On the stability of a reduced-order filter based on dominant singular value decomposition of the system dynamics

被引:3
作者
Hoang, H. S. [1 ]
Baraille, R. [1 ]
Talagrand, O. [2 ]
机构
[1] SHOM LEGOS, F-31041 Toulouse, France
[2] LMD ENS, F-75231 Paris 05, France
关键词
Singular value decomposition; Unstable dynamics; Mean square stability; Observability; Detectability; MODEL-REDUCTION; DATA ASSIMILATION; ADAPTIVE FILTER;
D O I
10.1016/j.automatica.2009.06.032
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The stability of a reduced-order filter (ROF), the gain of which is constructed on the basis of a subspace of dominant singular vectors of the system dynamics, is examined. A definition of s-detectability is introduced. It is found that the observability of all unstable and neutral singular vectors (s-detectability) is a sufficient condition for the existence of a stable filter. (C) 2009 Elsevier Ltd. All rights reserved.
引用
收藏
页码:2400 / 2405
页数:6
相关论文
共 14 条