T-S norm fuzzy neural network controller for underwater vehicles based on hybrid learning algorithm

Aiming at the problems that fuzzy neural network controller has heavy computation and response lag, a T-S fuzzy neural network based on hybrid learning algorithm was proposed. Immune genetic algorithm was used to optimize the parameters of membership functions off line, and the neural network was used to adjust the parameters of membership functions on line to enhance the response of the controller. Moreover, the latter network automatically adjusted the fuzzy rules to reduce the computation of the neural network and improve the robustness and adaptability of the controller, so that the controller can work well ever when underwater vehicles work in hostile ocean environment. Finally, simulation experiments were carried on ldquoXXrdquo underwater vehicle .The results show that this controller has great improvement in response and overshoot, compared with the traditional controller.