Fault identification of rotating machinery based on multiscale convolution and deep residual networks

Huihui Wang; Tianqi Fan; Sen Qiu; Long Liu

doi:10.1117/12.3014826

4 March 2024 Fault identification of rotating machinery based on multiscale convolution and deep residual networks

Huihui Wang, Tianqi Fan, Sen Qiu, Long Liu

Proceedings Volume 12981, Ninth International Symposium on Sensors, Mechatronics, and Automation System (ISSMAS 2023); 129813N (2024) https://doi.org/10.1117/12.3014826
Event: 9th International Symposium on Sensors, Mechatronics, and Automation (ISSMAS 2023), 2023, Nanjing, China

Abstract

Rotating machinery and equipment have a wide range of industrial applications, and it is important to perform intelligent fault detection during their operation. In order to fully capture the multi-scale features of mechanical fault data while solving the degradation problem of deep networks, we propose an intelligent fault detection model combining multi-scale convolution and deep residual networks. We validate it on four publicly available datasets, and the results demonstrate the excellent performance of the proposed method.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Huihui Wang, Tianqi Fan, Sen Qiu, and Long Liu "Fault identification of rotating machinery based on multiscale convolution and deep residual networks", Proc. SPIE 12981, Ninth International Symposium on Sensors, Mechatronics, and Automation System (ISSMAS 2023), 129813N (4 March 2024); https://doi.org/10.1117/12.3014826

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