Design and performance analysis of a direct adaptive controller for feedback linearizable systems

This paper presents a new direct adaptive controller based on multilayer neural networks for a class of feedback linearizable systems. The designed controller ensures that the system output tracking error converges to a small neighborhood of zero, while the stability of the closed-loop systems is guaranteed. In addition, the transient performance is analytically quantified by using the mean square error bound criterion and L/sub /spl infin// tracking error bound criterion.