Adaptive output feedback control of nonlinear systems using neural networks (Q5943839)

This paper deals with single-input/single-output nonlinear systems with known ouput, but with arbitrary relative degree. A direct adaptive output feedback is designed which employs feedback linearization, coupled with on-line neural networks to compensate for modeling errors. Then a fixed structure dynamic compensator is constructed to stabilize the linearized system. Lyapunov stability analysis is used to construct the neural network adaptation law. A numerical example of a van der Pol oscillator coupled to a linear oscillator is given to show the robustness of the design approach.