A NOVEL MODEL REFERENCE INTELLIGENT ADAPTIVE CONTROL USING NEURAL NETWORK AND FUZZY LOGIC CONTROLLER

In this paper two novel intelligent model reference adaptive controllers are proposed. In these schemes the
intelligent supervisory loop is incorporated into the conventional model reference adaptive controller
framework by utilizing an online growing neural / fuzzy network structure in parallel with it. In the
conventional MRAC scheme, the controller is designed to realize plant output converges to reference model
output based on the plant which is linear with disturbance free system. This scheme is for controlling linear
plant effectively with unknown parameters. However, using MRAC to control the linear system with
disturbance and nonlinearities at real time is difficult. In this paper, it is proposed to incorporate a neural /
fuzzy controller in MRAC to overcome the problem. The control input is given by the sum of the output of
conventional MRAC and the output of neural / fuzzy controller. The effectiveness of the proposed control
schemes is demonstrated by simulations. The proposed schemes can significantly improve the system’s
behavior and force the system to follow the reference model and minimize the error between the model and
plant output