Predictive maintenance report generation using large language models
Pollack Periodica · 17.06.2026
DOI: 10.1556/606.2026.01552 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pollack Periodica, erschienen am 17.06.2026. Verfasst von Martin Kernács und 1 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study presents an approach in the field of multisource predictive maintenance. It integrates large language models with structured and unstructured industrial data to improve maintenance decision-making. The proposed system processes equipment manuals, operating-hour records, and Hungarian-language maintenance logs to generate unified, equipment-specific maintenance recommendations. A key contribution is a data-cleaning pipeline that corrects linguistic and structural inconsistencies in natural-language maintenance entries and reconstructs standardized tag numbers using rule-based parsing. To ensure transparency and industrial applicability, the system incorporates explainable artificial intelligence principles.
Zitieren
APA
Kernács, M., & Hornyák, O. (2026). Predictive maintenance report generation using large language models. Pollack Periodica. https://doi.org/10.1556/606.2026.01552
Vancouver
Kernács M, Hornyák O. Predictive maintenance report generation using large language models. Pollack Periodica. 2026. doi:10.1556/606.2026.01552
BibTeX
@article{Kerncs2026,
author = {Kernács, Martin and Hornyák, Olivér},
title = {Predictive maintenance report generation using large language models},
journal = {Pollack Periodica},
year = {2026},
doi = {10.1556/606.2026.01552}
}
EUVIMED