EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Three-Layer Runtime Constraint Verification Framework with Self-Correction for AI-Generated Parametric CAD Models

Xiaoyi Yin, Zihan Chen, Yang Shen, Timothy Haw-Yu Lee

Applied Sciences · 23.07.2026 · 16 (15) · 7396

DOI: 10.3390/app16157396 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 23.07.2026. Verfasst von Xiaoyi Yin und 3 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key Laboratory for Bio-based Transportation Fuels.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) frequently generate physically impossible parametric specifications in computer-aided design (CAD). This paper presents FMforME, a three-layer runtime constraint verification framework that integrates LLM-based generation with six engineering standard-grounded defect detection predicates (D1–D6) and execution in Autodesk Fusion 360. To address detected violations, a Self-Examine subsystem iteratively provides structured, standard-referenced feedback to the LLM, enabling verifier-guided error correction. We evaluated the framework across 564 test cases using four LLM backends from three model families. The system showed consistent buildability within the evaluated benchmark: across all models, every specification validated by the Monitor successfully built in Fusion 360 (548/548). Across the four evaluated backends, realized seeded defect detection ranged from 95.5% to 95.8%, and three backends showed an observed 100% natural pass rate in this benchmark. Crucially, this runtime safety barrier adds little computational overhead relative to LLM inference, averaging only 0.1 ms per in-memory verification check. These results show that standards-referenced runtime verification with structured self-correction can serve as a practical safeguard for LLM-generated CAD specifications within the tested single-part workflows, while broader validation on complex assemblies remains future work.

Förderung

  • National Natural Science Foundation of China
  • National Key Laboratory for Bio-based Transportation Fuels

Zitieren

APA

Yin, X., Chen, Z., Shen, Y., & Lee, T. H. (2026). A Three-Layer Runtime Constraint Verification Framework with Self-Correction for AI-Generated Parametric CAD Models. Applied Sciences, 16(15), 7396. https://doi.org/10.3390/app16157396

Vancouver

Yin X, Chen Z, Shen Y, Lee TH. A Three-Layer Runtime Constraint Verification Framework with Self-Correction for AI-Generated Parametric CAD Models. Applied Sciences. 2026;16(15):7396. doi:10.3390/app16157396

BibTeX
@article{Yin2026,
  author = {Yin, Xiaoyi and Chen, Zihan and Shen, Yang and Lee, Timothy Haw-Yu},
  title = {A Three-Layer Runtime Constraint Verification Framework with Self-Correction for AI-Generated Parametric CAD Models},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {15},
  pages = {7396},
  doi = {10.3390/app16157396}
}
Kostenlos starten →