Adaptive nonlinear systems identification via dynamic multilayer neural networks with two-time scales

Author

Zhi-Jun Fu ; Xie, W.F. ; Liu, Siyuan

Author_Institution

Coll. of Mech. Eng., Zhejiang Univ. of Technol., Hangzhou, China

fYear

2013

fDate

28-30 Aug. 2013

Firstpage

1012

Lastpage

1017

Abstract

This paper presents a novel adaptive identification method for nonlinear systems including the aspects of fast and slow phenomenon via dynamic multilayer neural networks with two-time scales. The Lyapunov function and singularly perturbed techniques are used to develop the learning procedure for the hidden layers and output layers of the dynamic neural networks model. Novel correction terms are proposed in the learning algorithm to guarantee bounded tracking errors and bounded weights. The effectiveness of the algorithm is illustrated via the simulation results on an electric induction motor.

Keywords

Lyapunov methods; adaptive systems; induction motors; learning (artificial intelligence); neurocontrollers; nonlinear control systems; nonlinear dynamical systems; singularly perturbed systems; Lyapunov function; adaptive nonlinear system identification; bounded tracking error; bounded weight; dynamic multilayer neural network; electric induction motor; hidden layer; learning algorithm; singularly perturbed technique; time scale; Adaptive systems; Induction motors; Lyapunov methods; Neural networks; Nonlinear dynamical systems; Stability analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Applications (CCA), 2013 IEEE International Conference on

Conference_Location

Hyderabad

ISSN

1085-1992

Type

conf

DOI

10.1109/CCA.2013.6662884

Filename

6662884