×

Closed-loop subspace identification algorithm based on correlation function estimates. (English) Zbl 1331.93214

Summary: A novel subspace identification method based on correlation function which estimates a state-space system dynamics of unknown plant operating in closed-loop experimental condition is proposed in this paper. It is shown that the cross-correlation function of the output and external input signals are equal to the cross-correlation function of the input and external signals filtered through the system dynamics since noise signal has no correlation with the external input. The proposed algorithm is developed to obtain unbiased estimates of system matrices based on time-shifted invariance of the correlation function estimates. Later the algorithm is compared to other popular subspace methods in the simulation study and the results show the effectiveness of our method in the presence of colored noise and low signal-to-noise ratios.

MSC:

93E12 Identification in stochastic control theory
93E10 Estimation and detection in stochastic control theory
93E25 Computational methods in stochastic control (MSC2010)
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] Qin S J. An overview of subspace identification. Comput Chem Eng, 2006, 30: 1502-1513 · doi:10.1016/j.compchemeng.2006.05.045
[2] Cheng D Z. Advances in automation and control research in China. Sci China Ser-F: Inf Sci, 2009, 52: 1954-1963 · Zbl 1182.93002 · doi:10.1007/s11432-009-0198-2
[3] Katayama T, Tanakab H. An approach to closed-loop subspace identification by orthogonal decomposition. Automatica, 2007, 43: 1623-1630 · Zbl 1128.93316 · doi:10.1016/j.automatica.2007.02.011
[4] van Der Veen G, van Wingerden J W. Closed-loop subspace identification methods: an overview. IET Control Theory Appl, 2013, 7: 1339-1358 · doi:10.1049/iet-cta.2012.0653
[5] Houtzager I, van Wingerden J W, Verhaegen M. Recursive predictor-based subspace identification with application to the real-time closed-loop tracking of flutter. IEEE Trans Control Syst Technol, 2012, 20: 934-949 · doi:10.1109/TCST.2011.2157694
[6] Liu, T.; Shao, C.; Wang, X. Z., Consistency analysis of orthogonal projection based closed-loop subspace identification methods, 1428-1432 (2013)
[7] Chiuso A. On the asymptotic properties of closed-loop CCA-type subspace algorithms: equivalence results and role of the future horizon. IEEE Trans Automat Control, 2010, 55: 634-649 · Zbl 1368.93743 · doi:10.1109/TAC.2009.2039239
[8] Tóth R, Laurain V, Gilson M, et al. Instrumental variable scheme for closed-loop LPV model identification. Automatica, 2012, 48: 2314-2320 · Zbl 1258.93051 · doi:10.1016/j.automatica.2012.06.037
[9] Pintelon R, Schoukens J. System Identification: a Frequency Domain Approach. New York: John Wiley & Sons, 2004 · Zbl 1293.93221
[10] van Overschee P, de Moor B. Continuous-time frequency domain subspace system identification. Signal Process, 1996, 52: 179-194 · Zbl 0875.93560 · doi:10.1016/0165-1684(96)00052-7
[11] Ding F, Liu P X, Liu G. Multi-innovation least squares identification for system modelling. IEEE Trans Syst Man Cybern Part B-Cybern, 2010, 40: 767-778 · doi:10.1109/TSMCB.2009.2028871
[12] Ding F, Liu P X, Liu G. Gradient based and least-squares based iterative identification methods for OE and OEMA systems. Digit Signal Process, 2010, 20: 664-677 · doi:10.1016/j.dsp.2009.10.012
[13] Chiuso A. The role of vector autoregressive modeling in predictor-based subspace identification. Automatica, 2007, 43: 1034-1048 · Zbl 1282.93264 · doi:10.1016/j.automatica.2006.12.009
[14] Veen, G.; Wingerden, J. W.; Verhaegen, M., Closed-loop MOESP subspace model identification with parametrisable disturbances, 2813-1818 (2014)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.