EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fault Diagnosis of Rolling Bearing Acoustic Signal Under Strong Noise Based on WAA-FMD and LGAF-Swin Transformer

Hengdi Wang, Haokui Wang, Jizhan Xie, Zikui Ma

Processes · 27.08.2025 · 13 (9) · 2742

DOI: 10.3390/pr13092742 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 27.08.2025. Verfasst von Hengdi Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Program Project of the State Administration for Market Regulation, Ningbo Key Research and Development Program and “Unveiling and Leading” Project, National Natural Science Foundation of China Project: Research on Tribological Effects and Behavior Regulation Mechanisms of Magnetorheological Fluids.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of low diagnostic accuracy arising from the non-stationary and nonlinear time-varying characteristics of acoustic signals in rolling bearing fault diagnosis, as well as their susceptibility to noise interference, this paper proposes a fault diagnosis method based on a Weighted Average Algorithm–Feature Mode Decomposition (WAA-FMD) and a Local–Global Adaptive Multi-scale Attention Mechanism (LGAF)–Swin Transformer. First, the WAA is utilized to optimize the key parameters of FMD, thereby enhancing its signal decomposition performance while minimizing noise interference. Next, a bilateral expansion strategy is implemented to extend both the time window and frequency band of the signal, which improves the temporal locality and frequency globality of the time–frequency diagram, significantly enhancing the ability to capture signal features. Ultimately, the introduction of depthwise separable convolution optimizes the receptive field and improves the computational efficiency of shallow networks. When combined with the Swin Transformer, which incorporates LGAF and adaptive feature selection modules, the model further enhances its perceptual capabilities and feature extraction accuracy through dynamic kernel adjustment and deep feature aggregation strategies. The experimental results indicate that the signal denoising performance of WAA-FMD significantly outperforms traditional denoising techniques. In the KAIST dataset (NSK 6205: inner raceway fault and outer raceway fault) and the experimental dataset (FAG 30205: inner raceway fault, outer raceway fault, and rolling element fault), the accuracies of the proposed model reach 100% and 98.62%, respectively, both exceeding that of other deep learning models. In summary, the proposed method demonstrates substantial advantages in noise reduction performance and fault diagnosis accuracy, providing valuable theoretical insights for practical applications.

Förderung

  • Science and Technology Program Project of the State Administration for Market Regulation
  • Ningbo Key Research and Development Program and “Unveiling and Leading” Project
  • National Natural Science Foundation of China Project: Research on Tribological Effects and Behavior Regulation Mechanisms of Magnetorheological Fluids
  • Research on Grease Degradation Patterns and State Evaluation for High-power Wind Turbine Main Bearings

Zitieren

APA

Wang, H., Wang, H., Xie, J., & Ma, Z. (2025). Fault Diagnosis of Rolling Bearing Acoustic Signal Under Strong Noise Based on WAA-FMD and LGAF-Swin Transformer. Processes, 13(9), 2742. https://doi.org/10.3390/pr13092742

Vancouver

Wang H, Wang H, Xie J, Ma Z. Fault Diagnosis of Rolling Bearing Acoustic Signal Under Strong Noise Based on WAA-FMD and LGAF-Swin Transformer. Processes. 2025;13(9):2742. doi:10.3390/pr13092742

BibTeX
@article{Wang2025,
  author = {Wang, Hengdi and Wang, Haokui and Xie, Jizhan and Ma, Zikui},
  title = {Fault Diagnosis of Rolling Bearing Acoustic Signal Under Strong Noise Based on WAA-FMD and LGAF-Swin Transformer},
  journal = {Processes},
  year = {2025},
  volume = {13},
  number = {9},
  pages = {2742},
  doi = {10.3390/pr13092742}
}
Kostenlos starten →