Course Control Of Air Cushion Vessel Based On Terminal Sliding Mode Control With Rbf Neural Network

A terminal sliding mode (TSM) control system with radial basis function (RBF) neural network, which is designed for enhancing the maneuverability and realizing the course control accurately of air cushion vehicle is proposed in the paper. An advanced TSM is utilized to drive the system to converge in a fast period of time, and attenuate the air cushion vehicle uncertainties and external disturbances. In order to reduce the error caused by the unchangeable surface of the sliding mode control, a RBF neural network is introduced to approximate external disturbances to offset the disadvantage and guarantee robust performance of the sliding mode control by moving the sliding surface effectively. The stability of the proposed movement control law was proved utilizing the Lyapunov theory. Under conditions of different external disturbances, the simulation results of the TSM control confirm that TSM control can achieve fast response speed, good stability and high precision with a simple controller.