Predictive maintenance of standalone steel industrial components powered by a dynamic reliability digital twin model with artificial intelligence

Diego D'Urso, Ferdinando Chiacchio, Salvatore Cavalieri, Salvatore Gambadoro and Soheyl Moheb Khodayee

Reliability Engineering and System Safety, 2024, vol. 243, issue C

Abstract: The increasing use of Artificial Intelligence algorithms underscores the importance of large datasets. Recent trends highlight the need for high-quality training data, especially in scenarios where data may be outdated or insufficient. This challenge is particularly evident in applications where sensors cannot be installed or data is limited, such as in the case of steel components widely used in various industries. To address this gap, model-based approaches show promise by using advanced Digital Twin systems to generate synthetic data, closer to the real working scenarios, for training Artificial Intelligence algorithms. This paper introduces a novel Dynamic Reliability Digital Twin to model cumulative fatigue damage in steel components based on Wöhler and Manson & Halford theory and on a Monte Carlo simulation, providing a dataset for training an AI predictor to estimate remaining useful life. The results demonstrate that machine learning algorithms yield favorable outcomes when the dataset is appropriately calibrated. Therefore, a thorough understanding of the underlying physics is essential to avoid potential bias in the machine learning results.

Keywords: Steel cumulative damage; Digital twin; Model-based maintenance; Data driven maintenance (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0951832023007731
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:243:y:2024:i:c:s0951832023007731

DOI: 10.1016/j.ress.2023.109859

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 ().