文献类型：会议论文

英文题名：Fault diagnosis of Marine diesel engine based on deep belief network

作者：Zhong, Guo-qiang[1];Wang, Huai-yu[1];Zhang, Kun-yang[1];Jia, Bao-zhu[2]

机构：[1]Dalian Maritime Univ, Marine Engn Coll, Dalian, Peoples R China;[2]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：marine diesel engine; fault diagnosis; deep belief network; correlation analysis

外文摘要：In order to improve the accuracy of intelligent fault diagnosis of Marine diesel engine, deep learning is introduced into the fault diagnosis of Marine diesel engine, and an intelligent fault diagnosis method of Marine diesel engine based on correlation analysis and Deep Belief Network (DBN) is proposed. In this method, the method of correlation analysis is used to reduce the attributes of samples and remove the features with low correlation. Then deep belief network is used to study the samples after dimension reduction and a fault diagnosis model of Marine diesel engine is established. Through analyzing the data obtained from experiments with a fault simulation model for Marine diesel engines built on AVL BOOST, the proposed method has higher fault identification accuracy and better generalization performance than BP Neural Network (BPNN) and Support Vector Machine (SVM). This method can be used for the fault diagnosis of Marine diesel engine.