Neuro-adaptive and robust automatic train control subject to unknown dynamics

Advanced control method plays a key role in guaranteeing safe and reliable automatic train operation. This paper presents a neuro-adaptive robust control method for automatic train operation subject to unknown systematic time-varying dynamics. A general model for describing the train system dynamics is established. A control scheme using assumed bounded values of the unknown time-varying dynamics is proposed for achieving automatic train tracking control, based on which a more advance control scheme without requiring the bounded values is proposed. The closed-loop system is proved to be stable in the sense of Lyapunov. The effectiveness of the theoretical results is demonstrated by numerical simulations.