Adaptive output feedback control of nonlinear systems using neural networks

A direct adaptive output feedback control design procedure is developed for highly uncertain nonlinear systems, that does not rely on state estimation . The approach is also applicable to systems of unknown, but bounded dimens ion. In particular, we consider single-input/single-output nonlinear system s, whose output has known, but otherwise arbitrary relative degree. This in cludes systems with both parameter uncertainty and unmodeled dynamics. The result is achieved by extending the universal function approximation proper ty of linearly parameterized neural networks to model unknown system dynami cs from input/output data. The network weight adaptation rule is derived fr om Lyapunov stability analysis, and guarantees that the adapted weight erro rs and the tracking error are bounded. Numerical simulations of an output f eedback controlled van der Pol oscillator, coupled with a linear oscillator , is used to illustrate the practical potential of the theoretical results. (C) 2001 Elsevier Science Ltd. All rights reserved.