EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust AI‐Driven Artifact Model Generation for Development Standards in Regulated Domains

Philipp Straub, Mustafa Bülbül, Robin Korfmann, Jürgen Münch, Marco Kuhrmann

Journal of Software: Evolution and Process · 2026-03 · 38 (3)

DOI: 10.1002/smr.70093 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Software: Evolution and Process, online erschienen am 16.03.2026. Verfasst von Philipp Straub und 4 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsches Zentrum für Luft- und Raumfahrt.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In regulated domains such as aerospace or automotive software, compliance with standards like ECSS and ISO/IEC 26262 is mandatory to ensure safety and reliability. Artifacts, such as process or product models, lay the foundation for planning and managing development projects, as well as for measurement and evaluation tasks. Manually extracting such artifacts from PDF‐based standards is time‐consuming and error‐prone. To address this issue, we developed a large language model (LLM)‐based approach for automatically generating artifact models from standards. However, the evolution of AI models constitutes a challenge, since the extraction results might differ when updating the LLM to a newer version. In this article, we present an enhanced approach that strengthens the artifact‐generation process against such challenges. The approach generates machine‐readable artifact models that allow for automated measurement systems, for example, for monitoring compliance and controlling complex projects. The performance of the artifact model generation was evaluated using the ECSS standards from the aerospace domain and resulted in an average completeness of 100.00% and an average precision of 71.33% of the generated models.

Förderung

  • Deutsches Zentrum für Luft- und Raumfahrt

Zitieren

APA

Straub, P., Bülbül, M., Korfmann, R., Münch, J., & Kuhrmann, M. (2026). Robust AI‐Driven Artifact Model Generation for Development Standards in Regulated Domains. Journal of Software: Evolution and Process, 38(3). https://doi.org/10.1002/smr.70093

Vancouver

Straub P, Bülbül M, Korfmann R, Münch J, Kuhrmann M. Robust AI‐Driven Artifact Model Generation for Development Standards in Regulated Domains. Journal of Software: Evolution and Process. 2026;38(3). doi:10.1002/smr.70093

BibTeX
@article{Straub2026,
  author = {Straub, Philipp and Bülbül, Mustafa and Korfmann, Robin and Münch, Jürgen and Kuhrmann, Marco},
  title = {Robust AI‐Driven Artifact Model Generation for Development Standards in Regulated Domains},
  journal = {Journal of Software: Evolution and Process},
  year = {2026},
  volume = {38},
  number = {3},
  doi = {10.1002/smr.70093}
}
Kostenlos starten →