Adaptive Regulator Using Neural Network

Abstract

This paper proposes an adaptive regulator using a neural network. For a class of systems with linear and nonlinear modeling errors, the conventional optimal regulator is designed based on a known linear part of the controlled system, and the modeling errors included in the controlled system are identified using the neural network. At the same time, the neural network adaptively compensates a control input computed by the predesigned optimal regulator. The proposed regulator is applied to systems with linear and nonlinear modeling errors and simulation experiments are carried out. Results of the computer simulations show the effectiveness of the proposed method.