A direct approach to closed-loop identification of Wiener models using subspace-based methods

Author

Zhao, Yong ; Westwick, David

Author_Institution

Dept. of Electr. & Comput. Eng., Calgary Univ., Alta., Canada

Volume

4

fYear

2003

fDate

4-6 June 2003

Firstpage

3585

Abstract

In this paper, we present a new way to identify the Wiener system, a series connection of a linear dynamic system followed by a static non-linearity, operating in closed-loop systems experiments. A variant of the MOESP (multivariable output-error state space) algorithm is developed to identify a state space model of the linear part of a Wiener system operating in closed-loop. The nonlinearity can then be fitted between the simulated output of the linear system and the measured output of the cascade.

Keywords

closed loop systems; control nonlinearities; identification; linear systems; nonlinear systems; state-space methods; stochastic systems; MOESP algorithm; Wiener system; cascade output; closed-loop identification; linear dynamic system; multivariable output-error state space; nonlinear system; static nonlinearity; subspace-based method; Colored noise; Instruments; Iterative algorithms; Iterative methods; Linear systems; Noise measurement; Nonlinear dynamical systems; Nonlinear systems; State-space methods; System identification;

fLanguage

English

Publisher

ieee

Conference_Titel

American Control Conference, 2003. Proceedings of the 2003

ISSN

0743-1619

Print_ISBN

0-7803-7896-2

Type

conf

DOI

10.1109/ACC.2003.1244106

Filename

1244106