文献类型：会议论文

英文题名：Research on fusion diagnosis method of thermal fault of Marine diesel engine

作者：Zhong, Guo-qiang[1];Wang, Huai-yu[1];Zheng, Shuai[2];Jia, Bao-zhu[3]

机构：[1]Dalian Maritime Univ, Marine Engn Coll, Dalian, Peoples R China;[2]Dalian Maritime Univ, Marine Elect Engn Coll, Dalian, Peoples R China;[3]Guangdong Ocean Univ, Maritime Coll, Zhanjiang, Peoples R China

会议论文集：Chinese Automation Congress (CAC)

会议日期：NOV 22-24, 2019

会议地点：Hangzhou, PEOPLES R CHINA

语种：英文

外文关键词：information fusion; fault diagnosis; marine diesel engine

外文摘要：In order to avoid the situation that the diagnosis model based on single sensor data is easily disturbed by environmental noise and the diagnosis accuracy is low, an intelligent fault fusion diagnosis method for marine diesel engine is proposed. Firstly, the support vector machine which is optimized by genetic algorithm is used to learn the fault sample data from different sensors, then multiple fault diagnosis models and results can be got. After that, multiple groups of diagnosis results are taken as evidence bodies and fused by evidence theory to obtain more accurate diagnosis results. By analyzing the sample data obtained from the fault simulation experiment of marine diesel engine based on AVL BOOST software, the proposed method can improve the fault diagnosis accuracy of marine diesel engine and reduce the uncertainty value of diagnosis results.