CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12722 > Article
Paper
18 July 2023 Bearing fault diagnosis under variable working states based on transfer learning and deep learning
Xiao Teng, Bin Shi
Author Affiliations +
Proceedings Volume 12722, Third International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023); 127223K (2023) https://doi.org/10.1117/12.2679546
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023), 2023, Hangzhou, China
Abstract
Deep learning method is widely used in bearing fault diagnosis, but insufficient real working data and deviation of signal feature distribution often reduce the accuracy of fault diagnosis. To solve this problem, this paper proposed a diagnosis method combining transfer learning and convolutional neural network. The original vibration signal is transformed by wavelet to obtain the normalized time-frequency spectrum as the input of convolutional neural network model. Selecting a working state as the source domain to pre-train the network, and then make it applicable to other working states through transfer learning. The experimental results show that the new adaption network model can achieve a fault recognition rate over 99% for target task.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Xiao Teng and Bin Shi "Bearing fault diagnosis under variable working states based on transfer learning and deep learning", Proc. SPIE 12722, Third International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023), 127223K (18 July 2023); https://doi.org/10.1117/12.2679546
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 7 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Machine learning
Deep learning
Convolutional neural networks
Continuous wavelet transforms
Time-frequency analysis
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top