Subspace identification of Hammerstein systems using least squares support vector machines

Author

Goethals, Ivan ; Pelckmans, Kristiaan ; Suykens, Johan A K ; De Moor, Bart

Author_Institution

Dept. of Electr. Eng. ESAT-SCD, Katholieke Univ. Leuven, Belgium

Volume

50

Issue

10

fYear

2005

Firstpage

1509

Lastpage

1519

Abstract

This paper presents a method for the identification of multiple-input-multiple-output (MIMO) Hammerstein systems for the goal of prediction. The method extends the numerical algorithms for subspace state space system identification (N4SID), mainly by rewriting the oblique projection in the N4SID algorithm as a set of componentwise least squares support vector machines (LS-SVMs) regression problems. The linear model and static nonlinearities follow from a low-rank approximation of a matrix obtained from this regression problem.

Keywords

MIMO systems; control nonlinearities; identification; least squares approximations; linear systems; regression analysis; state-space methods; support vector machines; Hammerstein system; N4SID; least squares support vector machines; linear model; multiple input multiple output system; numerical algorithms; regression problem; static nonlinearities; subspace state space identification; Biological processes; Biological system modeling; Least squares approximation; Least squares methods; MIMO; Nonlinear systems; Signal processing algorithms; State-space methods; Support vector machines; System identification; Hammerstein models; least squares support vector machines; subspace identification;

fLanguage

English

Journal_Title

Automatic Control, IEEE Transactions on

Publisher

ieee

ISSN

0018-9286

Type

jour

DOI

10.1109/TAC.2005.856647

Filename

1516254