Application of Genetic Algorithms and Dempster-Shafer Fusion Theory in Fault Diagnosis of Diesel Engine

Abstract

The multiple evidence from different information sources of different importance are not equally important when they are combined in fault diagnosis of diesel engine. To calculate and adjust weighting coefficient of multiple evidence, the method of weighted evidence balance based on genetic algorithms is used. First it searches for the optimal weighting coefficients of different evidence using genetic algorithms, then balances the considered evidences according to the weighted average of all and the preferred evidence, and finally combine them. Thus it is guarantied that the balanced evidences won't change the weighted average of all and the preferred evidence. The experimental results demonstrate the excellent performance of the weighted evidence balance method to fault diagnosis of diesel engine as it enhance the confidence of correct judgment and advance the accuracy as compared with basic evidence theory method.