EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fault Diagnosis of Wind Turbine Bearings Based on a Multi-Scale Residual Attention Graph Neural Network

Yubo Liu, Xiaohui Zhang, Keliang Dong, Zhilei Xu, Fengjuan Zhang, Zhiwei Li

Electronics · 29.03.2026 · 15 (7) · 1422

DOI: 10.3390/electronics15071422 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 29.03.2026. Verfasst von Yubo Liu und 5 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Henan Province, Science and Technology Key Project of Henan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fault diagnosis of rolling bearings in wind turbines is significantly challenged by strong noise, non-stationary signals, and multi-source interference. To address these issues, a Multi-Scale Attention Residual Graph Convolutional Network (MSAR-GCN) is proposed. First, a fully connected graph is constructed in the frequency domain using a temporal segmentation strategy, which preserves full spectral resolution and captures cross-frequency coupling features via node embeddings. Second, a multi-scale residual module with a cross-layer pyramid structure is designed to extract features at varying granularities, integrated with a dynamic multi-head attention mechanism to adaptively emphasize damage-sensitive frequency bands. Additionally, a hierarchical feature distillation mechanism is employed to compress high-dimensional features, ensuring model lightweighting while retaining critical fault information. Experimental validations on CWRU and JNU datasets demonstrate that MSAR-GCN achieves 97.02% and 92.5% accuracy under −10 dB Gaussian noise, respectively, outperforming existing methods by over 4%. Specifically, the model exhibits exceptional robustness, maintaining 93.09% accuracy under severe non-Gaussian impulsive noise. With verified feature separability and high computational efficiency, the proposed method offers a promising solution for high-precision, real-time industrial fault diagnosis.

Förderung

  • Natural Science Foundation of Henan Province
  • Science and Technology Key Project of Henan Province

Zitieren

APA

Liu, Y., Zhang, X., Dong, K., Xu, Z., Zhang, F., & Li, Z. (2026). Fault Diagnosis of Wind Turbine Bearings Based on a Multi-Scale Residual Attention Graph Neural Network. Electronics, 15(7), 1422. https://doi.org/10.3390/electronics15071422

Vancouver

Liu Y, Zhang X, Dong K, Xu Z, Zhang F, Li Z. Fault Diagnosis of Wind Turbine Bearings Based on a Multi-Scale Residual Attention Graph Neural Network. Electronics. 2026;15(7):1422. doi:10.3390/electronics15071422

BibTeX
@article{Liu2026,
  author = {Liu, Yubo and Zhang, Xiaohui and Dong, Keliang and Xu, Zhilei and Zhang, Fengjuan and Li, Zhiwei},
  title = {Fault Diagnosis of Wind Turbine Bearings Based on a Multi-Scale Residual Attention Graph Neural Network},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {7},
  pages = {1422},
  doi = {10.3390/electronics15071422}
}
Kostenlos starten →