DocumentCode :
84178
Title :
Expectation–Maximization Approach to Fault Diagnosis With Missing Data
Author :
Kangkang Zhang ; Gonzalez, R. ; Biao Huang ; Guoli Ji
Author_Institution :
Dept. of Autom., Xiamen Univ., Xiamen, China
Volume :
62
Issue :
2
fYear :
2015
fDate :
Feb. 2015
Firstpage :
1231
Lastpage :
1240
Abstract :
This paper introduces a data-driven approach for fault diagnosis in the presence of incomplete monitor data. The expectation-maximization (EM) algorithm is applied to handle missing data in order to obtain a maximum-likelihood solution for the discrete (or categorical) distribution. Because of the nature of categorical distributions, the maximization step of the EM algorithm is shown in this paper to have an easily calculated analytical solution, making this method computationally simple. An experimental study on a ball-and-tube system is investigated to demonstrate advantages of the proposed approach.
Keywords :
data handling; expectation-maximisation algorithm; fault diagnosis; EM algorithm; ball-and-tube system; categorical distribution; discrete distribution; expectation-maximization approach; fault diagnosis; incomplete monitoring data; missing data handling; Bayes methods; Data models; Integrated circuits; Monitoring; Sensors; Training data; Vectors; Data-driven approach; expectation???maximization (EM) algorithm; fault diagnosis; missing data;
fLanguage :
English
Journal_Title :
Industrial Electronics, IEEE Transactions on
Publisher :
ieee
ISSN :
0278-0046
Type :
jour
DOI :
10.1109/TIE.2014.2336635
Filename :
6850032
Link To Document :
بازگشت