Multi-sensor information fusion method and its applications on fault detection of diesel engine
He Guo, Pan Xinglong, Zhang Chaojie, Ming Tingfeng, Jiufeng Qin · 2011
We proposed a method of multi-sensor information fusion based on Dempster-Shafer evidential theory for fault detection. At first, the basic probability assignment function (BPAF) is constructed based on probability statistics and fuzzy membership function. Then, the Dempster-Shafer evidential theory is applied to multi-sensor information fusion. Finally, the proposed method is applied to fault detection of a certain diesel engine. The experiment results indicate that the problem of multi-sensor information fusion in diesel engine fault detection is solved by using Dempster-Shafer evidential theory, and the uncertainty of single sensor information is avoided. The proposed methods are effective and the conclusions of fault detection are creditable.