Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/12320
Title: | Robust filtering for a class of nonlinear stochastic systems with probability constraints |
Authors: | Ma, L Wang, Z Lam, HK Alsaadi, FE Liu, X |
Keywords: | Probability constraint;Time-varying systems;Measurements degradation;Stochastic nonlinearity;Parameter uncertainty |
Issue Date: | 2016 |
Publisher: | Pleiades Publishing |
Citation: | Automation and Remote Control, 77(1): pp. 37 - 54, (2016) |
Abstract: | This paper is concerned with the probability-constrained filtering problem for a class of time-varying nonlinear stochastic systems with estimation error variance constraint. The stochastic nonlinearity considered is quite general that is capable of describing several well-studied stochastic nonlinear systems. The second-order statistics of the noise sequence are unknown but belong to certain known convex set. The purpose of this paper is to design a filter guaranteeing a minimized upper-bound on the estimation error variance. The existence condition for the desired filter is established, in terms of the feasibility of a set of difference Riccati-like equations, which can be solved forward in time. Then, under the probability constraints, a minimax estimation problem is proposed for determining the suboptimal filter structure that minimizes the worst-case performance on the estimation error variance with respect to the uncertain second-order statistics. Finally, a numerical example is presented to show the effectiveness and applicability of the proposed method. |
URI: | http://link.springer.com/article/10.1134%2FS0005117916010033 http://bura.brunel.ac.uk/handle/2438/12320 |
DOI: | http://dx.doi.org/10.1134/S0005117916010033 |
ISSN: | 0005-1179 |
Appears in Collections: | Dept of Computer Science Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Fulltext.pdf | 207.39 kB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.