Adaptive Neural Network Control for Uncertain High speed train with states constraint and Disturbances

The state of high-speed trains (HSTs) model is constraint and uncertain. An adaptive neural network trajectory tracking control method for HSTs is proposed on the basis of barrier Lyapunov function. The proposed method aims to solve problems, such as the trajectory and speed constraint, model parameter disturbance, and unknown external disturbance of HSTs. The neural network model is used to approximate the model uncertainties. Backstepping controller is constructed by considering the train position and velocity tracking errors. In the proposed controller, virtual controller and disturbance estimation are designed by Lyapunov stability analysis theory. Simulation examples illustrate that the proposed controller is has excellent tracking accuracy for system model parameter and external disturbance.