EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multimodal Fault Diagnosis of Rolling Bearings Based on GRU–ResNet–CBAM

Kunbo Xu, Jingyang Zhang, Dongjun Liu, Chaoge Wang, Ran Wang, Funa Zhou

Machines · 11.03.2026 · 14 (3) · 318

DOI: 10.3390/machines14030318 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 11.03.2026. Verfasst von Kunbo Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China’s National Natural Science Foundation Youth Fund, Ministry of Education of China’s Youth Fund for Humanities and Social Sciences, Open Project of the Key Laboratory of Aerodynamic Noise Control.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rolling bearings exhibit nonlinear and non-stationary fault signals under complex working conditions, rendering single-modal representation insufficient for accurate diagnosis. To address this limitation, this paper proposes a novel parallel multimodal fusion fault diagnosis model based on a Gated Recurrent Unit (GRU), a Residual Network (ResNet), and a Convolutional Block Attention Module (CBAM). First, a systematic multimodal representation selection framework is introduced, identifying the Markov Transition Field (MTF) as the optimal two-dimensional (2D) image modality due to its superior texture clarity and noise resistance compared to other methods. Second, parallel dual-branch architecture is designed to simultaneously process heterogeneous data. The 1D-GRU branch captures long-range temporal dependencies directly from raw vibration signals, while the 2D ResNet-CBAM branch extracts deep spatial features from the MTF images, adaptively focusing on key fault regions. These heterogeneous features are then fused through concatenation to retain complementary diagnostic information. Experimental validation on the Case Western Reserve University (CWRU) dataset demonstrates that the proposed model achieves a 99.57% accuracy in a 10-classification task. Furthermore, it exhibits significant parameter efficiency and outstanding robustness, with the accuracy decreasing by no more than 1.2% under noise interference and cross-load scenarios, comprehensively outperforming existing single-modal and advanced fusion methods.

Förderung

  • China’s National Natural Science Foundation Youth Fund
  • Ministry of Education of China’s Youth Fund for Humanities and Social Sciences
  • Open Project of the Key Laboratory of Aerodynamic Noise Control

Zitieren

APA

Xu, K., Zhang, J., Liu, D., Wang, C., Wang, R., & Zhou, F. (2026). Multimodal Fault Diagnosis of Rolling Bearings Based on GRU–ResNet–CBAM. Machines, 14(3), 318. https://doi.org/10.3390/machines14030318

Vancouver

Xu K, Zhang J, Liu D, Wang C, Wang R, Zhou F. Multimodal Fault Diagnosis of Rolling Bearings Based on GRU–ResNet–CBAM. Machines. 2026;14(3):318. doi:10.3390/machines14030318

BibTeX
@article{Xu2026,
  author = {Xu, Kunbo and Zhang, Jingyang and Liu, Dongjun and Wang, Chaoge and Wang, Ran and Zhou, Funa},
  title = {Multimodal Fault Diagnosis of Rolling Bearings Based on GRU–ResNet–CBAM},
  journal = {Machines},
  year = {2026},
  volume = {14},
  number = {3},
  pages = {318},
  doi = {10.3390/machines14030318}
}
Kostenlos starten →