EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Spectral Interpretable Bearing Fault Diagnosis Framework Powered by Large Language Models

Panfeng Bao, Wenjun Yi, Yue Zhu, Yufeng Shen, Haotian Peng iD

Sensors · 19.06.2025 · 25 (12) · 3822

DOI: 10.3390/s25123822 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.06.2025. Verfasst von Panfeng Bao und 4 weiteren Autor:innen. Beteiligte Einrichtung: National Key Laboratory of Transient Physics, Nanjing University of Science and Technology, Nanjing 210094, China. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hunan Provincial Department of Education Excellent Youth Project, Hunan Provincial Department of Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Most existing fault diagnosis methods, although capable of extracting interpretable features such as attention-weighted fault-related frequencies, remain essentially black-box models that provide only classification results without transparent reasoning or diagnostic justification, limiting users’ ability to understand and trust diagnostic outcomes. In this work, we present a novel, interpretable fault diagnosis framework that integrates spectral feature extraction with large language models (LLMs). Vibration signals are first transformed into spectral representations using Hilbert- and Fourier-based encoders to highlight key frequencies and amplitudes. A channel attention-augmented convolutional neural network provides an initial fault type prediction. Subsequently, structured information—including operating conditions, spectral features, and CNN outputs—is fed into a fine-tuned enhanced LLM, which delivers both an accurate diagnosis and a transparent reasoning process. Experiments demonstrate that our framework achieves high diagnostic performance while substantially improving interpretability, making advanced fault diagnosis accessible to non-expert users in industrial settings.

Schlagwörter

Stichwörter der Autor:innen

bearing fault diagnosisinterpretable artificial intelligencelarge language modelsmulti-source information fusionspectral feature extraction

Autor:innen und Institutionen

  • National Key Laboratory of Transient Physics, Nanjing University of Science and Technology, Nanjing 210094, China.
  • School of Aeronautical Mechanical Manufacturing, Changsha Aeronautical Vocational and Technical College, Changsha 410124, China.
  • Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110069, China.
  • University of Chinese Academy of Sciences, Beijing 101408, China.

ORCID-Profile: Haotian Peng

Förderung

  • Hunan Provincial Department of Education Excellent Youth Project
  • Hunan Provincial Department of Education

Zitieren

APA

Bao, P., Yi, W., Zhu, Y., Shen, Y., & Peng, H. (2025). A Spectral Interpretable Bearing Fault Diagnosis Framework Powered by Large Language Models. Sensors, 25(12), 3822. https://doi.org/10.3390/s25123822

Vancouver

Bao P, Yi W, Zhu Y, Shen Y, Peng H. A Spectral Interpretable Bearing Fault Diagnosis Framework Powered by Large Language Models. Sensors. 2025;25(12):3822. doi:10.3390/s25123822

BibTeX
@article{Bao2025,
  author = {Bao, Panfeng and Yi, Wenjun and Zhu, Yue and Shen, Yufeng and Peng, Haotian},
  title = {A Spectral Interpretable Bearing Fault Diagnosis Framework Powered by Large Language Models},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {12},
  pages = {3822},
  doi = {10.3390/s25123822}
}
Kostenlos starten →