Nonparametric identification of a particular nonlinear time series system

Author

Greblicki, W. ; Pawlak, M.

Author_Institution

Inst. of Eng. Cybern., Tech. Univ. of Wroclaw, Poland

Volume

40

Issue

4

fYear

1992

fDate

4/1/1992 12:00:00 AM

Firstpage

985

Lastpage

989

Abstract

A nonlinear time series system is identified. The system has a cascade structure, that is, it consists of a nonlinear memoryless element followed by a dynamic linear system. Given a Gaussian input, a Hermite series based method for recovering the system nonlinearity is presented. The proposed identification procedure is nonparametric since it is able to be consistent for a broad class of nonpolynomial characteristics. The consistency and rate of convergence of the procedure are established. Also, some data-driven methods for selecting the optimal number of terms in the procedure are proposed. The results are illustrated by a numerical example

Keywords

identification; nonlinear systems; time series; Gaussian input; Hermite series; convergence rate; data-driven methods; dynamic linear system; nonlinear memoryless element; nonlinear time series system; nonparametric identification; nonpolynomial characteristics; Analytical models; Circuit noise; Circuit theory; Digital filters; Emulation; Frequency; Low pass filters; Notice of Violation; Sensitivity analysis; Transfer functions;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.127973

Filename

127973