Stochastic subspace identification via "LQ decomposition"

Author

Tanaka, Hideyuki ; Katayama, Tohru

Author_Institution

Dept. of Appl. Math. & Phys., Kyoto Univ., Japan

Volume

4

fYear

2003

fDate

9-12 Dec. 2003

Firstpage

3467

Abstract

A new stochastic subspace identification algorithm is developed with the help of a stochastic realization on a finite interval. First, a finite-interval realization algorithm is re-derived via "block-LDL decomposition" for a finite string of complete covariance sequence. Next, a stochastic sub-space identification method is derived by adapting the finite-interval realization algorithm to incomplete covariance matrices defined by a finite time-series data. The proposed sub-space identification method always works, and computes a stochastic model from the "block-LQ decomposition" without solving any Riccati equations.

Keywords

Hankel matrices; Hilbert spaces; Riccati equations; covariance matrices; identification; matrix decomposition; stochastic processes; time series; Hankel matrices; Hilbert spaces; Riccati equations; block LDL decomposition; block LQ decomposition; covariance matrices; covariance sequence; finite interval realization algorithm; finite string; finite time series data; linear quadratic decomposition; stochastic realization; stochastic subspace identification algorithm; Covariance matrix; Hilbert space; Informatics; Mathematics; Physics; Riccati equations; Singular value decomposition; State-space methods; Stochastic processes; Stochastic systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 2003. Proceedings. 42nd IEEE Conference on

ISSN

0191-2216

Print_ISBN

0-7803-7924-1

Type

conf

DOI

10.1109/CDC.2003.1271683

Filename

1271683