A stochastic realization algorithm via block LQ decomposition in Hilbert space |
| |
Authors: | Hideyuki Tanaka [Author Vitae] Tohru Katayama [Author Vitae] |
| |
Affiliation: | Department of Applied Mathematics and Physics, Graduate School of Informatics, Kyoto University, Kyoto 606-8501, Japan |
| |
Abstract: | A stochastic realization problem of a stationary stochastic process is re-visited, and a new stochastically balanced realization algorithm is derived in a Hilbert space generated by second-order stationary processes. The present algorithm computes a stochastically balanced realization by means of the singular value decomposition of a weighted block Hankel matrix derived by a “block LQ decomposition”. Extension to a stochastic subspace identification method explains how the proposed abstract algorithm is implemented in system identification. |
| |
Keywords: | Stochastic realization Subspace identification Canonical correlation analysis Innovation representation Hilbert space LQ decomposition |
本文献已被 ScienceDirect 等数据库收录! |