Neural-net-based direct adaptive control for a class of nonlinear plants

Abstract

A direct adaptive control algorithm is presented for a class of nonlinear plants. No restriction has been imposed on the plant structure. The only condition the plant must satisfy is that the instantaneous input-output gain be positive. An artificial neural network (ANN)-based nonlinear controller structure has been employed. In line with the gain scheduling principle, however, the controller also has a pseudolinear time-varying structure with the parameters being the functions of the operating point. Simulation studies are also presented to validate the theoretical findings.