STOCHASTIC SUBSPACE IDENTIFICATION GUARANTEEING STABILITY AND MINIMUM PHASE

Abstract

Listen

Translate article

This paper presents a stochastic subspace identification algorithm to compute stable, minimum phase models from a stationary time-series data. The algorithm is based on spectral factorization techniques and a stochastic subspace identification method via a block LQ decomposition (Tanaka and Katayama, 2003c). Two Riccati equations are solved to ensure both stability and minimum phase property of resulting Markov models.