EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Scale Dual-Attention Feature Network with Bidirectional Temporal Constraints for Tool Wear Monitoring

Youqiang Xu, Rongyi Li, Xianli Liu, Haotuo Liu, Ying Wang, Xiaohua Liu, Yuqiang Gan

Coatings · 27.02.2026 · 16 (3) · 291

DOI: 10.3390/coatings16030291 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Coatings, online erschienen am 27.02.2026. Verfasst von Youqiang Xu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Heilongjiang Natural Science Foundation Outstanding youth project, National Natural Science Foundation of China, “Chunyan” Team Support Plan Project of Heilongjiang.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate tool wear monitoring plays a decisive role in machining efficiency, product quality and reliability in modern manufacturing systems. Existing deep learning methods struggle to balance the high-frequency transient features and low-frequency evolution trends in tool wear signals, often losing key temporal evolution details when processing long-range degradation data. Therefore, this paper proposes an online prediction method of tool wear value that combines multi-scale convolution and dual-attention temporal features. This method extracts local mutation and trend features in wear signals through multi-scale convolution, captures wear evolution features through bidirectional cyclic network, and adaptively fuses local detail information and global trend through dual attention mechanism SWGC-DA to generate a multi-scale time series feature-driven prediction model. The ablation experiment based on the PHM2010 public data set verifies the effectiveness of the network structure design and demonstrates the model’s superior predictive ability. Experiments on the self-built TiAl alloy milling dataset achieved a stable prediction of R2 up to 99.1%, with MAE and RMSE of 2.29 and 2.47, respectively. The results show that this method significantly improves the accuracy and robustness of wear prediction.

Förderung

  • Heilongjiang Natural Science Foundation Outstanding youth project
  • National Natural Science Foundation of China
  • “Chunyan” Team Support Plan Project of Heilongjiang
  • Opening Project of the Key Laboratory of Advanced Processing Technology and Intelligent Manufacturing (Heilongjiang Province), Harbin University of Science and…

Zitieren

APA

Xu, Y., Li, R., Liu, X., Liu, H., Wang, Y., Liu, X., & Gan, Y. (2026). Multi-Scale Dual-Attention Feature Network with Bidirectional Temporal Constraints for Tool Wear Monitoring. Coatings, 16(3), 291. https://doi.org/10.3390/coatings16030291

Vancouver

Xu Y, Li R, Liu X, Liu H, Wang Y, Liu X, et al. Multi-Scale Dual-Attention Feature Network with Bidirectional Temporal Constraints for Tool Wear Monitoring. Coatings. 2026;16(3):291. doi:10.3390/coatings16030291

BibTeX
@article{Xu2026,
  author = {Xu, Youqiang and Li, Rongyi and Liu, Xianli and Liu, Haotuo and Wang, Ying and Liu, Xiaohua and Gan, Yuqiang},
  title = {Multi-Scale Dual-Attention Feature Network with Bidirectional Temporal Constraints for Tool Wear Monitoring},
  journal = {Coatings},
  year = {2026},
  volume = {16},
  number = {3},
  pages = {291},
  doi = {10.3390/coatings16030291}
}
Kostenlos starten →