From geometry to function: towards context-aware generative AI for engineering design
Proceedings of the Design Society · 2026-08 · 6 · 2193-2202
DOI: 10.1017/pds.2026.10577 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Design Society, online erschienen am 02.07.2026. Verfasst von Elias Berger und 7 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Current generative artificial intelligence for Computer-Aided Design (CAD) optimizes for geometric similarity, neglecting engineering criteria like functionality, manufacturability, and sustainability. This paper addresses this gap and proposes a conceptual framework to reorient generative CAD from replicating shapes to achieving function. We introduce two hybrid training strategies: a pre-learning approach using synthetically labeled datasets (evaluated via FEA, CAM, LCA) and a self-learning approach where GenAI uses these knowledge-based tools as a reinforcement feedback loop.
Zitieren
APA
Berger, E., Herrmann, K., Pusch, F., Kriesell, T., Gembarski, P., Mehlstäubl, J., Lachmayer, R., & Paetzold-Byhain, K. (2026). From geometry to function: towards context-aware generative AI for engineering design. Proceedings of the Design Society, 6, 2193-2202. https://doi.org/10.1017/pds.2026.10577
Vancouver
Berger E, Herrmann K, Pusch F, Kriesell T, Gembarski P, Mehlstäubl J, et al. From geometry to function: towards context-aware generative AI for engineering design. Proceedings of the Design Society. 2026;6:2193-2202. doi:10.1017/pds.2026.10577
BibTeX
@article{Berger2026,
author = {Berger, Elias and Herrmann, Kevin and Pusch, Felix and Kriesell, Tobias and Gembarski, Paul and Mehlstäubl, Jan and Lachmayer, Roland and Paetzold-Byhain, Kristin},
title = {From geometry to function: towards context-aware generative AI for engineering design},
journal = {Proceedings of the Design Society},
year = {2026},
volume = {6},
pages = {2193--2202},
doi = {10.1017/pds.2026.10577}
}
EUVIMED