Department of Applied Mathematics & Physics, Kyoto University

Technical Report 2000-005 (August 26, 2000)

A Comparison of Two Stochastic Subspace System Identification Methods
by Hidetoshi Kawauchi, Alessandro Chiuso, Tohru Katayama and Giorgio Picci

PostScript File

In this paper, we analyze two subspace identification methods. The one is an N4SID-like algorithm which performs poorly in certain conditions where the past input signal and future input spaces are nearly parallel. The other method, based on a preliminary orthogonal decomposition of output data space, is more robust and reliable than the first method in critical cases. Numerical results demonstrate a substantial improvement of performance in such a parallel case. Keywords: canonical correlation analysis, orthogonal decomposition, parallel case, LQ factorization