The combination method for dependent evidence and its application for simultaneous faults diagnosis

Abstract

This paper provides a method based on Dezert-Smarandache Theory (DSmT) for simultaneous faults diagnosis when evidence is dependent. Firstly, according to the characteristics of simultaneous faults, a frame of discernment is given for both single fault and simultaneous faults diagnosis, the DSmT combination rule applicable to simultaneous faults diagnosis is introduced. Secondly, the dependence of original evidence is classified according to three main factors in information acquisition and extraction, a method for evidence decorrelation is provided. On the other hand, the weights for measuring evidence credibility are given to modify independent evidence based on Generalized Ambiguity Measure. Next, DSmT combination rule is used to aggregate the modified evidence. Finally, an example of rotor faults diagnosis is given to illustrate effectiveness of the proposed method.