Neural network robust control of ship trajectory tracking

A robust controller based on sliding mode method is presented to force one ship of three degrees of freedom to track a desired trajectory. Neural-network is designed to mimic an equivalent control law in the sliding-mode control, and a robust controller is chosen to curb the system dynamics on the sliding surface, thus the asymptotic stability property of closed system can be guaranteed. Furthermore, an adaptive estimation law based on Lyapunov stability theorem is employed to estimate the nonlinear uncertainties hydrodynamics of closed system. Numerical simulations illustrate the excellent tracking control performance of ship which suitable for engineering application demand.