Neural Network Sliding Mode Path Following Control Based on the DVS Algorithm of Underactuated Ships

Abstract

For the external environmental disturbance and model uncertainty of underctuated ships, to further realize the accuracy and stability of ship path tracking. A neural network (NN) sliding mode control strategy based on dynamic virtual ship (DVS) algorithm is proposed, under the condition of model uncertainties and external disturbances caused by winds, waves and currents. The virtual control law of controller is designed by backstepping method, and its derivative is estimated by the dynamic surface control (DSC) to reduce the computational burden. The NN minimum parameter learning method is adopted online to cope with the uncertainties of the model, to approximate the nonlinear terms and to design the actual control law. The direct Lyapunov technique is used to analyze the stability of the closed-loop system. Finally, the algorithm scheme is applied to the 32m mono hull ship, the simulation results are shown that the ship reached the desired path more quickly, and the tracking error was relatively smaller, the robust performance was stronger than before.