Robust discrete-time minimum-variance filtering

Author

Theodor, Yahali ; Shaked, Uri

Author_Institution

Fac. of Eng., Tel Aviv Univ., Israel

Volume

44

Issue

2

fYear

1996

fDate

2/1/1996 12:00:00 AM

Firstpage

181

Lastpage

189

Abstract

The bounded-variance filtered estimation of the state of an uncertain, linear, discrete-time system, with an unknown norm-bounded parameter matrix, is considered. An upper bound on the variance of the estimation error is found for all admissible systems, and estimators are derived that minimize the latter bound. We treat the finite-horizon, time-varying case and the infinite-time case, where the nominal system model is time invariant. In the special stationary case, where it is known that the uncertain system is time invariant, we provide a robust filter for all uncertainties that still keep the system asymptotically stable

Keywords

discrete time filters; error analysis; filtering theory; linear systems; matrix algebra; parameter estimation; time-varying systems; asymptotically stable system; bounded-variance filtered estimation; discrete-time minimum-variance filtering; discrete-time system; estimation error variance; finite-horizon; infinite-time; nominal system model; norm-bounded parameter matrix; stationary case; time invariant model; uncertain linear system; upper bound; Covariance matrix; Estimation error; Filtering; Nonlinear filters; Robustness; State estimation; Time varying systems; Uncertain systems; Uncertainty; Upper bound;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.485915

Filename

485915