A Modified Neural network for Dynamical System Identification and Control

摘要

This paper presents a ne 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 standardfeedforward networks. In addition, stable adaptive control scheme based on the proposed networks i developed. Several simulation results are provided to demonstrate the effctiveness of the proposed methods.