EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient Gearbox Fault Diagnosis Based on Improved Multi-Scale CNN with Lightweight Convolutional Attention

Bin Yuan, Yaoqi Li iD, Suifan Chen

Sensors · 22.04.2025 · 25 (9) · 2636

DOI: 10.3390/s25092636 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.04.2025. Verfasst von Bin Yuan und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical and Energy Engineering, Zhejiang University of Science and Technology, Hangzhou 310013, China. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Suifan Chen, Zhejiang Province “Sharp Soldiers” “leading geese” R & D PR program project, Zhejiang Province “Sharp Soldiers and leading geese + X” R & D research and development program project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As a core transmission component of modern industrial equipment, the operation status of the gearbox has a significant impact on the reliability and service life of major machinery. In this paper, we propose an intelligent diagnosis framework based on Empirical Mode Decomposition and multimodal feature co-optimization and innovatively construct a fault diagnosis model by fusing a multi-scale convolutional neural network and a lightweight convolutional attention model. The framework extracts the multi-band features of vibration signals through the improved multi-scale convolutional neural network, which significantly enhances adaptability to complex working conditions (variable rotational speed, strong noise); at the same time, the lightweight convolutional attention mechanism is used to replace the multi-attention of the traditional Transformer, which greatly reduces computational complexity while guaranteeing accuracy and realizes highly efficient, lightweight local–global feature modeling. The lightweight convolutional attention is adaptively captured by the dynamic convolutional kernel generation strategy to adaptively capture local features in the time domain, and combined with grouped convolution to enhance the computational efficiency further; in addition, parameterized revised linear units are introduced to retain fault-sensitive negative information, which enhances the model’s ability to detect weak faults. The experimental findings demonstrate that the proposed model achieves an accuracy greater than 98.9%, highlighting its exceptional diagnostic accuracy and robustness. Moreover, compared to other fault diagnosis methods, the model exhibits superior performance under complex working conditions.

Schlagwörter

Stichwörter der Autor:innen

EMDdynamic convolutional kernelgearbox fault diagnosislightweight convolutional attentionmulti-scale CNN

Autor:innen und Institutionen

  • College of Mechanical and Energy Engineering, Zhejiang University of Science and Technology, Hangzhou 310013, China.

ORCID-Profile: Yaoqi Li

Förderung

  • Suifan Chen
  • Zhejiang Province “Sharp Soldiers” “leading geese” R & D PR program project
  • Zhejiang Province “Sharp Soldiers and leading geese + X” R & D research and development program project

Zitieren

APA

Yuan, B., Li, Y., & Chen, S. (2025). Efficient Gearbox Fault Diagnosis Based on Improved Multi-Scale CNN with Lightweight Convolutional Attention. Sensors, 25(9), 2636. https://doi.org/10.3390/s25092636

Vancouver

Yuan B, Li Y, Chen S. Efficient Gearbox Fault Diagnosis Based on Improved Multi-Scale CNN with Lightweight Convolutional Attention. Sensors. 2025;25(9):2636. doi:10.3390/s25092636

BibTeX
@article{Yuan2025,
  author = {Yuan, Bin and Li, Yaoqi and Chen, Suifan},
  title = {Efficient Gearbox Fault Diagnosis Based on Improved Multi-Scale CNN with Lightweight Convolutional Attention},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {9},
  pages = {2636},
  doi = {10.3390/s25092636}
}
Kostenlos starten →