Open AccessFault diagnosis of rolling bearing based on empirical mode decomposition and convolutional recurrent neural network
Author(s) -
Mulin Huang,
Tingting Huang,
Yongxiang Zhao,
Wei Dai
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1043/4/042015
Subject(s) - hilbert–huang transform , bearing (navigation) , vibration , convolutional neural network , computer science , fault (geology) , classifier (uml) , recurrent neural network , failure mode and effects analysis , artificial neural network , artificial intelligence , pattern recognition (psychology) , structural engineering , engineering , white noise , acoustics , geology , telecommunications , physics , seismology
Bearing is more important in mechanical parts. Many failures of rotating machinery are caused by bearing failure. It is very important to diagnose the rolling bearing fault and help the mechanical products to find out the failure of parts in operation. It can avoid danger and improve efficiency. To research the problem of rolling bearing fault diagnosis under different loads, a method using vibration signals based on empirical mode decomposition (EMD) and convolutional recurrent neural network (CRNN) is proposed. First, the EMD is used to deal with the vibration signal for noise reduction. Then, CRNN is built as the rolling bearing fault diagnosis classifier using the envelope of EMD processing. The Case Western Reserve University data sets are used to validate the method. The result shows that the method fits well.