Learning of physical health timestep using the LSTM network for remaining useful life estimation

Jinwoo Bae and Zhimin Xi

Reliability Engineering and System Safety, 2022, vol. 226, issue C

Abstract: Remaining useful life (RUL) estimation is a key task in prognostics and health management. Due to the complexity of engineering systems, data-driven methods for the RUL estimation have been widely applied and developed through machine learning and artificial intelligence techniques. To enhance performance of these methods, improving data quality is as much important as developing sophisticated algorithms. This paper proposes learning of physical health timestep (PHT) using the long short-term memory (LSTM) network to replace the labeled timestep (LT) of a test unit. While the LT mainly records the timestep as an operation or observation index of the unit, the PHT estimates the unit's physical health from available sensory measurements. With the PHT, RUL estimation can be more accurate considering the unit's loading history. Effectiveness of the proposed methodology has been verified through experiments on lithium-ion battery and C-MAPSS engine datasets.

Keywords: Prognostics and health management; Remaining useful life; Data quality; Physical health timestep; Long short-term memory neural network (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0951832022003416
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:reensy:v:226:y:2022:i:c:s0951832022003416

DOI: 10.1016/j.ress.2022.108717

Access Statistics for this article

Reliability Engineering and System Safety is currently edited by Carlos Guedes Soares

More articles in Reliability Engineering and System Safety from Elsevier
Bibliographic data for series maintained by Catherine Liu ().