A Lightweight Rolling Bearing Fault Diagnosis Method Based on Multiscale Depth-Wise Separable Convolutions and Network Pruning
IEEE Access · 2024 · 12 · 186131-186144
DOI: 10.1109/access.2024.3441232 ↗At a glance
Journal article in IEEE Access, 2024. Written by Qingming Hu and 4 co-authors. Cited 14 times so far (Crossref); 41 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: Program of the Basic Scientific Research of Undergraduate Colleges and Universities, Heilongjiang, Heilongjiang Natural Science Foundation Project, Basic Scientific Research Operating Expenses Project of Heilongjiang Province.
Abstract (original language)
Fault diagnosis in rolling bearings is critical important in preventing machinery damage. Current deep learning-based approaches for rolling bearing fault diagnosis mainly rely on complex models that require significant hardware storage and computing power. In this paper, we introduce a multiscale Depth-wise Separable Convolutions and network pruning (MS-DWSC-PN) approach for lightweight rolling bearing fault diagnosis. Initially, the original one-dimensional vibration signals are transformed into two-dimensional time-frequency images using continuous wavelet transform (CWT), rendering them suitable for MS-DWSC-PN. Secondly, the datasets and an adaptive learning rate reduction algorithm are utilized to train the model, and the lightweight network model is achieved through network pruning. Subsequently, the results obtained from extensive experiments on identical datasets using AlexNet, VGG16, and LeNet confirm that the proposed model exhibits lower FLOPs and reduced iteration time. Finally, the generalizability of the model under variable operating conditions is discussed. Compared with other intelligent diagnosis methods, the presented strategy can achieve smaller model size and higher accuracy under both constant and variable working conditions.
Funding
- Program of the Basic Scientific Research of Undergraduate Colleges and Universities, Heilongjiang
- Heilongjiang Natural Science Foundation Project
- Basic Scientific Research Operating Expenses Project of Heilongjiang Province
Cite
APA
Hu, Q., Fu, X., Sun, D., Xu, D., & Guan, Y. (2024). A Lightweight Rolling Bearing Fault Diagnosis Method Based on Multiscale Depth-Wise Separable Convolutions and Network Pruning. IEEE Access, 12, 186131-186144. https://doi.org/10.1109/access.2024.3441232
Vancouver
Hu Q, Fu X, Sun D, Xu D, Guan Y. A Lightweight Rolling Bearing Fault Diagnosis Method Based on Multiscale Depth-Wise Separable Convolutions and Network Pruning. IEEE Access. 2024;12:186131-186144. doi:10.1109/access.2024.3441232
BibTeX
@article{Hu2024,
author = {Hu, Qingming and Fu, Xinjie and Sun, Dandan and Xu, Donghui and Guan, Yanqi},
title = {A Lightweight Rolling Bearing Fault Diagnosis Method Based on Multiscale Depth-Wise Separable Convolutions and Network Pruning},
journal = {IEEE Access},
year = {2024},
volume = {12},
pages = {186131--186144},
doi = {10.1109/access.2024.3441232}
}
EUVIMED