NN-adaptive output feedback for path tracking control of a surface ship at high speed

An adaptive output feedback controller based on neural network (NN) is proposed, which forces a surface ship at high speed to track a desired path. In general, tracking problem of the surface ship at low speed has been widely investigated in many studies, in which coupling interactions among the forces from each degree of freedom (DOF) is not considered. Nevertheless, the nonlinear characteristics of the hydrodynamic damping can never be neglected in high speed maneuvering situation. For this reason, the influence of the hydrodynamic damping on the tracking precision is considered in this paper. Since the hydrodynamic coefficients of the surface ship at high speed are very difficult to be accurately estimated as a prior, the unknown part of the tracking dynamics system is approximated by neural network. The stability analysis will be given by Lyapunov theorem. Numerical simulations illustrate the excellent tracking performance of the surface ship at high speed under the proposed control scheme.