Premium
Simplification techniques for EKF computations in fault diagnosis: Model decomposition
Author(s) -
Chang ChueiTin,
Hwang JungIng
Publication year - 1998
Publication title -
aiche journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.958
H-Index - 167
eISSN - 1547-5905
pISSN - 0001-1541
DOI - 10.1002/aic.690440617
Subject(s) - extended kalman filter , computation , fault (geology) , computer science , kalman filter , decomposition , filter (signal processing) , algorithm , process (computing) , identification (biology) , moving horizon estimation , invariant extended kalman filter , control theory (sociology) , artificial intelligence , botany , control (management) , seismology , computer vision , biology , operating system , geology , ecology
The extended Kalman filter (EKF) is one of the most popular model‐based techniques for fault detection and diagnosis. In this study, the suboptimal EKF technique is utilized to enhance computation efficiency without sacrificing diagnostic accuracy. In particular, three simple strategies are proposed to decompose the filter model according to the precedence order of the state/parameter estimation process. The computation load needed in fault identification can be reduced significantly by implementing all or part of these decomposed EKFs on‐line. Extensive simulation results are also presented to demonstrate the effectiveness of these proposed techniques.