Rolling bearing fault diagnosis method based on attention mechanism and CNN-BiLSTM

Xianghui Liao; Yuhan Mao

doi:10.1117/12.2679407

18 July 2023 Rolling bearing fault diagnosis method based on attention mechanism and CNN-BiLSTM

Xianghui Liao, Yuhan Mao

Proceedings Volume 12722, Third International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023); 127223N (2023) https://doi.org/10.1117/12.2679407
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023), 2023, Hangzhou, China

Abstract

For various bearing states, the traditonal model has insufficient ability to extract important information, low accuracy and poor generalization ability of the model in complex environment.Therefore, a bearing fault diagnosis method based on CNN-BiLSTM-Attention is proposed. This method combines convolutional neural network (CNN) and bidirectional long and short term memory network (BiLSTM), adds the Dropout mechanism to the BiLSTM network to suppress the overfitting problem, then introduces the attention mechanism to automatically assign different weights to the BiLSTM network to improve the sensitivity and the ability to grasp different fault information. In order to verify the effect of this model, the Case Western Reserve University(CWRU) bearing fault dataset was used for experimental verification, the results show that the proposed model has higher accuracy and stronger generalization ability than other models in the multitask problem under complex working conditions.

Citation Download Citation

Xianghui Liao and Yuhan Mao "Rolling bearing fault diagnosis method based on attention mechanism and CNN-BiLSTM", Proc. SPIE 12722, Third International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023), 127223N (18 July 2023); https://doi.org/10.1117/12.2679407

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
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Feature extraction

Data modeling

Diagnostics

Education and training

Visual process modeling

Convolution

Neural networks

Show All Keywords

Keywords/Phrases

Search In:

Publication Years