AI-enhanced damage detection in jack-up rig legs using an improved modal strain energy index: A numerical, experimental, and digital twin-based approach
Green Technology & Innovation · 04.11.2025 · 1 · 1-10
DOI: 10.36922/gti025340014 ↗Kurz gefasst
Fachartikel in der Zeitschrift Green Technology & Innovation, online erschienen am 04.11.2025. Verfasst von James Riffat und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Jack-up rigs work in challenging marine environments where conditions such as cyclic loading, corrosion, and hydrodynamic forces can quickly cause structural damage. This deterioration not only affects the safety of the operation but also shortens the rig’s service life. To address these issues, this study proposes a new way to monitor the health of these structures using artificial intelligence (AI). The approach combines the improved modal strain energy (IMSE) index with machine learning to improve how damage in the legs of the rigs is detected. Unlike traditional methods that often rely on static thresholds to identify problems, the proposed system uses AI and digital twin technology to provide more flexible and timely diagnostics, which ultimately helps with better maintenance planning and safer operations. Validation was conducted through a combination of finite element modeling and experimental testing using a 1:22 scale laboratory prototype of the SA20 jack-up rig. The results show that the AI-driven IMSE method performs better than the traditional Stubbs Index, improving accuracy by 12.5%. It also outperforms the standard IMSE method, boosting damage detection by 8.7%. Remarkably, this approach can identify damage as small as 1%, with an average deviation of
Zitieren
APA
Riffat, J., Doudran, H. A., & Samaei, S. R. (2025). AI-enhanced damage detection in jack-up rig legs using an improved modal strain energy index: A numerical, experimental, and digital twin-based approach. Green Technology & Innovation, 1, 1-10. https://doi.org/10.36922/gti025340014
Vancouver
Riffat J, Doudran HA, Samaei SR. AI-enhanced damage detection in jack-up rig legs using an improved modal strain energy index: A numerical, experimental, and digital twin-based approach. Green Technology & Innovation. 2025;1:1-10. doi:10.36922/gti025340014
BibTeX
@article{Riffat2025,
author = {Riffat, James and Doudran, Hamed Ahadpour and Samaei, Seyed Reza},
title = {AI-enhanced damage detection in jack-up rig legs using an improved modal strain energy index: A numerical, experimental, and digital twin-based approach},
journal = {Green Technology & Innovation},
year = {2025},
volume = {1},
pages = {1--10},
doi = {10.36922/gti025340014}
}
EUVIMED