Nonlinear feedback control based on ANFIS

Adaptive neural fuzzy interference system (ANFIS) controller has advantages of solving the control problem of uncertain systems by means of a fuzzy system and optimizing controller parameters though the self-learning ability of a neural network. For nonlinear and uncertain ship motion, ANFIS course keeping controller is designed to deal with the difficulty of parameters adjustment. Based on the controller, by modulating the control error utilizing a sine function as the feedback signal to drive the controller, the control performance is improved without changing the construction of the controller. Such kind a control scheme is called nonlinear feedback control. The simulation by Matlab of an oil tanker controlled by a marine autopilot with the suggested control algorithm is carried out. And simulating results indicate that the closed-loop control system responds quickly and the course deviation is smaller after ship stabilizing, although the mean rudder angle increases slightly. Thus the nonlinear feedback control algorithm based on ANFIS is more satisfactory for ship course keeping control.