Dynamic Fuzzy Neural Intelligent Control for ship course tracking

Aiming at modeling and controlling a kind of nonlinear dynamic systems and dealing with the uncertainties coursing by the changing of modeling parameters, a Dynamic Fuzzy Neural Intelligent Controller (DFNIC) is presented in this paper. A dynamic fuzzy neural networks (DFNN) with a PID controller are integrated in DFNIC, in which the structure and parameters are adjusted online, and the fuzzy rules are automatically generated when being trained. The intelligent algorithm conquers the disadvantage of either overfitting or overtraining in traditional static fuzzy neural networks based control methods. Simulation results of a container ship course tracking control validate the effectiveness of the proposed algorithm.