PID-type Sliding Mode Fault-tolerant Control for High-speed Trains using Neural Networks

The fault-tolerant control scheme is developed to tackle with the tracking problem for high-speed trains (HSTs) in the presence of unknown parameters, actuator faults and input saturation. During the procedure of designing controller, neural networks is used to approximate the unknown additional resistance. A sliding mode surface which is similar to proportion integration differentiation (PID) control algorithm is presented to improve the robustness of the system. With the application of the adaptive technique, the unknown parameters of dynamics formulation are estimated. By means of Lyapunov analysis, the stability of the system via the proposed control scheme can be obtained. In additional, all signals of the closed-loop system are proved to be uniformly ultimately bounded and the system has the good position tracking and velocity tracking performances. Compared with the simulation results between the desired controller and the presented controller, it is obvious that the research of compensating actuator faults and input saturation is full of significant, meanwhile, the proposed control strategy is proved to be efficient and feasible.