System identification based on DNNs with disturbance observer and application to unmanned aerial vehicles

摘要: In this paper, dynamic neural networks (DNNs) are used as the on-line identifier for a class of nonlinear systems with unknown external disturbance and multiple dead zone actuators. By integrating novel observer adaptive control algorithms, parameter coupling problem between DNNs can be successfully solved disturbances also rejected simultaneously. Both observation error identification proved to convergent zero. Furthermore, by combining numerical result an unmanned aerial vehicle (UAV) model, effectiveness theoretical algorithms fully verified.