Learning control of uncertain ocean surface ship dynamics using neural networks

Abstract

This paper presents neural learning control design for trajectory tracking of ocean surface ship dynamics in the presence of model uncertainties, which might be caused by unmodelled dynamics or environmental disturbances. Thanks to the learning capability of radial basis function (RBF) neural networks (NN), stable adaptive NN tracking controller is designed for the uncertain ship dynamics. Partial persistent excitation (PE) condition of some internal signals in the closed-loop system is satisfied during tracking control to a periodic reference trajectory. Under PE condition, the designed adaptive NN controller is shown to be capable of learning of the uncertain ship dynamics in the stable control process. Subsequently, neural learning control using the knowledge obtained from deterministic learning is constructed to achieve closed-loop stability and improved control performance. Simulation studies are performed to demonstrate the effectiveness of the proposed methods.