Design and performance analysis of a direct adaptive controller for nonlinear systems

Abstract

In this paper, a direct adaptive controller is developed based on multilayer neural networks (MNNs) for a class of nonlinear systems. The proposed scheme avoids the possible singularity problem of the controller usually met in adaptive control design. The system tracking error is proven to converge to a small neighborhood of zero, while the stability of the closed-loop system is guaranteed. The transient performance of the resulting adaptive system is analytically quantified, and an example is given to show the effectiveness of the scheme.