A Fault-Tolerant Safety Control Method for High-Speed ​​Trains Based on Iterative Learning Strategy

Abstract

This invention discloses a fault-tolerant safety control method for high-speed trains based on an iterative learning strategy, belonging to the field of high-speed train safety control technology. The method includes the following steps: Step 1, dynamic modeling, establishing a dynamic model considering the characteristics of repeated train operation, resistance, and the impact of faults; Step 2, fault estimation, designing an estimator based on an iterative learning strategy to estimate the impact of train operation faults; Step 3, fault-tolerant safety control, designing a train fault-tolerant safety controller based on a finite-fold convergence iterative learning control framework. This invention employs the aforementioned fault-tolerant safety control method for high-speed trains based on an iterative learning strategy, using historical data generated during repeated train operation to improve the accuracy of fault estimation; it designs a finite-fold convergence iterative learning controller, and through the iterative learning gain matrix update mechanism, significantly reduces the required number of repeated operations, effectively meeting the real-time and efficiency requirements of high-speed train system operation control.

Description

Technical Field

[0001] This invention relates to the field of high-speed train safety control technology, and in particular to a fault-tolerant safety control method for high-speed trains based on an iterative learning strategy. Background Technology

[0002] In the field of high-speed train safety control, existing research and technologies have explored various methods to improve safety and reliability. Traditional control strategies such as PID controllers and adaptive control have been widely used, but they have limitations in handling nonlinear systems, parameter variations, and uncertainties. In recent years, with the increasing demand for intelligent transportation systems, learning-based methods have gradually gained attention, among which iterative learning control (ILC) has shown potential due to its unique characteristics. However, current applications of ILC are mainly concentrated in areas such as robot arm motion control in laboratory environments. In practical industrial applications, especially in complex and high-risk environments like high-speed rail, the application of ILC is still in its early stages. Some research attempting to apply ILC to rail transit mainly focuses on how to improve the smoothness and energy efficiency of train acceleration / deceleration, but there is little design for fault-tolerant mechanisms. Furthermore, in practical applications, especially in real-time systems like high-speed trains, the limitations of computation time and the number of iterations must be considered to ensure rapid convergence to satisfactory control performance, which is also a lack of consideration in existing technologies. Summary of the Invention

[0003] The purpose of this invention is to provide a fault-tolerant safety control method for high-speed trains based on an iterative learning strategy. It designs an iterative learning controller that converges after a finite number of iterations and effectively meets the real-time and efficiency requirements of high-speed train system operation control through an iterative learning gain matrix update mechanism.

[0004] To achieve the above objectives, this invention provides a high-speed train fault-tolerant safety control method based on an iterative learning strategy, comprising the following steps:

[0005] Step 1: Dynamic modeling, establishing a dynamic model that considers the characteristics of repeated train operation, resistance, and the impact of faults;

[0006] Step 2: Fault estimation. Design an estimator based on an iterative learning strategy to estimate the impact of train operation faults.

[0007] Step 3: Fault-tolerant safety control. Design a train fault-tolerant safety controller based on a finite-time convergent iterative learning control framework.

[0008] Preferably, in step one, based on the high-speed train dynamics equations, the following train repetition model is established:

[0009]

[0010] in, It is the first derivative of the system state variable with respect to time during the k-th run; k represents the number of times the train runs repeatedly; x k It is the system state variable during the k-th run, and x k =[s k v k ] T s k and v k These represent the train's travel distance and speed during the k-th run, respectively; u k This represents the system control input during the k-th run; f represents the disturbance caused by external resistance during the k-th run; f is the impact of the fault.

[0011] Preferably, step two includes the following steps:

[0012] S21. Construct the Luenberger observer;

[0013]

[0014] in, It is the first derivative of the system state variable observations with respect to time during k runs; These are the system state variable observations during k runs. The observed value represents the disturbance caused by external resistance during the k-th run. For the virtual fault during the k-th run; L is the observer gain matrix;

[0015] S22. Design a fault estimator based on an open-loop and closed-loop PD-type iterative learning strategy:

[0016]

[0017] Where α1 is the open-loop proportional gain, α2 is the closed-loop proportional gain, β1 is the open-loop proportional gain, and β2 is the closed-loop proportional gain.

[0018] Preferably, the observation residual of the high-speed train system state variables in step two is defined as follows:

[0019]

[0020] Preferably, step three includes the following steps:

[0021] S31. High-speed trains perform periodic, repetitive operation tasks, and their target tracking is x. d (t), with the operating interval t∈[0,T];

[0022] S32, the finite-time convergent iterative learning controller is:

[0023] u k+1 (t)=u k (t)+Q(t)e k (t);

[0024] Among them, e k Let Q(t) be the state tracking error during the k-th run, and let Q(t) be the variable learning gain matrix.

[0025] S33. The fault-tolerant safety control law with feedforward is:

[0026]

[0027] Among them, u k * (t) represents the final fault-tolerant safety control input, C = [0M].

[0028] Preferably, in S32, to achieve finite convergence of the iterative learning controller, the variable learning gain matrix Q(t) follows the following update mechanism:

[0029] Q(t) = KP(t)[P(t) + R] -1 ;

[0030] Where K is a positive definite diagonal matrix used to adjust the learning rate; P(t) is the solution to the Riccati equation, reflecting the state covariance of the system; and R is the positive definite weight matrix.

[0031] Therefore, the high-speed train fault-tolerant safety control method based on the above-mentioned iterative learning strategy, as described in this invention, has the following advantages:

[0032] (1) Considering the impact of faults on high-speed trains, a fault estimator based on an open-loop PD-type iterative learning strategy is proposed. It can use historical data generated during repeated train operation to achieve fast and effective fault estimation. Furthermore, the accuracy of fault estimation is continuously improved as the train runs repeatedly, which is beneficial for further fault-tolerant safety control.

[0033] (2) By utilizing the historical data generated during repeated train runs, an iterative learning controller and an iterative learning gain matrix update mechanism are designed. After a limited number of repeated runs, good state tracking results can be obtained. Compared with other similar methods, the tracking error stability value is significantly reduced, and the number of repeated runs required to converge to a lower stability value is also significantly advantageous.

[0034] (3) Based on accurate fault estimation results and a finite-time convergent iterative learning controller, combined with the use of feedforward compensation, the fault-tolerant safety control scheme based on iterative learning strategy can effectively suppress the impact of faults on train operation and achieve accurate operation status tracking.

[0035] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0036] Figure 1 This is a flowchart of the method of the present invention;

[0037] Figure 2 This is a comparison chart of the fault estimation effects of the present invention;

[0038] Figure 3 This is a comparison chart of the fault-tolerant safety control effects of the present invention. Detailed Implementation

[0039] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0040] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0041] Example

[0042] Please see Figure 1-3 This invention provides a fault-tolerant safety control method for high-speed trains based on an iterative learning strategy, comprising the following steps:

[0043] Step 1: Dynamic modeling of high-speed trains; Analyze the dynamic characteristics of high-speed trains, and establish a dynamic model of repeated train operation that considers faults, disturbances and uncertainties, taking into account their operating environment and cyclical running characteristics.

[0044] According to Newton's laws of motion, the dynamic equations of a high-speed train considering the effects of running resistance and faults are as follows:

[0045]

[0046] in, and These are the first derivatives of the train displacement with respect to time and the first derivatives of the train speed with respect to time, respectively; s is the train displacement, v is the train speed, M represents the total mass of the train, u is the control input, ξ is the combined effect of resistance, faults, etc. on the system, a, b, and c are the basic resistance coefficients, and f is the effect of fault factors.

[0047] Based on the dynamic equations of high-speed trains, the following train repetitive operation model is further established:

[0048]

[0049] in, It is the first derivative of the system state variable with respect to time during the k-th run; k represents the number of times the train runs repeatedly; x k It is the system state variable during the k-th run, and x k =[s k v k ] T , where s k and v k These represent the train's travel distance and speed during the k-th run, respectively; u k This represents the system control input during the k-th run; Let represent the disturbance caused by external resistance during the k-th run, and f represents the impact of the fault.

[0050] Step 2: High-speed train fault estimation based on iterative learning strategy; Construct a train operation status observer to estimate the actual operation status of the train online, including key parameters such as speed, position, and acceleration; Based on the observation residuals, design a lumped fault estimator based on iterative learning strategy to gradually improve the accuracy of fault estimation with repeated operation.

[0051] After establishing the dynamic model of repeated high-speed train operation, the following Luenberger observer is constructed:

[0052]

[0053] in, It is the first derivative of the system state variable observations with respect to time during k runs; These are the system state variable observations during k runs. The observed value represents the disturbance caused by external resistance during the k-th run. is the virtual fault during the k-th run; L is the observer gain matrix.

[0054] The observation residuals of state variables in a high-speed train system are defined as follows:

[0055]

[0056] Based on the above observation residuals, the following fault estimator based on an open-loop and closed-loop PD-type iterative learning strategy is designed:

[0057]

[0058] Where α1 is the open-loop proportional gain, α2 is the closed-loop proportional gain, β1 is the open-loop proportional gain, and β2 is the closed-loop proportional gain. By using an iterative learning mechanism, the historical data generated during the repeated cyclical operation of the high-speed train is fully utilized. Data from previous runs is used to accelerate the convergence speed of fault estimation, and data generated during the current run further ensures the dynamic performance of fault estimation.

[0059] Comparing this fault estimation method with other methods demonstrates its effectiveness in fault estimation, and the estimation accuracy significantly improves with repeated operation. Figure 2 As shown.

[0060] Step 3: Design a train fault-tolerant safety controller based on a finite-time convergent iterative learning control framework; design a finite-time convergent iterative learning controller that can complete a full iteration process in a short time; combine the fault estimation results to design a feedforward control module to compensate for the negative impact of faults in advance; combine the finite-time iterative learning controller with the feedforward control based on fault estimation to form a new fault-tolerant safety control strategy for high-speed trains.

[0061] First, consider a high-speed train performing a periodic, repetitive operation task, with its target tracking being x. d (t), with the operating interval being t∈[0,T].

[0062] Define the state tracking error as

[0063] e k (t)=x d (t)-x k (t);

[0064] Design a finite-time convergent iterative learning controller.

[0065] u k+1 (t)=u k (t)+Q(t)e k (t);

[0066] Among them, ek Let t be the state tracking error during the k-th run, and Q(t) be the variable learning gain matrix.

[0067] To achieve finite convergence of the iterative learning controller, the variable learning gain matrix Q(t) follows the following update mechanism:

[0068] Q(t) = KP(t)[P(t) + R] -1 ;

[0069] Where K is a positive definite diagonal matrix used to adjust the learning rate; P(t) is the solution to the Riccat i equation, reflecting the state covariance of the system; and R is the positive definite weight matrix.

[0070] Based on the results of finite-time convergent iterative learning of the controller and fault estimation, the following fault-tolerant safety control law with feedforward is designed:

[0071]

[0072] Among them, u k * (t) represents the final fault-tolerant safety control input, C = [0M].

[0073] like Figure 3 As shown, compared with other iterative learning controllers, this fault-tolerant safety control method can achieve convergence in a finite number of iterations, and the tracking error index is much lower than other existing iterative learning methods. Based on the accurate fault estimation results, feedforward compensation can effectively compensate for the impact of faults on train operation performance.

[0074] Therefore, the present invention adopts the above-mentioned fault-tolerant safety control method for high-speed trains based on an iterative learning strategy, which can improve the accuracy of fault estimation by utilizing historical data generated during repeated train operations; it designs an iterative learning controller with finite convergence, and significantly reduces the number of repeated operations required through the iterative learning gain matrix update mechanism, effectively meeting the real-time and high-efficiency requirements of high-speed train system operation control.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A fault-tolerant safety control method for high-speed trains based on an iterative learning strategy, characterized in that, Includes the following steps: Step 1: Dynamic modeling, establishing a dynamic model that considers the characteristics of repeated train operation, resistance, and the impact of faults; Step 2: High-speed train fault estimation based on iterative learning strategy; Construct a train operation status observer to estimate the actual operation status of the train online; Based on the observation residuals, design a lumped fault estimator based on iterative learning strategy to gradually improve the accuracy of fault estimation with repeated operation. Step two includes the following steps: S21. Construct the Luenberger observer; ； in, It is the first derivative of the system state variable observations with respect to time during k runs; Represents the number of times the train runs repeatedly. These are the system state variable observations during k runs. The observed value represents the disturbance caused by external resistance during the k-th run. This represents a virtual fault during the k-th run. The observer gain matrix is... It is the system state variable during the k-th run, and , and These represent the train's travel distance and speed during the k-th run, respectively. This represents the system control input during the k-th run; , , , M This represents the total mass of the train; S22. Design a fault estimator based on an open-loop and closed-loop PD-type iterative learning strategy: ； in, For the open-loop proportional term gain, For the closed-loop proportional term gain, For the open-loop proportional term gain, This represents the gain of the closed-loop proportional term; In step two, the observation residuals of the state variables of the high-speed train system are defined as follows: ； Step 3: Design a train fault-tolerant safety controller based on a finite-time convergent iterative learning control framework; design a finite-time convergent iterative learning controller that can complete a full iteration process in a short time; combine the fault estimation results to design a feedforward control module to compensate for the negative impact of faults in advance; combine the finite-time iterative learning controller with the feedforward control based on fault estimation to form a new fault-tolerant safety control strategy for high-speed trains. Step three includes the following steps: S31. High-speed trains perform periodic, repetitive operation tasks, and their task target tracking is... The operating range is ; S32, the finite-time convergent iterative learning controller is: ； in, The state tracking error during the k-th run is... It is a variable learning gain matrix; S33. The fault-tolerant safety control law with feedforward is: ； in, Represents the final fault-tolerant safety control input. ; In S32, a variable learning gain matrix is ​​used to achieve finite convergence of the iterative learning controller. Follow the update mechanism as follows: ； in, It is a positive definite diagonal matrix used to adjust the learning rate; It is a solution to the Riccati equation, reflecting the state covariance of the system; It is a positive definite weight matrix.

2. The high-speed train fault-tolerant safety control method based on iterative learning strategy according to claim 1, characterized in that: Step 1: Based on the dynamic equations of the high-speed train, establish the following train repetition model: ； in, It is the first derivative of the system state variable with respect to time during the k-th run; This represents the number of times the train has run repeatedly. It is the system state variable during the k-th run, and , and These represent the train's travel distance and speed during the k-th run, respectively. This represents the system control input during the k-th run; , , ; The disturbance caused by external resistance during the k-th run; This is due to a malfunction.

Images