A novel AEDL network and its application in performance degradation assessment of rolling bearings

Zhigang Liu; Long Zhang; Chengyang Song

doi:10.1117/12.2611680

14 October 2021 A novel AEDL network and its application in performance degradation assessment of rolling bearings

Zhigang Liu, Long Zhang, Chengyang Song

Proceedings Volume 11930, International Conference on Mechanical Engineering, Measurement Control, and Instrumentation; 119302R (2021) https://doi.org/10.1117/12.2611680
Event: International Conference on Mechanical Engineering, Measurement Control, and Instrumentation (MEMCI 2021), 2021, Guangzhou, China

Abstract

Bearing is the most critical component in mechanical equipment, the performance degradation assessment (PDA) of bearing can improve the reliability of equipment. Research on the application of reconstruction-based neural network in PDA, this paper proposes AEDL neural network to assess bearing degradation. First, the time domain and frequency domain are used to extract the signals features. In AEDL neural network, auto-encoder and dictionary learning reconstruct the features. Finally, the reconstruction error is used as the degradation index to assessment bearing degradation. Particle Swarm Optimization (PSO) is to obtain the hyper-parameters of the model, and this paper proposes a new metric Mean- Square-Error-Ratio (MSER) to evaluate the effect of reconstruction. The bearing experimental results indicate the proposed method can track performance degradation effectively and detect incipient damage in time. This paper provides a potential tool for reconstruction-based PDA model research.

Citation Download Citation

Zhigang Liu, Long Zhang, and Chengyang Song "A novel AEDL network and its application in performance degradation assessment of rolling bearings", Proc. SPIE 11930, International Conference on Mechanical Engineering, Measurement Control, and Instrumentation, 119302R (14 October 2021); https://doi.org/10.1117/12.2611680

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
13 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Associative arrays

Neural networks

Personal digital assistants

Particle swarm optimization

Data modeling

Chemical species

Computer programming

Show All Keywords

Keywords/Phrases

Search In:

Publication Years