Join Us Sign In

Knowledge Base Repository

In addition to research papers, the Design Society is developing several valuable resources for those interested in the study of design. These include a repository of PhD theses, a library of case studies and transcripts of design activities, and an archive of our newsletters. Please note that these resources are accessible exclusively to Design Society members.

Characterizing geometric variability of industrial 3D models to guide preparation of synthetic datasets for machine learning applications

Sever, Lovro (1); Kosec, Petar (1,2); Škec, Stanko (1); Martinec, Tomislav (1)

Type:
Papers
DS 145: Proceedings of the DESIGN2026 19th International Design Conference
Year:
2026
Editor:
Štorga, M.; Škec, S.; Martinec, T.; Marjanović, D.; Pavković, N.
Author:
Sever, Lovro (1); Kosec, Petar (1,2); Škec, Stanko (1); Martinec, Tomislav (1)
Series:
DESIGN
Institution:
1: University of Zagreb Faculty of Mechanical Engineering and Naval Architecture, Croatia; 2: Neo Dens Ltd., Croatia
Page(s):
2531-2540
DOI number:
10.1017/pds.2026.10611
ISSN:
2732-527X (Online)
Abstract:
This paper presents a characterization approach for analysing geometric variability in industrial 3D model datasets to support the preparation of synthetic datasets for machine-learning applications. By implementing pairwise Hausdorff distances and manifold-based embedding techniques, the study identifies variability ranges required for generating representative synthetic data and demonstrates how targeted augmentation can effectively reproduce real data's variability, ultimately leading to more reliable and robust NN model performance.
Keywords:
computer-aided design (CAD), 3D modelling, data-driven design, synthetic dataset
DESIGN2026 - The 19th International Design Conference
Conferences

This site uses cookies and other tracking technologies to assist with navigation and your ability to provide feedback, analyse your use of our products and services, assist with our promotional and marketing efforts, and provide content from third parties. Privacy Policy.

Cookie Settings Accept Cookies