Neural networks as direct adaptive controllers

Abstract

A learning scheme for multilayer feedforward neural networks used as direct adaptive controllers of nonlinear plants is suggested. This scheme is a supervised steepest descent one that does not require backpropagation of the error. Using a neural network controller trained with this method does not require the identification stage and this makes it superior to the other methodologies. Methods of using neural networks for plant control suggested in the literature are discussed and compared with the proposed system. Simulations based on model reference control of nonlinear plants show satisfactory performance.