A methodology to develop and manage data-driven models for marine engine long-term health prognosis
ISA Transactions · 2026-08 · 175 · 3-15
DOI: 10.1016/j.isatra.2025.09.030 ↗Kurz gefasst
Fachartikel in der Zeitschrift ISA Transactions, 2026-08. Verfasst von Jaehan Jeon und 1 weiteren Autor:innen. Beteiligte Einrichtung: Maritime Safety Research Centre, Department of Naval Architecture, Ocean, and Marine Engineering, University of Strathclyde, Glasgow, G4 0LZ, United …. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Horizon 2020.
Abstract (Originalsprache)
This study proposes a novel methodology to develop and manage data-driven models for ship machinery Prognostics and Health Management (PHM). A four-stroke marine engine is investigated considering exhaust valve wear degradation. Simulated datasets are generated using a physics-based digital twin integrated with stochastic degradation models. Health indicators (HI) construction and forecast sub-models are developed, based on Multi-Layer Perceptron and Bayesian Neural Networks, respectively. Data-driven model management employs error and uncertainty metrics for deciding re-training of HI forecast sub-models, resulting in R2 increases from 0.24 to 0.89 and from 0.26 to 0.94 in Cases 1 and 2, respectively. This is the first study that integrates thermodynamic models with stochastic degradation models to develop marine engine digital twins, while also introducing data-driven model management, thus contributing to the PHM system adoption by the maritime industry.
Autor:innen und Institutionen
- Maritime Safety Research Centre, Department of Naval Architecture, Ocean, and Marine Engineering, University of Strathclyde, Glasgow, G4 0LZ, United Kingdom. Electronic address: jaehan.jeon@strath.ac.uk.
- Maritime Safety Research Centre, Department of Naval Architecture, Ocean, and Marine Engineering, University of Strathclyde, Glasgow, G4 0LZ, United Kingdom. Electronic address: gerasimos.theotokatos@strath.ac.uk.
Förderung
- Horizon 2020
Zitieren
APA
Jeon, J., & Theotokatos, G. (2026). A methodology to develop and manage data-driven models for marine engine long-term health prognosis. ISA Transactions, 175, 3-15. https://doi.org/10.1016/j.isatra.2025.09.030
Vancouver
Jeon J, Theotokatos G. A methodology to develop and manage data-driven models for marine engine long-term health prognosis. ISA Transactions. 2026;175:3-15. doi:10.1016/j.isatra.2025.09.030
BibTeX
@article{Jeon2026,
author = {Jeon, Jaehan and Theotokatos, Gerasimos},
title = {A methodology to develop and manage data-driven models for marine engine long-term health prognosis},
journal = {ISA Transactions},
year = {2026},
volume = {175},
pages = {3--15},
doi = {10.1016/j.isatra.2025.09.030}
}
EUVIMED