Rolling Bearing Fault Diagnosis Model Based on Multi-Scale Depthwise Separable Convolutional Neural Network Integrated with Spatial Attention Mechanism
Sensors · 30.06.2025 · 25 (13) · 4064
DOI: 10.3390/s25134064 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 30.06.2025. Verfasst von Zhixin Jin und 9 weiteren Autor:innen. Beteiligte Einrichtung: Coal Mine Intelligent Equipment Research Center of Shanxi Province, Taiyuan University of Technology, Taiyuan 030024, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the State Key Laboratory of Intelligent Mining Equipment Technology;Basic Research Program of Shanxi Province;Independent Research Project of the State Key Lab…, Basic Research Program of Shanxi Province, Key R&D Project of Shanxi Province.
Abstract (Originalsprache)
In response to the challenges posed by complex and variable operating conditions of rolling bearings and the limited availability of labeled data, both of which hinder the effective extraction of key fault features and reduce diagnostic accuracy, this study introduces a model that combines a spatial attention (SA) mechanism with a multi-scale depthwise separable convolution module. The proposed approach first employs the Gramian angular difference field (GADF) to convert raw signals. This conversion maps the temporal characteristics of the signal into an image format that intrinsically preserves both temporal dynamics and phase relationships. Subsequently, the model architecture incorporates a spatial attention mechanism and a multi-scale depthwise separable convolutional module. Guided by the attention mechanism to concentrate on discriminative feature regions and to suppress noise, the convolutional component efficiently extracts hierarchical features in parallel through the multi-scale receptive fields. Furthermore, the trained model serves as a pre-trained network and is transferred to novel variable-condition environments to enhance diagnostic accuracy in few-shot scenarios. The effectiveness of the proposed model was evaluated using bearing datasets and field-collected industrial data. Experimental results confirm that the proposed model offers outstanding fault recognition performance and generalization capability across diverse working conditions, small-sample scenarios, and real industrial environments.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Coal Mine Intelligent Equipment Research Center of Shanxi Province, Taiyuan University of Technology, Taiyuan 030024, China.
- School of Safety and Emergency Management Engineering, Taiyuan University of Technology, Taiyuan 030024, China.
- School of Mining Engineering, Taiyuan University of Technology, Taiyuan 030024, China.
- State Key Laboratory of Intelligent Mining Equipment Technology, Taiyuan 030032, China.
- Xinjiang Intelligent Equipment Research Institute, Aksu 843000, China.
ORCID-Profile: Hongli Wang, Shengyu Guan
Förderung
- the State Key Laboratory of Intelligent Mining Equipment Technology;Basic Research Program of Shanxi Province;Independent Research Project of the State Key Lab…
- Basic Research Program of Shanxi Province
- Key R&D Project of Shanxi Province
- Independent Research Project of the State Key Laboratory of Intelligent Mining Equipment Technology
Zitieren
APA
Jin, Z., Hu, X., Wang, H., Guan, S., Liu, K., Fang, Z., Wang, H., Wang, X., Wang, L., & Zhang, Q. (2025). Rolling Bearing Fault Diagnosis Model Based on Multi-Scale Depthwise Separable Convolutional Neural Network Integrated with Spatial Attention Mechanism. Sensors, 25(13), 4064. https://doi.org/10.3390/s25134064
Vancouver
Jin Z, Hu X, Wang H, Guan S, Liu K, Fang Z, et al. Rolling Bearing Fault Diagnosis Model Based on Multi-Scale Depthwise Separable Convolutional Neural Network Integrated with Spatial Attention Mechanism. Sensors. 2025;25(13):4064. doi:10.3390/s25134064
BibTeX
@article{Jin2025,
author = {Jin, Zhixin and Hu, Xudong and Wang, Hongli and Guan, Shengyu and Liu, Kaiman and Fang, Zhiwen and Wang, Hongwei and Wang, Xuesong and Wang, Lijie and Zhang, Qun},
title = {Rolling Bearing Fault Diagnosis Model Based on Multi-Scale Depthwise Separable Convolutional Neural Network Integrated with Spatial Attention Mechanism},
journal = {Sensors},
year = {2025},
volume = {25},
number = {13},
pages = {4064},
doi = {10.3390/s25134064}
}
EUVIMED