Open AccessRecursive filtering for complex networks using non‐linearly coupled UKF
Author(s) -
Li Wenling,
Meng Cong,
Jia Yingmin,
Du Junping
Publication year - 2018
Publication title -
iet control theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.059
H-Index - 108
eISSN - 1751-8652
pISSN - 1751-8644
DOI - 10.1049/iet-cta.2017.0738
Subject(s) - control theory (sociology) , upper and lower bounds , kalman filter , coupling (piping) , filter (signal processing) , tracking (education) , mathematics , coupling strength , sigma , class (philosophy) , computer science , mathematical analysis , engineering , physics , statistics , artificial intelligence , control (management) , mechanical engineering , psychology , pedagogy , quantum mechanics , computer vision , condensed matter physics
This study is concerned with the recursive filtering problem for a class of discrete‐time complex networks with non‐linearly coupled terms. A coupled unscented Kalman filter (UKF) is developed, where the sigma points of the UKF are propagated by introducing the coupled terms. By using the stochastic analysis technique, a sufficient condition is established to guarantee the boundedness of the estimation errors, where an upper bound for the coupling strength is derived. It is shown that the upper bound of the coupling strength is inversely proportional to the number of nodes. A numerical example involving tracking of multiple interacting targets is provided to verify the effectiveness of the proposed filter.