EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Attention Mechanism-Based Feature Fusion and Degradation State Classification for Rolling Bearing Performance Assessment

Teng Zhan, Wentao Chen, Congchang Xu, Luoxing Li, Xiaoxi Ding iD

Sensors · 10.08.2025 · 25 (16) · 4951

DOI: 10.3390/s25164951 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.08.2025. Verfasst von Teng Zhan und 4 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle, Changsha 410082, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Special Project for the Innovative Province Construction of Hunan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rolling bearing failure poses significant risks to mechanical system integrity, potentially leading to catastrophic safety incidents. Current challenges in performance degradation assessment include complex structural characteristics, suboptimal feature selection, and inadequate health index characterization. This study proposes a novel attention mechanism-based feature fusion method for accurate bearing performance assessment. First, we construct a multidimensional feature set encompassing time domain, frequency domain, and time–frequency domain characteristics. A two-stage sensitive feature selection strategy is developed, combining intersection-based primary selection with clustering-based re-selection to eliminate redundancy while preserving correlation, monotonicity, and robustness. Subsequently, an attention mechanism-driven fusion model adaptively weights selected features to generate high-performance health indicators. Experimental validation demonstrates the proposed method’s superiority in degradation characterization through two case studies. The intersection clustering strategy achieves 32% redundancy reduction compared to conventional methods, while the attention-based fusion improves health indicator consistency by 18.7% over principal component analysis. This approach provides an effective solution for equipment health monitoring and early fault warning in industrial applications.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismfeature fusionperformance degradation assessmentrolling bearing

Autor:innen und Institutionen

  • State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle, Changsha 410082, China.
  • Hunan Lince Rolling Stock Equipment Co., Ltd., Zhuzhou 412001, China.
  • State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400030, China.

ORCID-Profile: Xiaoxi Ding

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Special Project for the Innovative Province Construction of Hunan
  • Innovative Province Construction of Hunan

Zitieren

APA

Zhan, T., Chen, W., Xu, C., Li, L., & Ding, X. (2025). Attention Mechanism-Based Feature Fusion and Degradation State Classification for Rolling Bearing Performance Assessment. Sensors, 25(16), 4951. https://doi.org/10.3390/s25164951

Vancouver

Zhan T, Chen W, Xu C, Li L, Ding X. Attention Mechanism-Based Feature Fusion and Degradation State Classification for Rolling Bearing Performance Assessment. Sensors. 2025;25(16):4951. doi:10.3390/s25164951

BibTeX
@article{Zhan2025,
  author = {Zhan, Teng and Chen, Wentao and Xu, Congchang and Li, Luoxing and Ding, Xiaoxi},
  title = {Attention Mechanism-Based Feature Fusion and Degradation State Classification for Rolling Bearing Performance Assessment},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {16},
  pages = {4951},
  doi = {10.3390/s25164951}
}
Kostenlos starten →