Consistency analysis of some closed-loop subspace identification methods

We study statistical consistency of two recently proposed subspace identification algorithms for closed-loop systems. These algorithms may be seen as implementations of an abstract state-space construction procedure described by the authors in previous work on stochastic realization of closed-loop systems. A detailed error analysis is undertaken which shows that both algorithms are biased due to an unavoidable mishandling of initial conditions which occurs in closed-loop identification. Instability of the open loop system may also be a cause of trouble.

[1]  C. W. J. Granger,et al.  Economic Processes Involving Feedback , 1963, Inf. Control..

[2]  Michel Gevers,et al.  On jointly stationary feedback-free stochastic processes , 1982 .

[3]  M. Gevers,et al.  Representations of jointly stationary stochastic feedback processes , 1981 .

[4]  Anders Lindquist,et al.  Canonical correlation analysis, approximate covariance extension, and identification of stationary time series , 1996, Autom..

[5]  Giorgio Picci,et al.  Oblique Splitting Subspaces and Stochastic Realization with Inputs , 1997 .

[6]  Giorgio Picci,et al.  A subspace identification of closed-loop system by orthogonal decomposition , 2001, Proceedings of the 40th IEEE Conference on Decision and Control (Cat. No.01CH37228).

[7]  B. Moor,et al.  Closed loop subspace system identification , 1997 .

[8]  B. Anderson,et al.  Optimal Filtering , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[9]  Petre Stoica,et al.  Decentralized Control , 2018, The Control Systems Handbook.

[10]  Magnus Jansson,et al.  Subspace Identification and ARX Modeling , 2003 .

[11]  Giorgio Picci,et al.  Subspace identification of closed loop systems by the orthogonal decomposition method , 2005, Autom..

[12]  Michel Verhaegen,et al.  Application of a subspace model identification technique to identify LTI systems operating in closed-loop , 1993, Autom..

[13]  E. Hannan,et al.  The statistical theory of linear systems , 1989 .

[14]  Tohru Katayama.  Subspace identification of closed-loop systems , 2002, Proceedings of the 41st SICE Annual Conference. SICE 2002..

[15]  Bart De Moor,et al.  Subspace algorithms for the stochastic identification problem, , 1993, Autom..

[16]  Giorgio Picci,et al.  Stochastic realization with exogenous inputs and 'subspace-methods' identification , 1996, Signal Process..

[17]  Giorgio Picci,et al.  GEOMETRIC METHODS FOR STATE SPACE IDENTIFICATION , 2005 .

[18]  Alessandro Chiuso,et al.  Numerical conditioning and asymptotic variance of subspace estimates , 2004, Autom..

[19]  E. J. Hannan,et al.  Unit canonical correlations between future and past , 1988 .

[20]  A. Chiuso,et al.  Geometry of Oblique Splitting, Minimality and Hankel Operators , 2003 .

[21]  Michel Verhaegen,et al.  Closed-loop identification using canonical correlation analysis , 1999, 1999 European Control Conference (ECC).

[22]  Dieter Prätzel-Wolters,et al.  Operators, Systems and Linear Algebra , 1997 .

[23]  Alessandro Chiuso,et al.  On the ill-conditioning of subspace identification with inputs , 2004, Autom..

[24]  Lennart Ljung,et al.  Subspace identification from closed loop data , 1996, Signal Process..

[25]  P. Van Overschee,et al.  Two subspace algorithms for the identification of combined deterministic-stochastic systems , 1992 .

[26]  A. C. van der Klauw,et al.  State space identification of closed loop systems , 1991, [1991] Proceedings of the 30th IEEE Conference on Decision and Control.

[27]  Giorgio Picci,et al.  Identification, Adaptation, Learning , 1996 .

[28]  P. Caines,et al.  Estimation, Identification and Feedback , 1976 .

[29]  Lennart Ljung,et al.  Closed-Loop Subspace Identification with Innovation Estimation , 2003 .

[30]  Bart De Moor,et al.  N4SID: Subspace algorithms for the identification of combined deterministic-stochastic systems , 1994, Autom..