DocumentCode :
34952
Title :
Sparse-Grid Quadrature $H_infty $ Filter for Discrete-Time Systems with Uncertain Noise Statistics
Author :
Bin Jia ; Ming Xin
Author_Institution :
Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Volume :
49
Issue :
3
fYear :
2013
fDate :
Jul-13
Firstpage :
1626
Lastpage :
1636
Abstract :
In This paper H technique is combined with the recently developed sparse-grid quadrature (SGQ) filtering to improve the accuracy and robustness of the state estimation when the noise statistics is not known a priori. The proposed new SGQ H filter (SGQHF) is compared with other H filters via two numerical examples. It is shown that the SGQHF is more robust and accurate than the extended H filter, unscented H filter, and cubature H filter. In addition it maintains a close performance to the Gauss-Hermite quadrature (GHQ) H filter but is computationally much more efficient since it uses far fewer quadrature points.
Keywords :
H filters; statistical analysis; GHQ H filter; Gauss-Hermite quadrature H filter; SGQH∞F; cubature H∞ filter; discrete-time systems; noise statistics; quadrature points; sparse-grid quadrature H filter; uncertain noise statistics; unscented H∞ filter; Accuracy; Approximation methods; Filtering algorithms; Filtering theory; Noise; Robustness;
fLanguage :
English
Journal_Title :
Aerospace and Electronic Systems, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9251
Type :
jour
DOI :
10.1109/TAES.2013.6558008
Filename :
6558008
Link To Document :
بازگشت