EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A unified framework for interpretable elevator fault diagnosis and predictive maintenance via style-aware CoT fine-tuning

Yuhao Wang iD, Junjie Huang, Qiang Zhang iD

PLOS One · 07.07.2026 · 21 (7) · e0353219

DOI: 10.1371/journal.pone.0353219 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 07.07.2026. Verfasst von Yuhao Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Zhejiang University, Hangzhou, China. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang Provincial “Jianbing” “Lingyan” Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Although Large Language Models (LLMs) have shown potential in industrial applications, they encounter significant hurdles in vertical scenarios like elevator maintenance, including hallucinations, lack of domain specificity, and an inability to interpret numerical physical states. To bridge this semantic-physical gap, this paper proposes a Unified Style-Aware Chain-of-Thought (SA-CoT) framework tailored for Small Language Models (SLMs). The novelty of our approach lies in two aspects: first, we construct a robust instruction dataset using a style-aware augmentation strategy to simulate diverse real-world user behaviors and noise; second, we innovate by textualizing raw sensor data, enabling the fine-tuned 4B-parameter SLM to generate high-dimensional embeddings for downstream numerical analysis. Experiments demonstrate a dual breakthrough: in generative diagnosis, the SA-CoT framework consistently outperforms general models, achieving a 5.6-fold improvement in BLEU-4 scores compared to GPT-4o. Furthermore, its embeddings capture physical features more effectively than traditional baselines, yielding highly competitive accuracy in Alarm Type Classification and Vibration Magnitude Regression. These results suggest that domain-aligned SLMs offer a robust and cost-effective framework for autonomous predictive maintenance, indicating that knowledge density plays a more critical role than parameter scale in specialized industrial applications.

Autor:innen und Institutionen

  • Zhejiang University, Hangzhou, China.
  • ZJU-Hangzhou Global Scientific and Technological Innovation Center, Hangzhou, China.

ORCID-Profile: Yuhao Wang, Qiang Zhang

Förderung

  • Zhejiang Provincial “Jianbing” “Lingyan” Research and Development Program of China

Zitieren

APA

Wang, Y., Huang, J., & Zhang, Q. (2026). A unified framework for interpretable elevator fault diagnosis and predictive maintenance via style-aware CoT fine-tuning. PLOS One, 21(7), e0353219. https://doi.org/10.1371/journal.pone.0353219

Vancouver

Wang Y, Huang J, Zhang Q. A unified framework for interpretable elevator fault diagnosis and predictive maintenance via style-aware CoT fine-tuning. PLOS One. 2026;21(7):e0353219. doi:10.1371/journal.pone.0353219

BibTeX
@article{Wang2026,
  author = {Wang, Yuhao and Huang, Junjie and Zhang, Qiang},
  title = {A unified framework for interpretable elevator fault diagnosis and predictive maintenance via style-aware CoT fine-tuning},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {7},
  pages = {e0353219},
  doi = {10.1371/journal.pone.0353219}
}
Kostenlos starten →