EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Physics‐Aware Lightweight Transformer Network for Intelligent Bearing Fault Diagnosis Under Variable Operating Conditions

Ali Sayghe

Artificial Intelligence for Engineering · 2026-06 · 2 (2) · 195-207

DOI: 10.1049/aie2.70014 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Intelligence for Engineering, online erschienen am 17.06.2026. Verfasst von Ali Sayghe. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing bearing fault diagnosis methods fail to generalise across variable operating conditions while remaining lightweight for industrial edge deployment. We propose PLT‐Bearing, a physics‐aware transformer that adapts vision transformer tokenisation to vibration signals through overlapping convolutional patch embedding, sampling‐frequency‐guided patch sizing and analytically proved amplitude‐invariant self‐attention. With only 0.52 M parameters and 8.2 ms GPU inference latency, PLT‐bearing achieves 99.2% and 95.8% accuracy on the CWRU and Paderborn University benchmarks, respectively, and 90.3% zero‐shot cross‐load transfer accuracy, outperforming recent lightweight CNNs and Mamba‐based state‐space models.

Zitieren

APA

Sayghe, A. (2026). A Physics‐Aware Lightweight Transformer Network for Intelligent Bearing Fault Diagnosis Under Variable Operating Conditions. Artificial Intelligence for Engineering, 2(2), 195-207. https://doi.org/10.1049/aie2.70014

Vancouver

Sayghe A. A Physics‐Aware Lightweight Transformer Network for Intelligent Bearing Fault Diagnosis Under Variable Operating Conditions. Artificial Intelligence for Engineering. 2026;2(2):195-207. doi:10.1049/aie2.70014

BibTeX
@article{Sayghe2026,
  author = {Sayghe, Ali},
  title = {A Physics‐Aware Lightweight Transformer Network for Intelligent Bearing Fault Diagnosis Under Variable Operating Conditions},
  journal = {Artificial Intelligence for Engineering},
  year = {2026},
  volume = {2},
  number = {2},
  pages = {195--207},
  doi = {10.1049/aie2.70014}
}
Kostenlos starten →