Abstract
This paper presents an adaptive fuzzy neural controller (AFNC) suitable for modelling and control of MIMO non-linear dynamic systems. The proposed AFNC has the following salient features: (1) fuzzy neural control rules can be generated or deleted dynamically and automatically; (2) uncertain MIMO non-linear systems can be adaptively modelled on line; (3) adaptation and learning speed is fast; (4) expert knowledge can be easily incorporated into the system; (5) the structure and parameters of the AFNC can be self-adaptive in the presence of uncertainties to maintain a high control performance; and (6) the asymptotical stability of the system is established using the Lyapunov approach. Simulation studies on a two-link robot manipulator show that the performance of the proposed controller is better than that of some existing fuzzy/neural methods.