EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable and Noise-Robust Bearing Fault Diagnosis for CNC Machine Tools via Adaptive Shapelet-Based Deep Learning Model

Weiqi Hu, Huicheng Zhou, Jianzhong Yang

Machines · 12.02.2026 · 14 (2) · 214

DOI: 10.3390/machines14020214 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 12.02.2026. Verfasst von Weiqi Hu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Center of Technology Innovation for Intelligent Design and Numerical Control (NCDC), Huazhong University of Science and Technology, Huazhong University of Science and Technology, China, Wuhan Huazhong Numerical Control System, Inc., China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rolling bearings are crucial components in CNC machine tool spindles, and their health condition directly affects machining precision and operational reliability. To address the significant challenges of bearing fault diagnosis in industrial environments, this paper proposes an adaptive shapelet-based deep learning model for bearing fault diagnosis. The proposed model integrates three key components: (1) an adaptive multi-scale shapelet extraction module for discriminative pattern learning, (2) a gated parallel CNN with depthwise separable convolutions for multi-scale spatial feature extraction, (3) an enhanced bidirectional long short-term memory network with residual connections for temporal dependency modeling. A composite loss function combining cross-entropy, supervised contrastive learning, and multi-scale consistency regularization is employed for training. To simulate real-world industrial noise conditions, Gaussian, uniform, and impulse noise were injected into the signals. Experiments conducted on the CWRU and IMS datasets demonstrate that, compared with state-of-the-art methods, the proposed approach achieves stronger noise robustness, higher fault classification accuracy, and more stable performance under severe noise contamination.

Förderung

  • National Center of Technology Innovation for Intelligent Design and Numerical Control (NCDC), Huazhong University of Science and Technology
  • Huazhong University of Science and Technology, China
  • Wuhan Huazhong Numerical Control System, Inc., China

Zitieren

APA

Hu, W., Zhou, H., & Yang, J. (2026). Interpretable and Noise-Robust Bearing Fault Diagnosis for CNC Machine Tools via Adaptive Shapelet-Based Deep Learning Model. Machines, 14(2), 214. https://doi.org/10.3390/machines14020214

Vancouver

Hu W, Zhou H, Yang J. Interpretable and Noise-Robust Bearing Fault Diagnosis for CNC Machine Tools via Adaptive Shapelet-Based Deep Learning Model. Machines. 2026;14(2):214. doi:10.3390/machines14020214

BibTeX
@article{Hu2026,
  author = {Hu, Weiqi and Zhou, Huicheng and Yang, Jianzhong},
  title = {Interpretable and Noise-Robust Bearing Fault Diagnosis for CNC Machine Tools via Adaptive Shapelet-Based Deep Learning Model},
  journal = {Machines},
  year = {2026},
  volume = {14},
  number = {2},
  pages = {214},
  doi = {10.3390/machines14020214}
}
Kostenlos starten →