A Small-Sample Transfer Learning Framework for Cross-Domain Ship Motion Prediction in Extreme Sea States
Journal of Marine Science and Engineering · 23.07.2026 · 14 (15) · 1353
DOI: 10.3390/jmse14151353 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 23.07.2026. Verfasst von Lingyi Hou und 4 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fund for Distinguished Young Scholars of Dalian Naval Academy, Development Fund of Dalian Naval Academy.
Abstract (Originalsprache)
Accurate ship motion prediction is important for navigation safety, onboard decision support, and shipborne digital twins. Yet data-driven models trained on one vessel often degrade when applied to different hull forms, speed regimes, and sea states. This study proposes a small-sample transfer learning method for cross-domain ship motion prediction in extreme sea states. A CEEMDAN–SSA–Informer model is pre-trained on sea-trial data from the displacement-type training ship Yu Kun and adapted to a high-speed V-shaped target vessel under SS5–SS6 conditions. Only a 15-min target-domain segment is used to update the final model parameters. The method combines maximum mean discrepancy-guided layer freezing, domain-adaptive modal attention, and a peak-aware loss to preserve transferable representations and improve extreme-response prediction. Under SS6, the roll PRE decreases from 48.7% with direct transfer to 8.2% after adaptation, corresponding to an 83.2% reduction and indicating substantially improved prediction accuracy over high-amplitude roll-response samples. Ablation and sensitivity analyses show that the three transfer components improve both prediction accuracy and data efficiency. The proposed method provides a practical solution for adapting ship motion predictors across vessel and severe sea-state domains with limited target-domain data.
Förderung
- Fund for Distinguished Young Scholars of Dalian Naval Academy
- Development Fund of Dalian Naval Academy
Zitieren
APA
Hou, L., Wang, X., Wei, Z., Wang, X., & Sun, Y. (2026). A Small-Sample Transfer Learning Framework for Cross-Domain Ship Motion Prediction in Extreme Sea States. Journal of Marine Science and Engineering, 14(15), 1353. https://doi.org/10.3390/jmse14151353
Vancouver
Hou L, Wang X, Wei Z, Wang X, Sun Y. A Small-Sample Transfer Learning Framework for Cross-Domain Ship Motion Prediction in Extreme Sea States. Journal of Marine Science and Engineering. 2026;14(15):1353. doi:10.3390/jmse14151353
BibTeX
@article{Hou2026,
author = {Hou, Lingyi and Wang, Xiao and Wei, Zhiyuan and Wang, Xu and Sun, Yuwen},
title = {A Small-Sample Transfer Learning Framework for Cross-Domain Ship Motion Prediction in Extreme Sea States},
journal = {Journal of Marine Science and Engineering},
year = {2026},
volume = {14},
number = {15},
pages = {1353},
doi = {10.3390/jmse14151353}
}
EUVIMED