The unified structure of unbiased minimum-variance reduced-order filters

Author

Hsieh, Chien-Shu

Author_Institution

Dept. of Electr. Eng., Ta Hwa Inst. of Technol., Hsinchu, Taiwan

Volume

5

fYear

2003

fDate

9-12 Dec. 2003

Firstpage

4871

Abstract

A unified two-stage functional filter (UTSFF) is proposed serving as a unified structure of unbiased minimum-variance reduced-order filters for linear time-varying discrete-time systems. The UTSFF includes two parts: one is for main reduced-order state estimate and the other is for the complementary signal, which is added to the former in order to reconstruct the true state estimate. It is shown in this paper that the main difference in various reduced-order filters lies in the prediction model of the complementary signal.

Keywords

Kalman filters; discrete time systems; linear systems; reduced order systems; state estimation; time-varying systems; complementary signal; linear time varying discrete time systems; prediction model; reduced order state estimation; unbiased minimum variance reduced order filters; unified structure; unified two stage functional filter; Computational complexity; Ear; Filtering; Kalman filters; Noise measurement; Nonlinear filters; State estimation; Stochastic systems; Time varying systems; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 2003. Proceedings. 42nd IEEE Conference on

ISSN

0191-2216

Print_ISBN

0-7803-7924-1

Type

conf

DOI

10.1109/CDC.2003.1272375

Filename

1272375