Neural net based MRAC for a class of nonlinear plants

A neural net based state feedback model reference adaptive control scheme is presented for a class of nonlinear plants. The proposed scheme employs a time varying pseudo-linear state feedback control, where the state feedback gain being generated from the output of artificial neural networks. The plant need not be in a feedback linearizable form. Both regulation and tracking control have been considered. Global stability of the scheme has been proved through Lyapunov theory. The extension of the scheme to MIMO plants is also included. Simulation studies have been conducted on an industrial robot to validate and illustrate the proposed method.