Fractional Order Nonsingular Terminal Sliding Mode Cooperative Fault-Tolerant Control for High-Speed Trains With Actuator Faults Based on Grey Wolf Optimization

This paper mainly studies the cooperative precise control of multiple high-speed trains under external random interference. The safety distance potential energy function is introduced to constrain the safety distance between trains, and the output control quantity is adjusted rapidly in real-time. An effective fractional nonsingular terminal sliding surface is designed to ensure that the system can quickly converge to the equilibrium point while reducing buffeting. The double-loop recurrent neural network with better approximation ability is used to approximate the external interference during high-speed train operation and update the parameters in real-time. Aiming at the possible actuator failure during train operation, a high-robustness fractional nonsingular terminal sliding mode controller is designed, and its stability and convergence are proved by using Lyapunov stability theory. Based on the idea of inertia weight and the nonlinear position update strategy of convergence factor, an improved grey wolf optimization algorithm is proposed to obtain the optimal parameters of the control system. The simulation results show that the method designed in this paper can accurately track the ideal speed and displacement, and has better control accuracy, ideal fault-tolerance, robustness and stability compared with other control methods.