Dual mode adaptive control with Gaussian networks

Abstract

An adaptive control structure called dual mode adaptive control (DMAC) is proposed for a class of nonlinear systems. A Gaussian neural network is used to adaptively compensate the plant nonlinearity. The network learning strategy is based on a combination of parameter adaptation learning with variable structure control. The proposed controller is compared to a controller based on a convex combination of variable structure and parameter adaptive laws. As an application, we focus on the problem of nonlinearly parametrized systems.