DocumentCode :
3160267
Title :
Asymptotic Tracking for Uncertain Dynamic Systems via a Multilayer NN Feedforward and RISE Feedback Control Structure
Author :
Patre, P.M. ; MacKunis, W. ; Kaiser, K. ; Dixon, W.E.
Author_Institution :
Florida Univ., Gainesville
fYear :
2007
fDate :
9-13 July 2007
Firstpage :
5989
Lastpage :
5994
Abstract :
The use of a neural network (NN) as a feedforward control element to compensate for nonlinear system uncertainties has been investigated for over a decade. Typical NN-based controllers yield uniformly ultimately bounded (UUB) stability results due to residual functional reconstruction inaccuracies and an inability to compensate for some system disturbances. Several researchers have proposed discontinuous feedback controllers (e.g., variable structure or sliding mode controllers) to reject the residual errors and yield asymptotic results. The research in this paper describes how a recently developed continuous robust integral of the sign of the error (RISE) feedback term can be incorporated with a NN-based feedforward term to achieve semi-global asymptotic tracking. To achieve this result, the typical stability analysis for the RISE method is modified to enable the incorporation of the NN-based feedforward terms, and a projection algorithm is developed to guarantee bounded NN weight estimates.
Keywords :
asymptotic stability; feedback; multilayer perceptrons; neurocontrollers; nonlinear control systems; uncertain systems; RISE feedback control structure; asymptotic tracking; discontinuous feedback controllers; feedforward control; multilayer NN feedforward; neural network; nonlinear system uncertainties; projection algorithm; uncertain dynamic systems; uniformly ultimately bounded stability; Control systems; Feedback control; Feedforward neural networks; Multi-layer neural network; Neural networks; Nonhomogeneous media; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems; Sliding mode control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
American Control Conference, 2007. ACC '07
Conference_Location :
New York, NY
ISSN :
0743-1619
Print_ISBN :
1-4244-0988-8
Electronic_ISBN :
0743-1619
Type :
conf
DOI :
10.1109/ACC.2007.4282255
Filename :
4282255
Link To Document :
بازگشت