Adaptive output feedback control of a class of multi-input multi-output systems using neural networks

For a class of uncertain multi-input multi-output non-linear systems an adaptive output feedback control methodology is developed using linearly parameterized neural networks. The neural network operates over a tapped delay line of memory units, comprised of system input/output signals. The adaptive laws for neural network parameters are written in terms of a linear observer of the nominal system's error dynamics. Ultimate boundedness of the error signals is shown through Lyapunov's direct method. Simulations illustrate the theoretical results.