EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

In search for working principles using large language models: an experimental study

Fabio Hanspach, Kilian Gericke, Ute Dietrich, Boris Eisenbart

Proceedings of the Design Society · 2026-08 · 6 · 2333-2341

DOI: 10.1017/pds.2026.10591 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Design Society, online erschienen am 02.07.2026. Verfasst von Fabio Hanspach und 3 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The use of artificial intelligence, especially large language models (LLMs), is increasingly explored to support early system development. This paper evaluates low-threshold LLM-based tools for supporting conceptual design. Through an experiment, two LLM-based tools were compared generating alternative solutions using an existing function model of an electro-mechanical system as input. Functions were provided in natural language and using the Functional Basis. Results show limitations and significant potentials for effective and efficient conceptual design support.

Zitieren

APA

Hanspach, F., Gericke, K., Dietrich, U., & Eisenbart, B. (2026). In search for working principles using large language models: an experimental study. Proceedings of the Design Society, 6, 2333-2341. https://doi.org/10.1017/pds.2026.10591

Vancouver

Hanspach F, Gericke K, Dietrich U, Eisenbart B. In search for working principles using large language models: an experimental study. Proceedings of the Design Society. 2026;6:2333-2341. doi:10.1017/pds.2026.10591

BibTeX
@article{Hanspach2026,
  author = {Hanspach, Fabio and Gericke, Kilian and Dietrich, Ute and Eisenbart, Boris},
  title = {In search for working principles using large language models: an experimental study},
  journal = {Proceedings of the Design Society},
  year = {2026},
  volume = {6},
  pages = {2333--2341},
  doi = {10.1017/pds.2026.10591}
}
Kostenlos starten →