A MODEL-REFERENCE CONTROL-STRUCTURE USING A FUZZY NEURAL-NETWORK

In this paper, we present a design method for a model reference control structure using a fuzzy neural network. We study a simple fuzzy-logic based neural network system. Knowledge of rules is explicitly encoded in the weights of the proposed network and inferences are executed efficiently at high rate. Two fuzzy neural networks are utilized in the control structure. One is a controller, called the fuzzy neural network controller (FNNC); the other is an identifier, called the fuzzy neural network identifier (FNNI). Adaptive learning rates for both the FNNC and FNNI are guaranteed to converge by a Lyapunov function. The on-line control ability, robustness, learning ability and interpolation ability of the proposed model reference control structure are confirmed by simulation results.