EUVIMEDEUVIMED entdecken
Crossref

A multi-scale defect detection network for wind turbines utilizing margin aware features

Yuxin Si, Yunfei Ding, Fudi Ge, Xingtao Wu, Jinglin Liu, Dong Ding, Hongwei Zhang

Measurement Science and Technology · 30.09.2025 · 36 (9) · 095416

DOI: 10.1088/1361-6501/ae08db ↗

Kurz gefasst

Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 29.09.2025. Verfasst von Yuxin Si und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Dong Ding.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The long-term operation of wind turbines (WTs) leads to multi-scale surface defects that critically compromise operational reliability. Drone-based defect detection offers a viable approach for real-time assessment of WT operational status. However, the current deployment of UAV-based detection systems struggles to simultaneously achieve both sensitivity and positioning accuracy for such multi-scale defects. To address this limitation, we propose a novel defect marginal-aware and multi-scale collaborative attention network (DMCA-Net). First, we propose a defect marginal detail transfer backbone to enhance edge information in shallow features, which can be fused with multi-scale features. Second, a triple-layer anchor attention feature selection and fusion pyramid network is introduced to optimize channel-space interactions, which can dynamically balance local details and global features, thereby improving defect localization accuracy. In addition, a histogram-based synergistic attention head encoder is designed to detect small object defects by co-optimizing frequency-domain split-box attention and cross-box attention to enhance the feature intensity of small object defects. Finally, the Normalized Wasserstein Distance–Inner Distance–IoU (NWD-InnerDIoU) loss is introduced to enhance model generalization and mitigate severe data imbalance, effectively reducing performance fluctuations resulting from interactions among multi-scale targets. Experimental results demonstrate that DMCA-Net achieves state-of-the-art performance with 83.1% mAP50, representing a 3.1% improvement over baseline, while maintaining real-time detection capability at 81.3 frames-per-second on the WT defect dataset. Especially, it outperforms commonly used detection models in terms of detection performance.

Förderung

  • Dong Ding

Zitieren

APA

Si, Y., Ding, Y., Ge, F., Wu, X., Liu, J., Ding, D., & Zhang, H. (2025). A multi-scale defect detection network for wind turbines utilizing margin aware features. Measurement Science and Technology, 36(9), 095416. https://doi.org/10.1088/1361-6501/ae08db

Vancouver

Si Y, Ding Y, Ge F, Wu X, Liu J, Ding D, et al. A multi-scale defect detection network for wind turbines utilizing margin aware features. Measurement Science and Technology. 2025;36(9):095416. doi:10.1088/1361-6501/ae08db

BibTeX
@article{Si2025,
  author = {Si, Yuxin and Ding, Yunfei and Ge, Fudi and Wu, Xingtao and Liu, Jinglin and Ding, Dong and Zhang, Hongwei},
  title = {A multi-scale defect detection network for wind turbines utilizing margin aware features},
  journal = {Measurement Science and Technology},
  year = {2025},
  volume = {36},
  number = {9},
  pages = {095416},
  doi = {10.1088/1361-6501/ae08db}
}
Kostenlos starten →