EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Early Anomaly Detection in Maritime Refrigerated Containers Using a Hybrid Digital Twin and Deep Learning Framework

Marko Vukšić, Jasmin Ćelić, Dario Ogrizović, Ana Perić Hadžić

Applied Sciences · 13.02.2026 · 16 (4) · 1887

DOI: 10.3390/app16041887 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 13.02.2026. Verfasst von Marko Vukšić und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Rijeka.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Maritime refrigerated containers operate under harsh and highly variable conditions, where gradual equipment degradation can lead to temperature excursions, cargo losses, and operational disruptions. In current practice, monitoring relies largely on threshold-based temperature alarms, which are reactive and provide limited insight into early abnormal behaviour. This study proposes a hybrid framework for early anomaly detection in maritime refrigerated containers that combines a lightweight physics-based digital twin with a deep learning anomaly detector trained exclusively on fault-free operation. The approach is designed for shipboard constraints and uses only controller-level signals augmented by locally derived features, enabling low-complexity edge execution. The digital twin produces physically interpretable temperature residuals, while a convolutional autoencoder learns normal multivariate operating patterns and flags deviations via reconstruction error. Both indicators are integrated using conservative persistence gating to suppress short-lived transients typical of maritime operation. The framework is evaluated in a simulation environment calibrated to representative reefer thermal dynamics under variable ambient conditions and progressive fault injection across gradual and abrupt fault categories. Results indicate earlier and operationally credible detection compared to conventional alarms, supporting practical predictive maintenance in maritime cold-chain logistics.

Förderung

  • University of Rijeka

Zitieren

APA

Vukšić, M., Ćelić, J., Ogrizović, D., & Hadžić, A. P. (2026). Early Anomaly Detection in Maritime Refrigerated Containers Using a Hybrid Digital Twin and Deep Learning Framework. Applied Sciences, 16(4), 1887. https://doi.org/10.3390/app16041887

Vancouver

Vukšić M, Ćelić J, Ogrizović D, Hadžić AP. Early Anomaly Detection in Maritime Refrigerated Containers Using a Hybrid Digital Twin and Deep Learning Framework. Applied Sciences. 2026;16(4):1887. doi:10.3390/app16041887

BibTeX
@article{Vuki2026,
  author = {Vukšić, Marko and Ćelić, Jasmin and Ogrizović, Dario and Hadžić, Ana Perić},
  title = {Early Anomaly Detection in Maritime Refrigerated Containers Using a Hybrid Digital Twin and Deep Learning Framework},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {4},
  pages = {1887},
  doi = {10.3390/app16041887}
}
Kostenlos starten →