东南大学学报（英文版）2019，Vol.35Issue(3)：302-309,8.DOI:10.3969/j.issn.1003-7985.2019.03.005
基于随机森林和自编码的滚动轴承多视角特征融合
Multi-view feature fusion for rolling bearing fault diagnosis using random forest and autoencoder
摘要
Abstract
To improve the accuracy and robustness of rolling bearing fault diagnosis under complex conditions,a novel method based on multi-view feature fusion is proposed.Firstly,multi-view features from perspectives of the time domain,frequency domain and time-frequency domain are extracted through the Fourier transform,Hilbert transform and empirical mode decomposition (EMD).Then,the random forest model (RF) is applied to select features which are highly correlated with the bearing operating state.Subsequently,the selected features are fused via the autoencoder (AE) to further reduce the redundancy.Finally,the effectiveness of the fused features is evaluated by the support vector machine (SVM).The experimental results indicate that the proposed method based on the multi-view feature fusion can effectively reflect the difference in the state of the rolling bearing,and improve the accuracy of fault diagnosis.关键词
多视角特征/特征融合/故障诊断/滚动轴承/机器学习Key words
multi-view features/feature fusion/fault diagnosis/rolling bearing/machine learning分类
机械制造引用本文复制引用
孙文卿,邓艾东,邓敏强,朱静,翟怡萌,程强,刘洋..基于随机森林和自编码的滚动轴承多视角特征融合[J].东南大学学报（英文版）,2019,35(3):302-309,8.基金项目
The National Natural Science Foundation of China(No.51875100). （No.51875100）
