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

In this paper, a direct adaptive controller is developed based on multilaye r neural networks (MNNs) for a class of nonlinear systems. The proposed sch eme avoids the possible singularity problem of the controller usually met i n adaptive control design. The system tracking error is proven to converge to a small neighborhood of zero, while the stability of the closed-loop sys tem is guaranteed. The transient performance of the resulting adaptive syst em is analytically quantified, and an example is given to show the effectiv eness of the scheme. (C) 1999 Elsevier Science Ltd. Ail rights reserved.