Fault-tolerant control for high-speed trains based on neural network embedded compensation control

In this paper, novel adaptive fault-tolerant control (FTC) algorithms are put forward to address the position and velocity tracking control problems of high-speed trains (HSTs). The basic running resistances, additional resistances and interactive forces between the connected carriages are taken into account. On account of the system uncertainties, a novel multidimensional sliding mode surface with time-varying parameters estimated by the adaptive technique is proposed. And neural networks (NNS) are made use of approximating the additional resistances viewed as a bounded disturbance. Two cases for system parameters are taken into consideration: 1) Parameters with unknown boundary are unknown; 2) Parameters with known upper and lower boundary are unknown. As for the former, the unknown parameters are formulated via formal mathematical expression with indicator functions and the adaptive technique is introduced; As for the latter, a continuous functions related to the above multidimensional sliding mode surface is defined and the adaptive technique with Project functions is designed, which guarantees saturation characteristics of the presented controller. The closed-loop system stability can be proved by means of the Lyapunov theory and the feasibility and effectiveness of the presented control schemes can be revealed via simulation experiments.

This paper discusses the problem of fault-tolerant tracking control for discrete-time nonstrict-feedback nonlinear systems in the presence of stochastic noises and actuator faults. The system is characterized by a discrete-time nonstrict-feedback structure and multiplicative stochastic noise related to the states, which poses a challenge for the design and analysis of the fault-tolerant controller. Moreover, the considered actuator faults include multiplicative and additive faults without prior information. By integrating the properties of the backstepping framework and neural networks, and by introducing an adaptive fault compensation term, a novel fault-tolerant tracking control strategy is proposed. The effects of faults are compensated and the difficulties caused by the system structure are overcome, avoiding the algebraic loop problem and overcoming the causal contradiction. Given specific parameters, the designed fault-tolerant controller can ensure that the tracking error converges to an adjustable region regarding the origin and that all system signals are uniformly bounded concerning the mean-square sense. The simulation examples illustrate the effectiveness of the designed fault-tolerant control method. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —As system complexity has been increasing, practical systems are often affected by faults when performing tracking control. Fault-tolerant control can provide acceptable robustness and improve system safety. On the one hand, many practical systems are nonlinear, difficult to model mathematically and accurately, and affected by stochastic noises. On the other hand, with digital control, the object is a discrete-time system. In practical applications, the upper bounds of the faults and the noises are often unknown. In this paper, a novel adaptive fault-tolerant control method is proposed for the more general uncertain discrete-time nonlinear systems, i.e., nonstrict-feedback nonlinear systems, with stochastic noises and actuator faults. Neural networks and an adaptive fault compensation term are integrated into the fault-tolerant controller. By adjusting the controller parameters properly, it is ensured that the tracking error converges to a small neighborhood of zero in the event of a fault occurring. In future research, sensor faults, input constraints, optimal control design, and applications in multi-agent systems will be considered.

This paper presents a fault-tolerant flight control method for a multi-rotor UAV under actuator failure and external wind disturbances. The control method is based on an active disturbance rejection controller (ADRC) and spatio-temporal radial basis function neural networks, which can be used to achieve the stable control of the system when the parameters of the UAV mathematical model change. Firstly, an active disturbance rejection controller with an optimized parameter design is designed for rthe obust control of a multi-rotor vehicle. Secondly, a spatio-temporal radial basis function neural network with a new adaptive kernel is designed. In addition, the output of the novel radial basis function neural network is used to estimate fusion parameters containing actuator faults and model uncertainties and, consequently, to design an active fault-tolerant controller for a multi-rotor vehicle. Finally, fault injection experiments are carried out with the Qball-X4 quadrotor UAV as a specific research object, and the experimental results show the effectiveness of the proposed self-tolerant, fault-tolerant control method.

Automatic operation of high speed trains (HSTs) requires dedicated control schemes to tackle uncertain dynamics, unknown resistive forces, coupling nonlinearities, interactive in-train forces, unexpected disturbances, and faults. This paper addresses the problem of position and velocity tracking control of HSTs with multiple vehicles connected through elastic couplers. A neuro-adaptive fault tolerant control scheme is developed to compensate the input nonlinearities due to traction or braking notches, uncertain impacts from in-train forces, resistive aerodynamic drag forces, traction or braking faults, and adherence-antiskid constraints. High precision velocity and position tracking is achieved by using the proposed control scheme that combines the robust adaptive control with nonlinearly layered neural networks. Closed-loop stability is ensured with strict mathematical analysis. The effectiveness of the proposed approach is also validated through numerical simulations with considering the adherence-antiskid constraints.

Many control methods are used in attitude control of reentry vehicle, such as optimal control and classical control methods. However, those control laws may not work effectively if the attitude system is confronted with actuator faults and saturation. This paper proposes an adaptive fault tolerant attitude control method for the reentry vehicle's attitude control system, by combining the radial basis function network technology with adaptive fault tolerant control method. We simultaneously considered actuator fault, actuator saturation, time varying unknown disturbances and uncertainties when designing the control method. First, we set up the reentry attitude dynamic model concerning actuator fault; second, a finite-time H∞ adaptive fault-tolerant attitude controller is introduced to deal with the actuator fault, saturation, unknown disturbances and uncertainties of the reentry vehicle system; we proved the stability of our proposed adaptive attitude fault-tolerant controller through the Lyapunov function and the linear matrix inequality method. Finally, the effectiveness of such adaptive fault-tolerant control method has been identified by numerous simulation results. The simulation results show that our proposed method can not only effectively deal with actuator fault in the attitude control system, but also has very good robustness for actuator saturation, time varying unknown disturbances and uncertainties.

Analysis and design of control systems via parameter‐based approach

This paper presents an adaptive fault-tolerant control (FTC) scheme for leader-follower formation of uncertain secondorder mobile agents with actuator faults. A local FTC component is designed for each agent in the distributed system by using local measurements and suitable information exchanged between neighboring agents. Each local FTC component consists of a fault detection module and a reconfigurable controller module comprised of a baseline controller and an adaptive fault-tolerant controller activated after fault detection. Under certain assumptions, the closed-loop system stability and leader-follower formation properties of the distributed system are rigorously established under different modes of behavior of the FTC system. A simulation example is used to illustrate the effectiveness of the FTC method.

This study proposes a novel fault tolerant voltage control method considering actuator faults and disturbances by using the backstepping control augmented by a new differentiator for islanded microgrids (MGs). Existing voltage control methods are designed based on the ideal condition that the distributed generations' actuators work healthily with the assumption of the absence of faults and disturbances, whereas MGs are exposed to the actuator faults including partial loss of effectiveness and biased faults. The proposed controller robustly regulates the MG voltages irrespective of the actuator faults. In contrast to existing methods, the controller has considered both actuator faults and loads with harmonic/interharmonic currents, which does not need to know the exact model of faults and frequency of harmonic and interharmonic of MG loads. This feature enables the MG to work properly, even at the lowest level, instead of the system completely collapsing. Therefore, it improves the reliability of the MG system. The MATLAB/SimPowerSystems toolbox has verified the validity of the proposed fault tolerant control method. Compared with effective methods, both the theoretical and simulation results show that the proposed method has better, robust, resilient, acceptable, and desirable performance, with respect to the unknown faults, actuator faults, non‐linear loads, and disturbances.

This paper studies the robust fault-tolerant control problem against actuator faults and parameter uncertainty for High-Speed Trains. First, models of actuator faults and parameter uncertainty are presented. Then a robust fault-tolerant tracking controller design method is developed. This method is based on the mixed Linear Matrix Inequalities (LMI)/Lyapunov stability theory. Tracking control examples and simulations are given, and the response curves of the fault system and the system with the fault-tolerant tracking controller are presented.

The fault-tolerant control problem is investigated for high-speed trains with actuator faults and multiple disturbances. Based on the novel train model resulting from the Takagi–Sugeno fuzzy theory, a sliding-mode fault-tolerant control strategy is proposed. The norm bounded disturbances which are composed of interactive forces among adjacent carriages and basis running resistances are rearranged by the fuzzy linearity technique. The modeled disturbances described as an exogenous system are compensated for by a disturbance observer. Moreover, a sliding mode surface is constructed, which can transform the stabilization problem of position and velocity into the stabilization problem of position errors and velocity errors, i.e., the tracking problem of position and velocity. Based on the parallel distributed compensation method and the disturbance observer, the fault-tolerant controller is solved. The Lyapunov theory is used to prove the stability of the closed-loop system. The feasibility and effectiveness of the proposed fault-tolerant control strategy are illustrated by simulation results.

This paper investigates the position and velocity tracking control problem of high-speed trains with multiple vehicles connected through couplers. A dynamic model reflecting nonlinear and elastic impacts between adjacent vehicles as well as traction/braking nonlinearities and actuation faults is derived. Neuroadaptive fault-tolerant control algorithms are developed to account for various factors such as input nonlinearities, actuator failures, and uncertain impacts of in-train forces in the system simultaneously. The resultant control scheme is essentially independent of system model and is primarily data-driven because with the appropriate input-output data, the proposed control algorithms are capable of automatically generating the intermediate control parameters, neuro-weights, and the compensation signals, literally producing the traction/braking force based upon input and response data only--the whole process does not require precise information on system model or system parameter, nor human intervention. The effectiveness of the proposed approach is also confirmed through numerical simulations.

The problem of active fault-tolerant control (FTC) is investigated for the large-scale nonlinear systems in nonstrict-feedback form. The nonstrict-feedback nonlinear systems considered in this paper consist of unstructured uncertainties, unmeasured states, unknown interconnected terms, and actuator faults (e.g., bias fault and gain fault). A state observer is designed to solve the unmeasurable state problem. Neural networks (NNs) are used to identify the unknown lumped nonlinear functions so that the problems of unstructured uncertainties and unknown interconnected terms can be solved. By combining the adaptive backstepping design principle with the combination Nussbaum gain function property, a novel NN adaptive output-feedback FTC approach is developed. The proposed FTC controller can guarantee that all signals in all subsystems are bounded, and the tracking errors for each subsystem converge to a small neighborhood of zero. Finally, numerical results of practical examples are presented to further demonstrate the effectiveness of the proposed control strategy.The problem of active fault-tolerant control (FTC) is investigated for the large-scale nonlinear systems in nonstrict-feedback form. The nonstrict-feedback nonlinear systems considered in this paper consist of unstructured uncertainties, unmeasured states, unknown interconnected terms, and actuator faults (e.g., bias fault and gain fault). A state observer is designed to solve the unmeasurable state problem. Neural networks (NNs) are used to identify the unknown lumped nonlinear functions so that the problems of unstructured uncertainties and unknown interconnected terms can be solved. By combining the adaptive backstepping design principle with the combination Nussbaum gain function property, a novel NN adaptive output-feedback FTC approach is developed. The proposed FTC controller can guarantee that all signals in all subsystems are bounded, and the tracking errors for each subsystem converge to a small neighborhood of zero. Finally, numerical results of practical examples are presented to further demonstrate the effectiveness of the proposed control strategy.

This article investigates the cooperative fault-tolerant control problem for multiple high-speed trains (MHSTs) with actuator faults and communication delays. Based on the actor-critic neural network, a distributed sliding mode fault-tolerant controller is designed for MHSTs to solve the problem of actuator faults. To eliminate the negative effects of unknown disturbances and time delay on train control system, a distributed radial basis function neural network (RBFNN) with adaptive compensation term of the error is designed to approximate the nonlinear disturbances and predict the time delay, respectively. By calculating the tracking error online, an actor-critic structure with RBFNN is used to estimate the switching gain of the distributed controller, which reduces the chattering phenomenon caused by sliding mode control. The global stability and ultimate bounded of all signals of the closed-loop system are proposed with strict mathematic proof. Simulations show that the proposed method has superior effectiveness and robustness compared with other fault-tolerant control methods, which ensures the safe operation of MHSTs under moving block conditions.

An investigation of fault tolerant control of distillation columns under faulty sensors and actuators is presented in this work. Real-time sensor and actuator fault detection, propagation and accommodation are all investigated. Dynamic principal components analysis is used to promptly and effectively detect and isolate actuator and sensor faults. Alternative control strategy is then implemented to accommodate the faults. Specifically, fault tolerant inferential control is employed to accommodate sensor fault using soft sensor developed through dynamic principal component regression. Dual composition control strategy used for normal column operation is switched to one-point control to accommodate actuator fault utilizing the remaining healthy actuator. The main contributions of this paper is the application of fault tolerant inferential control and one-point control strategy to accommodate sensor and actuator faults respectively in the distillation column operation. The effectiveness of the proposed approaches are demonstrated on a simulated methanol-water separation column.

Adaptive neural network state constrained fault-tolerant control for a class of pure-feedback systems with actuator faults