Ship Propulsion Performance Estimation from Limited Hull Form Images Using Self-Supervised Pretraining with Decoder-Side Masking
Journal of Advanced Computational Intelligence and Intelligent Informatics · 20.11.2026 · 30 (6) · 1876-1883
DOI: 10.20965/jaciii.2026.p1876 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Advanced Computational Intelligence and Intelligent Informatics, online erschienen am 20.11.2026. Verfasst von Taian Kigawa und 3 weiteren Autor:innen. Die Arbeit nennt 10 Literaturangaben.
Abstract (Originalsprache)
Efficient estimation of ship propulsion performance from hull form geometry is essential for data-driven ship design. However, limited hull data due to confidentiality and manufacturing constraints hinder stable training of deep learning models. To address this challenge, we propose a self-supervised pretraining framework, salience-based adaptive decoder-side masking (SBADM), for estimating performance from a limited number of hull-form images. SBADM integrates two techniques: decoder-side masking, which preserves complete geometric information during encoding, and salience-based adaptive masking (SBAM), which dynamically adjusts masking ratios and regions based on token salience. These mechanisms enable effective pretraining even with small sample sizes. Experiments using 299 hull geometries provided by Japan Marine United Corporation show that SBADM improves estimation accuracy, particularly for the form factor ( 1+ K) and the highly sensitive thrust deduction factor ( 1- t) , confirming its effectiveness in enhancing feature representation and prediction robustness.
Zitieren
APA
Kigawa, T., Hamagami, T., Amaya, I., & Okamoto, N. (2026). Ship Propulsion Performance Estimation from Limited Hull Form Images Using Self-Supervised Pretraining with Decoder-Side Masking. Journal of Advanced Computational Intelligence and Intelligent Informatics, 30(6), 1876-1883. https://doi.org/10.20965/jaciii.2026.p1876
Vancouver
Kigawa T, Hamagami T, Amaya I, Okamoto N. Ship Propulsion Performance Estimation from Limited Hull Form Images Using Self-Supervised Pretraining with Decoder-Side Masking. Journal of Advanced Computational Intelligence and Intelligent Informatics. 2026;30(6):1876-1883. doi:10.20965/jaciii.2026.p1876
BibTeX
@article{Kigawa2026,
author = {Kigawa, Taian and Hamagami, Tomoki and Amaya, Ichiro and Okamoto, Naoya},
title = {Ship Propulsion Performance Estimation from Limited Hull Form Images Using Self-Supervised Pretraining with Decoder-Side Masking},
journal = {Journal of Advanced Computational Intelligence and Intelligent Informatics},
year = {2026},
volume = {30},
number = {6},
pages = {1876--1883},
doi = {10.20965/jaciii.2026.p1876}
}
EUVIMED