AWCDN: an interpretable transferable Siamese network model for few-shot fault diagnosis
Measurement Science and Technology · 30.06.2025 · 36 (6) · 066131
DOI: 10.1088/1361-6501/ade0e2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 12.06.2025. Verfasst von Sun Fenghao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: Jilin Province Science and Technology Development Plan Program, General Technology Group Science and Technology Major Project.
Abstract (Originalsprache)
In engineering, fault diagnosis faces numerous challenges, including scarcity of fault samples, noise interference, and variations in operating conditions, which significantly degrade the performance of traditional deep learning methods. To address these issues, this paper proposes an Adaptive wavelet contrastive diagnosis network. Firstly, a transferable adaptive laplace wavelet convolution layer is designed, which effectively enhances the model’s generalization ability and transfer learning capability under different operating conditions by dynamically adjusting the kernel function parameters. Secondly, a discrete wavelet transform layer is introduced to convert time-domain signals into the wavelet domain, capturing more refined fault features. Finally, convolutional layers are utilized to extract features from the wavelet-domain signals, and fault classification is achieved through similarity comparison. Experimental results on two bearing datasets demonstrate that the proposed method outperforms seven other advanced deep learning models, exhibiting excellent noise robustness and cross-domain transfer learning capability.
Förderung
- Jilin Province Science and Technology Development Plan Program
- General Technology Group Science and Technology Major Project
Zitieren
APA
Fenghao, S., Guofa, L., Jialong, H., & Shaoyang, L. (2025). AWCDN: an interpretable transferable Siamese network model for few-shot fault diagnosis. Measurement Science and Technology, 36(6), 066131. https://doi.org/10.1088/1361-6501/ade0e2
Vancouver
Fenghao S, Guofa L, Jialong H, Shaoyang L. AWCDN: an interpretable transferable Siamese network model for few-shot fault diagnosis. Measurement Science and Technology. 2025;36(6):066131. doi:10.1088/1361-6501/ade0e2
BibTeX
@article{Fenghao2025,
author = {Fenghao, Sun and Guofa, Li and Jialong, He and Shaoyang, Liu},
title = {AWCDN: an interpretable transferable Siamese network model for few-shot fault diagnosis},
journal = {Measurement Science and Technology},
year = {2025},
volume = {36},
number = {6},
pages = {066131},
doi = {10.1088/1361-6501/ade0e2}
}
EUVIMED