Similarity-aware VAE with wavelet-convolutional 1D-CNN for rolling bearing fault diagnosis
PLOS One · 05.01.2026 · 21 (1) · e0338388
DOI: 10.1371/journal.pone.0338388 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 05.01.2026. Verfasst von Wei Xiong und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Engineering, Huanghe Science and Technology College, Zhengzhou City, China. Hauptthemen laut MEDLINE: Wavelet Analysis, Neural Networks, Computer, Deep Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National College Students' Innovation Training Program project.
Abstract (Originalsprache)
To address the uneven distribution of fault categories in data sets for deep learning-based fault diagnosis, we propose a fault diagnosis framework combining an improved Variational Autoencoder (Similarity-Aware VAE) with a Wavelet-Convolutional 1D-CNN. The Similarity-Aware VAE employs a novel similarity loss function for data augmentation, measuring feature distances in high-dimensional space while automatically adjusting training parameters and weights through an enhanced attention mechanism to balance the dataset.The Wavelet-Convolutional 1D-CNN replaces the first convolutional layer of CNN with a Wavelet-Convolutional layer based on continuous wavelet transform, enabling multi-scale feature extraction for fault data analysis. Experimental validation using public datasets demonstrates that this method effectively enhances data quality while maintaining robust diagnostic performance, offering practical implications for industrial fault diagnosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Faculty of Engineering, Huanghe Science and Technology College, Zhengzhou City, China.
ORCID-Profile: Wei Xiong
Förderung
- National College Students' Innovation Training Program project
Zitieren
APA
Xiong, W., Xiao, N., & Wang, R. (2026). Similarity-aware VAE with wavelet-convolutional 1D-CNN for rolling bearing fault diagnosis. PLOS One, 21(1), e0338388. https://doi.org/10.1371/journal.pone.0338388
Vancouver
Xiong W, Xiao N, Wang R. Similarity-aware VAE with wavelet-convolutional 1D-CNN for rolling bearing fault diagnosis. PLOS One. 2026;21(1):e0338388. doi:10.1371/journal.pone.0338388
BibTeX
@article{Xiong2026,
author = {Xiong, Wei and Xiao, Na and Wang, Ruili},
title = {Similarity-aware VAE with wavelet-convolutional 1D-CNN for rolling bearing fault diagnosis},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {1},
pages = {e0338388},
doi = {10.1371/journal.pone.0338388}
}
EUVIMED