Combined parametric-nonparametric identification of Hammerstein systems

Author

Hasiewicz, Zygmunt ; Mzyk, Grzegorz

Author_Institution

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

Volume

49

Issue

8

fYear

2004

Firstpage

1370

Lastpage

1375

Abstract

A novel, parametric-nonparametric, methodology for Hammerstein system identification is proposed. Assuming random input and correlated output noise, the parameters of a nonlinear static characteristic and finite impulse-response system dynamics are estimated separately, each in two stages. First, the inner signal is recovered by a nonparametric regression function estimation method (Stage 1) and then system parameters are solved independently by the least squares (Stage 2). Convergence properties of the scheme are established and rates of convergence are given.

Keywords

FIR filters; convergence; least squares approximations; nonlinear control systems; nonparametric statistics; parameter estimation; regression analysis; transient response; Hammerstein systems; combined parametric-nonparametric identification; convergence properties; finite impulse-response system dynamics; least squares method; nonlinear static characteristics; nonparametric regression function estimation method; Colored noise; Convergence; Finite impulse response filter; Independent component analysis; Least squares approximation; Nonlinear dynamical systems; Parameter estimation; Polynomials; Signal processing; System identification; Convergence analysis; least squares; nonparametric regression; parameter estimation;

fLanguage

English

Journal_Title

Automatic Control, IEEE Transactions on

Publisher

ieee

ISSN

0018-9286

Type

jour

DOI

10.1109/TAC.2004.832662

Filename

1323180