Hostname: page-component-77c78cf97d-d2fvj Total loading time: 0 Render date: 2026-04-25T18:21:47.949Z Has data issue: false hasContentIssue false
  • English
  • Français

Multivariable adaptive parameter and state estimators with convergence analysis

Published online by Cambridge University Press:  17 February 2009

J. B. Moore  and
G. Ledwich
J. B. Moore
Affiliation:
Electrical Engineering Department, University of Newcastle, Newcastle, N.S.W. 2308
G. Ledwich
Affiliation:
Electrical Engineering Department, University of Queensland, St Lucia, Qld 4067
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

The convergence properties of a very general class of adaptive recursive algorithms for the identification of discrete-time linear signal models are studied for the stochastic case using martingale convergence theorems. The class of algorithms specializes to a number of known output error algorithms (also called model reference adaptive schemes) and equation error schemes including extended (and standard) least squares schemes. They also specialize to novel adaptive Kalman filters, adaptive predictors and adaptive regulator algorithms. An algorithm is derived for identification of uniquely parameterized multivariable linear systems.

A passivity condition (positive real condition in the time invariant model case) emerges as the crucial condition ensuring convergence in the noise-free cases. The passivity condition and persistently exciting conditions on the noise and state estimates are then shown to guarantee almost sure convergence results for the more general adaptive schemes.

Of significance is that, apart from the stability assumptions inherent in the passivity condition, there are no stability assumptions required as in an alternative theory using convergence of ordinary differential equations.

Information

Type
Research Article
Information
The ANZIAM Journal , Volume 21 , Issue 2 , August 1979 , pp. 176 - 197
Copyright
Copyright © Australian Mathematical Society 1979

References

[1]Astrom, K. J. and Eykhoff, P., “System identification—a survey”, Automatica 7 (1971), 123–162.CrossRefGoogle Scholar
[2]Saridis, G. N., “Stochastic approximation methods for identification and control”, IEEE Trans. Auto. Control AC-19 (1974), 798–809.CrossRefGoogle Scholar
[3]Kudva, P. and Narendra, K. S., “An identification procedure for discrete multivariable systems”, IEEE Trans. Auto. Control AC-19 (1974), 549–552.CrossRefGoogle Scholar
[4]Kudva, P. and Narendra, K. S., “The discrete adaptive observer”, Proc. of Decision and Control Conference (1974), 307–312.CrossRefGoogle Scholar
[5]Landau, I. D., “Unbiased recursive identification using model reference adaptive techniques”, IEEE Trans. Auto. Control AC-21 (1976), 194–203. Also an addendum submitted for publication.CrossRefGoogle Scholar
[6]Anderson, B. D. O., “An approach to multivariable identification”, Automatica 13 (1977), 401–408.CrossRefGoogle Scholar
[7]Clarke, D. W., “Generalized least squares estimation of the parameters of a dynamic model”, 1st IFAC Symposium on Identification in Automatic Control Systems (Prague, 1967).Google Scholar
[8]Soderstrom, T., “Convergence properties of the generalized least squares identification method”, Automatica 10 (1974), 617–626.CrossRefGoogle Scholar
[9]Finigan, B. M. and Rowe, I. H., “Strongly consistent parameter estimation by the introduction of strong instrumental variables”, IEEE Trans. Auto. Control AC-19 (1974), 825–831.CrossRefGoogle Scholar
[10]Young, P. D., “An instrumental variable method for real-time identification of a noisy process”, Automatica 6, 271–287.CrossRefGoogle Scholar
[11]Ledwich, G. and Moore, J. B., “Multivariable self-tuning filters”, Differential Games and Control Theory II, (Lecture notes in pure and applied mathematics, Dekker, 1977), pp. 345–376.Google Scholar
[12]Ljung, L., “Analysis of recursive, stochastic algorithms”, IEEE Trans. Auto. Control AC-22 (1977), 551–575.CrossRefGoogle Scholar
[13]Ljung, L., “On positive real transfer function and the convergence of some recursive schemes”, IEEE Trans. Auto Control AC-22 (1977), 539–551.CrossRefGoogle Scholar
[14]Ljung, L., “Convergence of an adaptive filter algorithm”, International Control 27 (1978), 673–694.CrossRefGoogle Scholar
[15] (a)Moore, J. B., Clark, Martin C. and Anderson, B. D. O., “On martingales and least squares linear system identification”, IFAC Symposium of Identification and System Parameter Estimation (USSR, 1976).Google Scholar
(b) Also Moore, J. B., “On strong consistency of least squares identification algorithms”, Automatica 14 (1978), 505–509.CrossRefGoogle Scholar
[16]Anderson, B. D. O. and Moore, J. B., Linear optimal control (Prentice-Hall, Englewood Cliffs, N.J., 1970).Google Scholar
[17]Desoer, C. and Vidyasaga, M., Feedback systems: input–output properties (Academic Press, New York, 1975).Google Scholar
[18]Doob, J. L., Stochastic processes (John Wiley and Sons, New York, 1953).Google Scholar
[19]Wittenmark, B., “A self-tuning predictor”, IEEE Trans. Auto. Control AC-19 (1974), 848–851.CrossRefGoogle Scholar
[20]Goodwin, G. C. and Payne, R. L., Dynamic System identification (Academic Press, New York, 1977).Google Scholar