D3 Article in a professional conference publication
A RAG-based LLM Approach for Data Validation and Harmonization in Ship Design
Authors: Bronson, Janica; Teimouri, Maryam; Gaspar, Henrique; Fonseca, Icaro; Bierkowska, Karolina; Ginter, Filip; Koelman, Herbert
Editors: Bertram, Volker
Conference name: International Conference on Computer and IT Applications in the Maritime Industries
Publication year: 2025
Book title : 23rd Conference on Computer and IT Applications in the Maritime Industries: COMPIT’25
First page : 171
Last page: 181
DOI: https://doi.org/10.5281/zenodo.17223682
Web address : https://doi.org/10.5281/zenodo.17223682
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/505154067
Validating ship design data across systems is challenging due to fragmented information from multiple
sources, file types, and formats – from 2D drawings, 3D models, and specifications, often found in
unstructured text files. While unified 3D models aim to serve as a single source of truth, ensuring
accuracy and consistency across all representations remains a complex task. This paper presents a
retrieval-augmented generation (RAG) solution for extracting and comparing design parameters from
diverse files and formats. The approach aims to detect inconsistencies between documents and versions,
helping designers maintain data integrity and reduce manual effort throughout the ship design process.
Downloadable publication This is an electronic reprint of the original article. |  |
Funding information in the publication:
This paper is the result of the research project funded by the Smart European Shipbuilding (SEUS) Project (grant ID 101096224).
