Edge-cloud collaborative multi-level fault diagnosis based on stacked sparse autoencoder

Shihu Zhao; Weixin Yang; Haining Liu; Fajia Li; Huanyong Cui; Xiaoguang Li

doi:10.1117/12.3030280

5 June 2024 Edge-cloud collaborative multi-level fault diagnosis based on stacked sparse autoencoder

Shihu Zhao, Weixin Yang, Haining Liu, Fajia Li, Huanyong Cui, Xiaoguang Li

Proceedings Volume 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024); 1316372 (2024) https://doi.org/10.1117/12.3030280
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 2024, Xi'an, China

Abstract

In industrial applications, detecting a fault in time is critical to ensure production safety. Edge-cloud collaborative condition monitoring provides a more flexible solution to achieve both computational efficiency and accuracy. In this paper, an Edge-cloud collaborative multi-level fault diagnosis model is developed based on stacked sparse autoencoder to minimize the fault detection time, meanwhile, the diagnostic accuracy can also be guaranteed. By filtering most of the normal data and less model inference time, the anomaly detection model on the edge can minimize the fault detection time. When a fault occurs, the fault data will be sent to the cloud to infer the fault details. The experimental results show that the proposed method can detect faults 0.12s earlier on average compared to edge-inferencing after cloud-trained method.

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

Citation Download Citation

Shihu Zhao, Weixin Yang, Haining Liu, Fajia Li, Huanyong Cui, and Xiaoguang Li "Edge-cloud collaborative multi-level fault diagnosis based on stacked sparse autoencoder", Proc. SPIE 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 1316372 (5 June 2024); https://doi.org/10.1117/12.3030280

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