Recursive Subspace Identification Based on Principal Component Analysis

Author

Yue-Ping Jiang ; Hai-Tao Fang

Author_Institution

Acad. of Math. & Syst. Sci., Chinese Acad. of Sci., Beijing, China

fYear

2006

fDate

7-11 Aug. 2006

Firstpage

444

Lastpage

449

Abstract

The problem of recursive subspace identification of state-space models is considered in this paper. A new recursive algorithm based on SA-PCA (stochastic approximation-principal component analysis) is proposed to estimate a basis of the extended observability matrix in the noise-free case. Besides, a recursive algorithm based on RLS (Recursive Least-Squares) is proposed to estimate the system matrices. The algorithm is evaluated by a simulation study.

Keywords

least squares approximations; matrix algebra; observability; principal component analysis; recursive estimation; state-space methods; stochastic processes; extended observability matrix; recursive algorithm; recursive least-squares; recursive subspace identification; state-space models; stochastic approximation-principal component analysis; system matrix estimation; Algorithm design and analysis; Least squares approximation; Mathematical model; Mathematics; Observability; Principal component analysis; Recursive estimation; Resonance light scattering; Stochastic resonance; Technological innovation; Principal component analysis; Recursive least squares; Recursive subspace identification; State-space models;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference, 2006. CCC 2006. Chinese

Conference_Location

Harbin

Print_ISBN

7-81077-802-1

Type

conf

DOI

10.1109/CHICC.2006.280591

Filename

4060554