Intelligent hybrid control for uncertain nonlinear systems using a recurrent cerebellar model articulation controller

An intelligent hybrid control scheme, using an adaptive recurrent cerebellar model articulation controller (CMAC), is developed for a class of nonlinear dynamical systems. In this control system, an adaptive recurrent CMAC is used as the main tracking controller which mimics a perfect control law, and a compensated controller is designed to compensate for the difference between the perfect control law and the adaptive recurrent CMAC. The online adaptive laws of the control system are derived based on the Lyapunov stability theorem, so that the stability of the system can be guaranteed. In addition, in order to relax the requirement for a bound on the minimum approximation error, an adaptive estimation law is derived to estimate the approximation error bound in the compensated controller. Finally, the proposed control system is applied to control a Duffing forced oscillation system and a rocking motion for an aircraft wing. Simulation results demonstrate the effectiveness of the proposed control scheme for nonlinear systems with unknown dynamic functions.