A new bearing fault diagnosis method based on multi-scale CNN and LSTM

Haibin Sun; Yueguang Fan

doi:10.1117/12.3006762

26 September 2023 A new bearing fault diagnosis method based on multi-scale CNN and LSTM

Haibin Sun, Yueguang Fan

Proceedings Volume 12793, International Conference on Mechatronics and Intelligent Control (ICMIC 2023); 127931R (2023) https://doi.org/10.1117/12.3006762
Event: International Conference on Mechatronics and Intelligent Control (ICMIC2023), 2023, Wuhan, China

Abstract

Detection accuracy of bearing faults is crucial in saving economic loss for industrial applications. Various diagnostic methods proposed by researchers can produce highly accurate bearing fault diagnosis, but it is difficult to obtain accurate and effective diagnosis results under variable working conditions and noise conditions. Thus, A hybrid model M-SWCAL based on multi-scale convolutional neural network (CNN), artificial neural network (ANN) and long short-term memory (LSTM) neural network is proposed for fault diagnosis of rolling bearings. The model uses multiscale CNN to extract the frequency domain information of the vibration signal at different resolutions, and the multiscale structure can effectively enrich the number of feature information. After that, the features of different channels are fused into one long sequence by using splicing fusion. Then ANN is used to filter and sort out the noise and redundant information in the features, and finally LSTM is used to further learn the sequence characteristics in the new sequence. Experiments show that the model can generally achieve more than 99% diagnostic accuracy for different data sets, and the generalization performance and noise immunity of the model are completely better than other existing methods.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Haibin Sun and Yueguang Fan "A new bearing fault diagnosis method based on multi-scale CNN and LSTM", Proc. SPIE 12793, International Conference on Mechatronics and Intelligent Control (ICMIC 2023), 127931R (26 September 2023); https://doi.org/10.1117/12.3006762

ACCESS THE FULL ARTICLE

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
22 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Signal to noise ratio

Diagnostics

Performance modeling

Feature extraction

Education and training

Vibration

Show All Keywords

Keywords/Phrases

Search In:

Publication Years