An Adaptive Neural Network Fast Terminal Sliding Mode Controller for Hovering Motion of Underwater Vehicles

An adaptive neural network fast terminal sliding mode control method which was applied to the hovering motion control of underwater vehicles was proposed in this paper. Based on the conventional fast terminal sliding mode control algorithm, the RBF neural network was introduced, of which the weight adaptation law was obtained by back-stepping method. Compared with the conventional sliding mode controllers, this controller was composed to solve the problem of the dependence on the parameters of the system. At the same time, the stability of the closed-loop system was proved using Lyapunov function. In the end, a simulation is presented, where three control methods were applied to control the hovering motion of underwater vehicle and the results showed that the proposed control method was more superior in terms of the accuracy, rapidity, and robustness.