A weighted total least squares estimator for multivariable systems with nearly maximum likelihood properties

Author

Guillaume, P. ; Pintelon, R. ; Schoukens, J.

Author_Institution

Vrije Univ., Brussels, Belgium

Volume

1

fYear

1996

fDate

1996

Firstpage

282

Abstract

The aim of the present paper is to develop a parametric estimator for linear time-invariant multivariable systems with nearly maximum likelihood properties. The estimator is based on the total least squares (TLS) method. It can be seen as an “optimally” weighted iterative generalized total least squares (GTLS) estimator, combining the nice asymptotic properties of the maximum likelihood (ML) method with the global minimization property of the GTLS estimator. The main difference with, for instance, the IQML method and the method of Sanathanan and Koerner is that it generates consistent estimates in each iteration step

Keywords

control system analysis; least squares approximations; maximum likelihood estimation; minimisation; multivariable systems; parameter estimation; GTLS estimator; asymptotic properties; generalised total least squares method; global minimization; maximum likelihood method; multivariable systems; nearly maximum likelihood properties; parametric estimator; system identification; Electronic mail; Equations; Frequency domain analysis; Least squares approximation; Least squares methods; MIMO; Maximum likelihood estimation; Polynomials; Singular value decomposition; Yield estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 1996. IMTC-96. Conference Proceedings. Quality Measurements: The Indispensable Bridge between Theory and Reality., IEEE

Conference_Location

Brussels

Print_ISBN

0-7803-3312-8

Type

conf

DOI

10.1109/IMTC.1996.507393

Filename

507393