Order estimation for linear time-invariant systems using frequency domain identification methods

Author

Rolain, Yves ; Schoukens, Johan ; Pintelon, Rik

Author_Institution

Dept. ELEC/TW, Vrije Univ., Brussels, Belgium

Volume

42

Issue

10

fYear

1997

fDate

10/1/1997 12:00:00 AM

Firstpage

1408

Lastpage

1417

Abstract

A two-step coarse-fine order estimation technique is proposed to determine the order of the numerator and the denominator polynomials of rational transfer function models for single-input/single-output (SISO) linear time-invariant systems. The coarse order estimation is based on rank detection by verification of the stochastic significance of the singular values of a linearized problem. The fine order estimation is based on a statistical analysis of the maximum likelihood cost function. The method is tested on measurements of low-(4 zeros, 6 poles) and high- (58 poles, 58 zeros) order systems

Keywords

frequency-domain analysis; maximum likelihood estimation; polynomials; transfer functions; SISO linear time-invariant systems; coarse order estimation; denominator polynomials; fine order estimation; frequency domain identification methods; linear time-invariant systems; linearized problem; maximum likelihood cost function; numerator polynomials; rank detection; rational transfer function models; singular values; statistical analysis; two-step coarse-fine order estimation; Cost function; Frequency estimation; Maximum likelihood detection; Maximum likelihood estimation; Poles and zeros; Polynomials; Statistical analysis; Stochastic processes; System testing; Transfer functions;

fLanguage

English

Journal_Title

Automatic Control, IEEE Transactions on

Publisher

ieee

ISSN

0018-9286

Type

jour

DOI

10.1109/9.633829

Filename

633829