Journal
EXPERT SYSTEMS WITH APPLICATIONS
Volume 39, Issue 3, Pages 2524-2531Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2011.08.104
Keywords
Fault diagnosis; Evidence theory; Information fusion; Agent
Categories
Funding
- National Natural Science Foundation of China [70971035, 90718037, 70631003, 70801024]
- Ph.D. Programs Foundation of Ministry of Education of China [200803590007]
- China Scholarship Council
Ask authors/readers for more resources
Multi sensors fusion is a very important process for fault diagnosis system. Information obtained from multi sensors need to be fused because no single sensor can get all the information for fault diagnosis. Moreover, information from different sensors may be uncertainty, inaccuracy, or even conflicting. Evidence theory can be used for information fusion, which is regarded as an extension form of Bayesian reasoning, but it has a better fusion result by simple reasoning process using belief function without knowing the prior probability. All the information collected from multi sensors in the system can be described as the evidence for diagnosis so that the fault diagnosis problem can then be modeled as a problem of evidence fusion and decision. In this paper, the classical Dempster-Shafer evidence theory is discussed, and the disadvantages of the combination rule are also analyzed. The notion of support degree of focal element is suggested in order to evaluate the conflicts between multi sensors. The new combination rule is then built to allocate the conflicted information from multi sensors based on the support degree of focal element. Furthermore, the decision rules for fault diagnosis are also proposed, as well as the architecture of the agent oriented intelligent fault diagnosis system. Finally, a case study is given to illustrate the performance of the proposed model. (C) 2011 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available