Multi-model ensemble deep learning method for intelligent fault diagnosis with high-dimensional samples

作     者：Xin ZHANG Tao HUANG Bo WU Youmin HU Shuai HUANG Quan ZHOU Xi ZHANG Xin ZHANG;Tao HUANG;Bo WU;Youmin HU;Shuai HUANG;Quan ZHOU;Xi ZHANG

作者机构：School of Mechanical Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China School of Mechanical and Electronic EngineeringWuhan University of TechnologyWuhan 430070China 

出 版 物：《Frontiers of Mechanical Engineering》 (机械工程前沿（英文版）)

年 卷 期：2021年第16卷第2期

页      面：340-352页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This study was financially supported by the National Key R&D Program of China(Grant No.2017YFD0400405) 

主　　题：fault intelligent diagnosis deep learning deep convolutional neural network high-dimensional samples 

摘      要：Deep learning has achieved much success in mechanical intelligent fault diagnosis in recent years. However, many deep learning methods cannot fully extract fault information to recognize mechanical health states when processing high-dimensional samples. Therefore, a multi-model ensemble deep learning method based on deep convolutional neural network (DCNN) is proposed in this study to accomplish fault recognition of high-dimensional samples. First, several 1D DCNN models with different activation functions are trained through dimension reduction learning to obtain different fault features from high-dimensional samples. Second, the obtained features are constructed into 2D images with multiple channels through a conversion method. The integrated 2D feature images can effectively represent the fault characteristic contained in raw high-dimension vibration signals. Lastly, a 2D DCNN model with multi-layer convolution and pooling is used to automatically learn features from the 2D images and identify the fault mode of the mechanical equipment by adopting a softmax classifier. The proposed method, which is validated using the bearing public dataset of Case Western Reserve University, USA and a one-stage reduction gearbox dataset, has high recognition accuracy. Compared with other classical deep learning methods, the proposed fault diagnosis method has considerable improvements.