AI-enhanced computer-aided design: predictive modelling of operations
Proceedings of the Design Society · 2026-08 · 6 · 2561-2570
DOI: 10.1017/pds.2026.10614 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Design Society, online erschienen am 02.07.2026. Verfasst von Sarah Steininger und 4 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
This work introduces a graph-based CAD assistant that predicts the next modelling operation in parametric design sequences. Real CATIA V5 models from the automotive domain are converted into directed acyclic graphs capturing feature dependencies, enabling learning directly from structural design data. A four-layer Graph Attention Network achieved a top-5 prediction accuracy of 94%, outperforming a frequency-based non-parametric baseline. The results show that graph representations and attention-based message passing provide a strong foundation for context-aware modelling assistance.
Zitieren
APA
Steininger, S., Kezer, S., Krüger, M., Richtsfeld, R., & Fottner, J. (2026). AI-enhanced computer-aided design: predictive modelling of operations. Proceedings of the Design Society, 6, 2561-2570. https://doi.org/10.1017/pds.2026.10614
Vancouver
Steininger S, Kezer S, Krüger M, Richtsfeld R, Fottner J. AI-enhanced computer-aided design: predictive modelling of operations. Proceedings of the Design Society. 2026;6:2561-2570. doi:10.1017/pds.2026.10614
BibTeX
@article{Steininger2026,
author = {Steininger, Sarah and Kezer, Saltuk and Krüger, Moritz and Richtsfeld, Robin and Fottner, Johannes},
title = {AI-enhanced computer-aided design: predictive modelling of operations},
journal = {Proceedings of the Design Society},
year = {2026},
volume = {6},
pages = {2561--2570},
doi = {10.1017/pds.2026.10614}
}
EUVIMED