A New Extension of Newton Algorithm for Nonlinear System Modelling Using RBF Neural Networks

Author

Long Zhang ; Kang Li ; Er-Wei Bai

Author_Institution

Sch. of Electron., Queen´s Univ. Belfast, Belfast, UK

Volume

58

Issue

11

fYear

2013

fDate

Nov. 2013

Firstpage

2929

Lastpage

2933

Abstract

Model performance and convergence rate are two key measures for assessing the methods used in nonlinear system identification using Radial Basis Function neural networks. A new extension of the Newton algorithm is proposed to further improve these two aspects by extending the results of recently proposed continuous forward algorithm (CFA) and hybrid forward algorithm (HFA). Computational complexity analysis confirms its efficiency, and numerical examples show that it converges faster and potentially outperforms CFA and HFA.

Keywords

Newton method; computational complexity; convergence; identification; neurocontrollers; nonlinear systems; radial basis function networks; CFA; HFA; Newton algorithm; RBF neural networks; computational complexity analysis; continuous forward algorithm; convergence rate; hybrid forward algorithm; model performance; nonlinear system identification; nonlinear system modelling; radial basis function neural networks; Adaptation models; Computational modeling; Convergence; Jacobian matrices; Nonlinear systems; Radial basis function networks; Convergence rate; Newton method; orthogonal least squares (OLS); radial basis function (RBF); sum squared errors;

fLanguage

English

Journal_Title

Automatic Control, IEEE Transactions on

Publisher

ieee

ISSN

0018-9286

Type

jour

DOI

10.1109/TAC.2013.2258782

Filename

6504726