A deep learning method on remaining useful life estimation based on linear regression model and greed matching strategy

Guliang Li; Qiujuan Huang; Yongfang Mao; Yi Chai

doi:10.1117/12.2624063

6 February 2022 A deep learning method on remaining useful life estimation based on linear regression model and greed matching strategy

Guliang Li, Qiujuan Huang, Yongfang Mao, Yi Chai

Author Affiliations +

Proceedings Volume 12081, Sixth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2021); 120813V (2022) https://doi.org/10.1117/12.2624063
Event: Sixth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2021), 2021, Chongqing, China

Abstract

Remaining useful life (RUL) estimation is critical to facilities under poor working conditions to prevent major safety accidents. In this article, we propose a data-driven scheme adopting a gated neural network, similarity-metric curve matching technique and the greed matching strategy to predict the RUL of facilities. The gated neural network transforms the multi-dimensional sensor readings to low-dimensional embedding, which are used to describe health degradation followed by linear regression to get the health index (HI). The online step is to match the test HI curves to the trained HI curves using the similarity-metric HI curve matching technique, which calculates the best match between the test HI curve and the training HI curves, and the greed matching strategy. The greed strategy contributes to limiting the scope of searching the time tag, which determines whether the two curves (one test HI curve and one training HI curve) match well or not by the similarity-metric HI curve matching technique. The proposed approach was test on the turbofan engine dataset #1 and comparison results show good performance compared to other existing approaches.

Citation Download Citation

Guliang Li, Qiujuan Huang, Yongfang Mao, and Yi Chai "A deep learning method on remaining useful life estimation based on linear regression model and greed matching strategy", Proc. SPIE 12081, Sixth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2021), 120813V (6 February 2022); https://doi.org/10.1117/12.2624063

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
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Sensors

Neural networks

Data modeling

Lawrencium

Distributed interactive simulations

Performance modeling

Stochastic processes

Show All Keywords

Keywords/Phrases

Search In:

Publication Years