EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Similarity-aware VAE with wavelet-convolutional 1D-CNN for rolling bearing fault diagnosis

Wei Xiong iD, Na Xiao, Ruili Wang

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

Wavelet AnalysisNeural Networks, ComputerDeep LearningAlgorithmsHumans

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}
}
Kostenlos starten →