle at the kth iteration; w is the inertia weight; c1 is the individual learning factor; Pbest i k represents the individual optimal solution of the particle in the kth iteration; c2 is the social learning factor; Gbest k represents the global optimal solution of the population during the kth iteration; r1 and r2 represent random numbers in the range [0,1]; X i k represents the current position of the particle at the kth iteration; X i k+1 Indicates the updated position of the particle.

[0039] As a preferred technical solution, this method only requires a set of input and output data of the urban rail transit train speed control system, and globally coordinates and optimizes the reference model and PID controller parameters through an intelligent optimization algorithm.

[0040] According to a second aspect of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and the method described above is implemented when the processor executes the program.

[0041] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the program implements the method described above when executed by a processor.

[0042] Compared with the prior art, the present invention has the following advantages:

[0043] 1) The present invention does not need to establish a mathematical model for the urban rail transit train speed system. By adopting the intelligent VRFT method, only a set of input and output data of the urban rail transit train is needed to complete the design of the PID controller and realize the control of the urban rail transit train speed. This solves the problem that it is difficult to establish an accurate mathematical model of the urban rail transit speed system in practice, and saves a lot of time and energy required in the modeling process.

[0044] 2) The present invention globally coordinates and optimizes the reference model and PID controller parameters through an intelligent optimization algorithm, solves the reference model and PID controller structure design problems, and thus realizes the optimal PID controller design.

[0045] 3) The present invention introduces the intelligent VRFT algorithm into the speed control of urban rail transit trains for the first time, provides a new algorithm for train speed control, and achieves an ideal control effect for train speed control, which has great application significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is the principle diagram of VRFT method;

[0047] Figure 2 It is the schematic diagram of the intelligent VRFT method applied to the PID controller;

[0048] Figure 3 It is a specific flow chart of the method of the present invention;

[0049] Figure 4 It is a control curve diagram of the ATO train speed model of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0051] The present invention applies the intelligent VRFT method to urban rail transit train speed PID control for the first time, solves the problem of artificial trial PID parameters and virtual reference model parameters commonly used in the field of urban rail transit, and provides an urban rail transit train speed PID control method based on intelligent VRFT. The method does not need to establish an urban rail transit train speed model, but only requires a set of input and output data under the closed-loop condition of the train. The PID controller parameters are adjusted and the parameters of the virtual reference model are identified through an intelligent optimization algorithm to complete the speed control of the urban rail transit train. Simulation experiments show that the method is correct and has high performance, and has great application significance and theoretical value.

[0052] The present invention provides a PID control method for urban rail transit train speed based on intelligent VRFT, comprising the following steps:

[0053] Step S101, collecting a set of input and output data {u i ,y i} i＝1,2,…,N , where u i represents the input data of the speed control of the i-th train, y i represents the output data of the i-th train speed control system, and N represents the length of input and output data;

[0054] Step S102, initializing the PID controller parameters and the parameters of the virtual reference model using an intelligent optimization algorithm;

[0055] Step S103, using an intelligent VRFT method, the PID controller parameters and the parameters of the virtual reference model can be collaboratively optimized without modeling the urban rail transit train speed, so as to obtain the desired PID controller parameters;

[0056] Step S104, using intelligent optimization algorithms such as particle swarm optimization (PSO), differential evolution algorithm, etc., taking the adjustment parameter A of the virtual reference model and the PID controller parameters kp, ki, kd as the optimization objects, and taking Formula 5 as the fitness function, optimizing and solving the optimal PID controller parameters. The algorithm flow is as follows: Figure 3 As shown;

[0057] Step S105, connecting the optimized PID controller to the urban rail transit train speed control system to achieve control of the train speed. Specific embodiments

[0059] The following embodiments use a single-particle dynamics velocity model of an automatic train operation (ATO) system, and the object function is:

[0060]

[0061] Taking the sampling time T = 0.001s, the discrete transfer function of the ATO train is:

[0062]

[0063] It should be noted that the speed model of the ATO train is only used to obtain test data and method verification. In the intelligent VRFT method, there is no need to establish a mathematical model of the train speed, and the design of the PID controller can be completed directly using a set of input and output data.

[0064] Urban rail transit train speed PID control method based on intelligent VRFT, the principle is as follows Figure 2 As shown, the process is as follows Figure 3 As shown, the following steps are included:

[0065] 1. Perform an open-loop test on the ATO train and apply a set of step signals u i , measure its corresponding velocity output y i , and obtain this set of input and output data {u i ,y i}i=1,2,…,N, where u i represents the input data of the speed control of the i-th train, y i represents the output data of the i-th train speed control system, N represents the length of input and output data, and in this example, the value of N is 1000.

[0066] 2. There are many types of intelligent optimization algorithms. This example uses the particle swarm optimization algorithm PSO, but intelligent optimization algorithms are not limited to this method. The particle swarm optimization algorithm PSO is a group-based intelligent optimization algorithm that optimizes the search by simulating the foraging behavior of birds. Each particle in the PSO algorithm is a potential optimal solution, and the speed and position are used to reflect the characteristics of each particle. During each iteration, each particle is updated by the current position and speed of the particle. The speed of the particle is dynamically adjusted according to the individual optimal solution and the global optimal solution. The optimal solution is found through continuous iteration. The calculation of the PSO algorithm is shown in Formula 13:

[0067]

[0068] V i k+1 represents the velocity of the particle at the k+1th iteration; V i k represents the current velocity of the particle at the kth iteration; w is the inertia weight; c1 is the individual learning factor; Pbest ik represents the individual optimal solution of the particle in the kth iteration; c2 is the social learning factor; Gbest k represents the global optimal solution of the population during the kth iteration; r1 and r2 represent random numbers in the range [0,1]; X i k represents the current position of the particle at the kth iteration; X i k+1 Indicates the updated position of the particle.

[0069] Set the number of iterations to 10 3 times, the population size M is 50, the individual learning factor c1 is 2, the social learning factor c2 is 2, the inertia weight w is 0.6, the position X represents the controller parameters kp, ki, kd, A, and k in Equation 5 is 0.001.

[0070] 3. Randomly initialize the speed V and position X of the 50 individuals in the PSO algorithm, and calculate the fitness value of each individual according to Formula 5.

[0071] 4. Update the speed and position of each individual according to formula 13.

[0072] 5. Recalculate the fitness value of each individual according to formula 5, and update the optimal solution of each individual and the global optimal solution

[0073] 6. Determine whether the algorithm has reached the maximum number of iterations. If so, output the optimal solution kp, ki, kd, A. Otherwise, continue to step 4.

[0074] 7. Output the optimal PID controller parameters and use them to control the ATO train speed model, such as Figure 4 shown.

[0075] 8. The simulation results show that for the simplified mathematical model of train speed, the PSO algorithm is used to optimize the three parameters of PID controller kp, ki, kd and the VRFT reference model adjustment parameter A to complete the design of the optimal PID controller, in which the rise time and overshoot can meet the control performance index requirements and realize the urban rail transit train speed control based on intelligent VRFT. In the case that the mathematical model of train speed cannot be accurately established in practice, the urban rail transit train speed PID control method based on intelligent VRFT only needs a set of input and output data to realize the optimal design of the controller, which is more advantageous in the actual train speed control application.

[0076] The above is an introduction to a method embodiment. The following further illustrates the solution of the present invention through an electronic device and a storage medium embodiment.

[0077] The electronic device of the present invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0078] Multiple components in the device are connected to the I / O interface, including: input units, such as keyboards, mice, etc.; output units, such as various types of displays, speakers, etc.; storage units, such as disks, optical disks, etc.; and communication units, such as network cards, modems, wireless communication transceivers, etc. The communication unit allows the device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunication networks.

[0079] The processing unit performs the various methods and processes described above, such as methods S101 to S105. For example, in some embodiments, methods S101 to S105 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on the device via a ROM and / or a communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more steps of methods S101 to S105 described above may be performed. Alternatively, in other embodiments, the CPU may be configured to execute methods S101 to S105 in any other appropriate manner (e.g., by means of firmware).

[0080] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0081] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0082] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0083] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for controlling the speed of urban rail transit trains based on intelligent VRFT, characterized in that: The method comprises the following steps: Step S101, collecting a set of input and output data of the urban rail transit train speed control system; Step S102, initializing the PID controller parameters and the parameters of the virtual reference model using an intelligent optimization algorithm; Step S103, calculating the intelligent VRFT fitness value of each particle according to the PID and the virtual reference model; Step S104, using an intelligent optimization algorithm to optimize and solve the optimal PID controller parameters; Step S105, connecting the optimized PID controller to the urban rail transit train speed control system to achieve train speed control; The set of input and output data in step S101 is {u i ,y i }, where i=1,2,…,N,u i represents the input data of the speed control of the i-th train, y i represents the output data of the i-th train speed control system, and N represents the length of input and output data; The intelligent VRFT method in step S103 is specifically as follows: According to the controlled object P(z -1 ) a set of input and output data {u i, y i } Calculate the virtual reference signal r vir , where P(z -1 ) represents the urban rail transit train speed object; Controller C(z -1 ) Ensure that the input is e vir When u vir As close as possible to the input data u of the controlled object, so that the output of the controlled object is y, the controller parameters are identified by the least squares method so that the sum of the squares of the controller output calculated based on the reference signal and the actual output collected is minimized, where the input data u and the virtual reference error signal e vir Select a suitable filter L(z) for filtering as shown in formula (1), the VRFT method objective function J VRFT The calculation process of is shown in formula (2), and the expression of incremental PID discretization C(z -1 ) is shown in formula (3), where k p , k i , k d They are the proportional adjustment coefficient, integral adjustment coefficient, and differential adjustment coefficient of the PID controller respectively; where u L (i) is the input of the real input data after passing through the filter, u vir (i) is the virtual reference input, e L vir(i) is the signal error after passing through the filter, M -1 (z -1 ) is the inverse expression of the VRFT reference model, L(z) is the expression of the filter, and z represents the Z transform of the expression; The reference model M(z -1 )Select expression (4), where A is the adjustment parameter of the reference model, d is the time delay of the controlled object, M(z -1 ) directly determines the control performance of the PID controller; the intelligent VRFT method simultaneously optimizes the controller parameters and the reference model adjustment parameters to improve the controller performance. The intelligent VRFT fitness function is expressed as expression (5), where k is the proportion of the reference model adjustment parameters; I iVRFT N (θ)=J VRFT +k×A (5) Combining equations (3) and (4), the virtual reference output u in equation (2) is vir The calculation expression of is shown in formula (6): where u vir (z -1 ) is the virtual reference input expression, and y is the actual output; u vir The expression is further expressed as formula (7): are the PID controller parameters k p , k i , k d The corresponding coefficients are shown in equations (8)-(10). The values ​​of the three coefficients are determined by the sampled output data and the reference model adjustment parameter A; The intelligent optimization algorithm in step S102 adopts the particle swarm optimization algorithm PSO; The particle swarm optimization algorithm PSO takes the adjustment parameter A of the virtual reference model and the PID controller parameters kp, ki, kd as the optimization objects, takes formula (5) as the fitness function, and optimizes and solves the optimal PID controller parameters.

2. According to claim 1, a method for controlling the speed of urban rail transit trains based on intelligent VRFT is characterized in that: In the particle swarm optimization algorithm (PSO) algorithm, each particle is a potential optimal solution. The speed and position are used to reflect the characteristics of each particle. In each iteration, each particle is updated by the current position and the speed of the particle. The speed of the particle is dynamically adjusted according to the individual optimal solution and the global optimal solution, and the optimal solution is found through continuous iteration.

3. According to claim 2, a method for controlling the speed of urban rail transit trains based on intelligent VRFT is characterized in that: The calculation formula of the PSO algorithm is as follows: V i k+1 =wV i k +c1r1(Pbest i k -X i k )+c2r2(Gbest i k -X i k ) X i k+1 =X i k +V i k+1 Where V i k+1 represents the velocity of the particle at the k+1th iteration; V i k represents the current velocity of the particle at the kth iteration; w is the inertia weight; c1 is the individual learning factor; Pbest i k represents the individual optimal solution of the particle in the kth iteration; c2 is the social learning factor; Gbest i k represents the global optimal solution of the population during the kth iteration; r1 and r2 represent random numbers in the range [0,1]; X i k represents the current position of the particle at the kth iteration; X i k+1 Indicates the updated position of the particle.

4. The urban rail transit train speed control method based on intelligent VRFT according to claim 1 is characterized in that: This method only requires a set of input and output data of the urban rail transit train speed control system, and globally coordinates the optimization of the reference model and PID controller parameters through an intelligent optimization algorithm.

5. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images