Can I read Extension of Minimum Variance Estimation for Systems with Unknown Inputs on EtoBox?

Extension of Minimum Variance Estimation for Systems with Unknown Inputs by M. Darouach; M. Zasadzinski; M. Boutayeb is a Engineering article available to read on EtoBox.

What is Extension of Minimum Variance Estimation for Systems with Unknown Inputs about?

In this paper, we address the problem of minimum variance estimation for discrete-time time-varying stochastic systems with unknown inputs. The objective is to construct an optimal ÿlter in the general case where the unknown inputs a ect both the stochastic model and the outputs. It extends the results of Darouach and Zasadzinski (Automatica 33 (1997) 717) where the unknown inputs are only present in the model. The main di culty in treating this problem lies in the fact that the estimation error is correlated with the systems noises, this fact leads generally to suboptimal ÿlters. Necessary and su cient conditions for the unbiasedness of this ÿlter are established. Then conditions under which the estimation error and the system noises are uncorrelated are presented, and an optimal estimator and a predictor ÿlters are derived. Su cient conditions for the existence of these ÿlters are given and su cient conditions for their stability are obtained for the time-invariant case. A numerical example is given in order to illustrate the proposed method.

Who reads Extension of Minimum Variance Estimation for Systems with Unknown Inputs?

Author

M. Darouach; M. Zasadzinski; M. Boutayeb

Publisher

Elsevier Science; Elsevier ; Elsevier Ltd.; Test accounts; Elsevier BV (ISSN 0005-1098)

Published

2003

Language

EN

Field

Engineering (Physical Sciences)