EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Large Language Model-Based Manufacturing Execution System for Heat Treatment and Its Evaluation Method

Yixiao Sun, Wenyu Zhang, Chao Liu, Xiaohu Deng, Dongying Ju

Processes · 06.11.2026 · 14 (21) · 3597

DOI: 10.3390/pr14213597 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 06.11.2026. Verfasst von Yixiao Sun und 4 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Liaoning Provincial Key Laboratory of Internet of Things Application Technology for Intelligent Construction.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Quality investigations in heat treatment require inspection results to be linked with processing histories, while conventional manufacturing execution systems distribute these records across separate modules. This study develops a read-only language-model interface with product and basket-time linkage and evaluates query execution separately from evidence correctness. A same-model comparison using GPT–OSS 20B covers 48 tasks and 288 attempted executions, with 273 complete responses. Frozen condition-screen counts were similar; asymmetrically reviewed scope corrections are not used as comparative evidence. Independent backend checks identified alarm-count inconsistencies before evidence reached the model. A retrospective, non-blinded review of 41 numerical fallbacks, assisted by artificial intelligence (AI), found six pre-fallback answers supported relative to the saved evidence, 34 containing unsupported or incorrect claims, and one indeterminate. These assessments do not independently validate the enterprise records. Three quality cases illustrate linkage to stage-specific furnace evidence, but incomplete basket coverage leaves the relationship between temperature deviations and hardness nonconformity undetermined. The study separates returned states, answer support, and independently verified facts when evaluating language-model access to manufacturing records.

Förderung

  • Liaoning Provincial Key Laboratory of Internet of Things Application Technology for Intelligent Construction

Zitieren

APA

Sun, Y., Zhang, W., Liu, C., Deng, X., & Ju, D. (2026). A Large Language Model-Based Manufacturing Execution System for Heat Treatment and Its Evaluation Method. Processes, 14(21), 3597. https://doi.org/10.3390/pr14213597

Vancouver

Sun Y, Zhang W, Liu C, Deng X, Ju D. A Large Language Model-Based Manufacturing Execution System for Heat Treatment and Its Evaluation Method. Processes. 2026;14(21):3597. doi:10.3390/pr14213597

BibTeX
@article{Sun2026,
  author = {Sun, Yixiao and Zhang, Wenyu and Liu, Chao and Deng, Xiaohu and Ju, Dongying},
  title = {A Large Language Model-Based Manufacturing Execution System for Heat Treatment and Its Evaluation Method},
  journal = {Processes},
  year = {2026},
  volume = {14},
  number = {21},
  pages = {3597},
  doi = {10.3390/pr14213597}
}
Kostenlos starten →