» Download Article

Authors
Oku, Hiroshi

Identifier
10.3182/20090706-3-FR-2004.00163

Index Terms
Fault Detection and Diagnosis; Subspace Methods; Recursive Identification

Abstract
This paper presents an on-line change detection method that uses a recursive subspace model identification algorithm as a residual generator. In our method, a change in the variance of the residual is monitored by a statistical change detector based on the log-likelihood ratio test. An experiment using a real-life cart system as well as a numerical example demonstrates that the proposed method can detect changes in the dynamics of a system, without being disturbed by changes in the dynamics of an input signal which are not our concern.

References

M. Basseville, �gDetecting Changes in Signals and Systems
? A Survey,�h Automatica, 24(3), pp. 309-326, 1988.
M. Basseville, et al., �gSubspace-based fault detection algorithm
for vibration monitoring,�h Automatica, 36(1),
pp. 101-109, 2000.
M. Basseville and I. V. Nikiforov, Detection of Abrupt
Changes. Prentice Hall, New Jersey, 1993.
D. Bauer and M. Jansson, �gAnalysis of the asymptotic
properties of the MOESP type of subspace algorithms,�h
Automatica, 36(4), pp. 497-509, 2000.
F. Gustafsson, Adaptive Filtering and Change Detection.
John Wiley & Sons Ltd., Chichester, 2000.
E. J. Hannan and M. Deistler, The Statistical Theory of
Linear Systems. John Wiley & Sons, New York, 1988.
A. Ingimundarson, et al., �gModel-Based Detection of Hydrogen
Leaks in a Fuel Cell Stack,�h IEEE Trans. on
Control System Technology, 16(5), pp. 1004-1012, 2008.
M. Jansson and B. Wahlberg, �gA linear regression approach
to state-space subspace system identification,�h
Signal Processing, 52, pp. 103-129, 1996.
T. Katayama, Subspace Methods for System Identification,
Springer, London, 2005.
L. Ljung, System Identification, 2nd Ed. Prentice Hall,
New Jersey, 1999.
M. Lovera, et al., �hRecursive subspace identification of
linear and non-linear Wiener state-space models,�h Automatica,
36(11), pp. 1639-1650, 2000.
G. Merc`ere and M. Lovera, �gConvergence analysis of
instrumental variable recursive subspace identification
algorithms,�h Automatica, 43(8), pp. 1377-1386, 2007.
H. Oku, �gApplication of a recursive subspace identification
algorithm to change detection,�h in Proceedings of the
13th IFAC Symposium on System Identification, (Rotterdam,
The Netherlands), pp. 1399-1404, August 2003.
H. Oku, �gChange Detection Algorithm based on Recursive
Subspace Identification,�h Trans. of the Institute of
Systems, Control and Information Engineers, 17(11),
pp. 506-513, 2004. in Japanese.
H. Oku and H. Kimura, �gA recursive 4SID from the inputoutput
point of view,�h Asian J. Control, 1(4), pp. 258-
269, 1999.
H. Oku, G. Nijsse, M. Verhaegen, and V. Verdult, �gChange
detection in the dynamics with recursive subspace identification,�h
in Proceedings of the 40th IEEE CDC, (Orlando,
Florida), pp. 2297-2302, December 2001.
H. Oku and H. Kimura, �gRecursive 4SID algorithms using
gradient type subspace tracking,�h Automatica, 38(6),
pp. 1035-1043, 2002.
P. Van Overschee and B. De Moor, Subspace Identification
for Linear Systems. Kluwer Academic Publishers,
Massachusetts, 1996.
M. Verhaegen and E. Deprettere, �gA fast, recursive MIMO
state space model identification algorithm,�h in Proceedings
of the 30th IEEE CDC, (Brighton), pp. 1349-1354,
December 1991.
M. Verhaegen and V. Verdult, Filtering and System Identification,
Cambridge University Press, 2007.