Dual Mode Adaptive Control using Gaussian Networks: Stability analysis

Abstract This paper presents the stability analysis of a novel adaptive control scheme, for a class of nonlinear plants, based on Neural Networks. The proposed controller, named Dual Mode Adaptive Control with Gaussian Network (DMAC-GN), combines parametric adaptation with variable structure control. This combination results in a controller capable of providing good transient and steady state behavior. Particular emphasis is given to output-feedback schemes. The controller is shown to be globally exponentially stable with respect to a small residual set. Simulations are performed to illustrate several aspects of the theoretical results.