A modified neural network for dynamical system identification and control

Abstract

ABSTRAC This paper presents a new type of neural network in which the dynamical error feedback is used to modify the inputs of the network. A new identification model constructed by the proposed network and stable filters is used for continuous time nonlinear system identification, which can achieve the superior modeling performance over the standard feedforward networks. In addition, stable adaptive control scheme based on the proposed networks is developed. Several simulation results are provided to demonstrate the effectiveness of the proposed methods