A fault diagnosis technique based on EMD and CNN-LSTM

Shua Shang; Zheng Guo; Zhijie Cao; Haibo Fan; Tao Liu

doi:10.1117/12.3009586

16 October 2023 A fault diagnosis technique based on EMD and CNN-LSTM

Shua Shang, Zheng Guo, Zhijie Cao, Haibo Fan, Tao Liu

Proceedings Volume 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023); 128033C (2023) https://doi.org/10.1117/12.3009586
Event: 2023 5th International Conference on Artificial Intelligence and Computer Science (AICS 2023), 2023, Wuhan, China

Abstract

On the backdrop of energy conservation and emission reduction, fault diagnosis is an important way to promote energy conservation and emission reduction. Traditional bearing fault diagnosis methods usually show a series of difficulties including difficulty in feature extraction, low robustness and multiple pre-processing steps. In allision to the issues above, a rolling bearing fault diagnosis technique is proposed in this paper taking CNN and EMD-LSTM as the foundation, which can automatically identify and process fault feature information. The original bearing vibration signals were reconstructed by EMD denoising and sliced into the CNN-LSTM model for classification and identification of rolling bearing fault types. The open dataset from CWRU was introduced. Compared with LSTM and CNN, the experimental results show that this diagnosis technique are better in classification. The accuracy of the model is up to 99.20% during the experiment.

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

Citation Download Citation

Shua Shang, Zheng Guo, Zhijie Cao, Haibo Fan, and Tao Liu "A fault diagnosis technique based on EMD and CNN-LSTM", Proc. SPIE 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023), 128033C (16 October 2023); https://doi.org/10.1117/12.3009586

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