Automatic tuning of a fuzzy logic controller using neural network

This paper presents a method for automatic tuning of a fuzzy logic controller based on a control scheme which consists of a fuzzy logic controller and a conventional derivative controller. For this purpose, a neural network is first used to represent fuzzy logic inference. Membership functions regarding change-in-error e/spl dot/, which represent the feedback of velocity, are then defined by the functions of cubic splines. A desired control performance of a system is achieved by the adaptation of the defined membership functions using neural network in the self-organizing process. To demonstrate the effectiveness and robustness of the proposed fuzzy neural network control we report a number of simulation results involving both stepping and tracking controls of a nonlinear plant.<
>