A fast evaluation framework for the hydrodynamic performance of deformed marine structures using artificial intelligence-based three-dimensional reconstruction

Abstract Marine structures such as ships and offshore platforms often suffer structural deformation during service due to factors including collision and corrosion. After deformation occurs, the rapid evaluation of the hydrodynamic performance of structures is a prerequisite for ensuring safety and formulating maintenance strategies. To this end, this paper establishes a rapid evaluation framework for the hydrodynamic performance of deformed marine structures, which integrates image acquisition, Artificial Intelligence (AI)-based Three-Dimensional (3D) reconstruction, numerical simulation, and emergency decision-making. The specific procedure of the framework consists of four steps: First, a multi-view image acquisition scheme for structures considering deformed regions is designed to collect two-dimensional images and complete preprocessing. Second, the 3D model of the structure is reconstructed based on the HunYuan3D model, followed by preprocessing operations such as hole filling and topological repair. Third, the processed model is imported into hydrodynamic software to complete the numerical simulation and performance evaluation of the structure. Finally, a follow-up disposal plan is formulated and decision-making suggestions are provided based on the evaluation results.The framework is validated on a deformed ship: the errors of the governing geometric parameters of the reconstructed model are within 3%, and the simulated deterioration of the stability reserve and motion responses is consistent with the mechanisms reported for damaged hulls. Positioning the framework as a rapid preliminary screening and decision-support tool for emergency scenarios, the results demonstrate an efficient evaluation of the hydrodynamic performance of deformed structures with a balance among low cost, high efficiency, and verifiable reliability, providing data support for the emergency decision-making of deformed ships and offshore platforms.

Authors

Institutions

Publication Details

Journal
Discover Artificial Intelligence
Published
2026-10-29
DOI
https://doi.org/10.1007/s44163-026-02685-z
Primary Topic
Ship Hydrodynamics and Maneuverability
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A fast evaluation framework for the hydrodynamic performance of deformed marine structures using artificial intelligence-based three-dimensional reconstruction

Chunmei Xie, Yunxing Zhang, Jiepeng Huang, Yan Zhou
2 links
Discover Artificial Intelligence
Ship Hydrodynamics and Maneuverability
article

A fast evaluation framework for the hydrodynamic performance of deformed marine structures using artificial intelligence-based three-dimensional reconstruction

Chunmei Xie, Yunxing Zhang, Jiepeng Huang, Yan Zhou
article en

Abstract

Abstract Marine structures such as ships and offshore platforms often suffer structural deformation during service due to factors including collision and corrosion. After deformation occurs, the rapid evaluation of the hydrodynamic performance of structures is a prerequisite for ensuring safety and formulating maintenance strategies. To this end, this paper establishes a rapid evaluation framework for the hydrodynamic performance of deformed marine structures, which integrates image acquisition, Artificial Intelligence (AI)-based Three-Dimensional (3D) reconstruction, numerical simulation, and emergency decision-making. The specific procedure of the framework consists of four steps: First, a multi-view image acquisition scheme for structures considering deformed regions is designed to collect two-dimensional images and complete preprocessing. Second, the 3D model of the structure is reconstructed based on the HunYuan3D model, followed by preprocessing operations such as hole filling and topological repair. Third, the processed model is imported into hydrodynamic software to complete the numerical simulation and performance evaluation of the structure. Finally, a follow-up disposal plan is formulated and decision-making suggestions are provided based on the evaluation results.The framework is validated on a deformed ship: the errors of the governing geometric parameters of the reconstructed model are within 3%, and the simulated deterioration of the stability reserve and motion responses is consistent with the mechanisms reported for damaged hulls. Positioning the framework as a rapid preliminary screening and decision-support tool for emergency scenarios, the results demonstrate an efficient evaluation of the hydrodynamic performance of deformed structures with a balance among low cost, high efficiency, and verifiable reliability, providing data support for the emergency decision-making of deformed ships and offshore platforms.

Discover Artificial IntelligenceVol. 6(1)
Harbin University (CN), Harbin Engineering University (CN), Ludong University (CN), Harbin Finance University (CN), China Ship Scientific Research Center (CN), Shandong Institute of Business and Technology (CN)
National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Natural Science Foundation of Shandong Province
Industry, innovation and infrastructure
Openalex Percentile: Top 19%
Ship Hydrodynamics and Maneuverability
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon