e-RULENet: remaining useful life estimation with end-to-end learning from long run-to-failure data

Abstract

This paper presents the e-RULENet, which is a novel framework to train a data-driven model for remaining useful life estimation from long run-to-failure data with an end-to-end manner. In order to enable end-to-end learning, a change point from the healthy stage to the degradation stage is estimated for each instance from measurements. The change point estimation in the previous framework is computationally expensive since it utilizes entire measurements over the lifetime for each instance. The e-RULENet solves this issue with estimating the change points with segments sampled from run-to-failure data. It is evaluated on three datasets for RUL estimation including two real-world datasets, and on a dataset for tension estimation as another use case. It outperforms an approach without end-to-end learning on all the three datasets. The results indicates that the e-RULENet works not only for cases with multiple health stages but also for a single degradation stage, which does not have any changes points.

Keywords:

• Remaining useful life estimation
• predictive maintenance
• deep learning
• sequential model
• end-to-end learning

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Masanao Natsumeda

Masanao Natsumeda received the B.Eng. degree in electronic engineering from the Univerity of Electro-Communications, Chofu, Tokyo, Japan in 2006 and the M.Eng. degree in atom photonics from Tokyo Institute of Technology, Tokyo, Japan in 2008 and is working toward the Ph.D degree in prognostics and health management from the University of Tokyo, Tokyo, Japan.

He is a Lead Research Engineer with NEC Corporation, Japan. His research interests include machine learning, artificial intelligence, anomaly detection, fault diagnosis and prognostics.

Mr. Natsumeda was a recipient of Honorable Mention Award from Japan Institute of Invention and Innovation in 2022, and 69th Electrical Science and Technology Honorable Mention Award in 2021.