Multisensor fault diagnosis via Markov chain and Evidence theory

In multi-sensor fusion, the Dempster-Shafer theory is frequently used for fault diagnosis and other decisionmaking problems. However, if the information collected from various sensors exhibits uncertainty and high conflict, the classical Dempster's Combination Rule may produce a counter-intuitive result. Various studies were conducted by Ghosh and other scholars to solve this problem, and good results were achieved. This work provides a novel idea which uses the Markov chain to model the uncertainty information in evidence theory, explore the ordered rules in random evidence, and then obtain the evidence support degree, thereby reducing the effect of high-conflict evidence. Considering the information amount of evidence combined with the evidence support degree, the final credibility of evidence is obtained, and the weighted summation is used to obtain new evidence. Finally, the classical Dempster combination rule is used to process new evidence and make the final decision. Through numerical examples and case studies, the proposed method's superior efficiency and robustness over the existing multisensor fault diagnosis methods are illustrated.

Automated summary

In multi-sensor fusion, the classical Dempster's Combination Rule may produce counter-intuitive results when handling uncertain and conflicting information. To address this issue, Ghosh and other scholars proposed a novel approach that utilizes Markov chain and ordered rules to model uncertainty in evidence theory, thereby reducing the effect of high-conflict evidence. By considering both the information amount and evidence support degree, the proposed method obtains the final credibility of evidence and uses weighted summation to combine new evidence. Numerical examples and case studies demonstrate the superior efficiency and robustness of the proposed method compared to existing multisensor fault diagnosis methods.