High-fidelity digital twin modelling for predictive maintenance state-of-the-art

Liu, Yuhan, Liu, Ying ORCID: https://orcid.org/0000-0001-9319-5940, McCrory, John and Guo, Xiao 2024. High-fidelity digital twin modelling for predictive maintenance state-of-the-art. Presented at: The 51st International Conference on Computers and Industrial Engineering (CIE51), Sydney, Australia, 9-11 December 2024.

Preview

PDF - Accepted Post-Print Version Download (885kB) | Preview

Abstract

High-fidelity modelling techniques provide high-precision simulations required for the construction of digital twin (DT), facilitating high-level mapping of physical systems in virtual space. The integration of DT and high-fidelity modelling enables real-time monitoring, fault diagnosis, performance evaluation and optimization of physical entities. These techniques have been explored in different industrial sectors and on various topics in recent years, such as predictive maintenance (PdM). Existing literature on high-fidelity DT has extensively covered major aspects such as framework construction and applications, advances in applications in various fields, and integration with the Internet of Things (IoT) or machine learning (ML) technologies. However, there is limited research on how high-fidelity modelling methods interact with DT to aid and optimize PdM. To comprehensively analyze the state-ofthe- art of high-fidelity DT modelling in PdM, this paper focuses on how high-fidelity DT modelling facilitates three key PdM tasks: health indicator estimation, remaining useful life prediction and fault diagnosis. For each task, discussion will be subdivided into two parts: 1) high-fidelity modelling methods, and 2) the process of integrating these methods into DTdriven predictive analytics. The advantages of high-fidelity DT modelling brings to PdM are also summarized. Finally, challenges and opportunities for future research are discussed.

Item Type:	Conference or Workshop Item (Paper)
Status:	In Press
Schools:	Engineering
Date of First Compliant Deposit:	22 August 2024
Date of Acceptance:	13 August 2024
Last Modified:	03 Nov 2024 02:30
URI:	https://orca.cardiff.ac.uk/id/eprint/171548

Actions (repository staff only)

Edit Item