EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Wind Turbine Blade Defect Recognition Method Based on Large-Vision-Model Transfer Learning

Xin Li, Jinghe Tian iD, Xinfu Pang iD, Li Shen, Haibo Li iD, Zedong Zheng

Sensors · 15.07.2025 · 25 (14) · 4414

DOI: 10.3390/s25144414 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.07.2025. Verfasst von Xin Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Energy Saving and Controlling in Power System of Liaoning Province, Shenyang Institute of Engineering, Shenyang 110136, China. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Liaoning Province, China, Department of Education of Liaoning Province, China, Shenyang Science and Technology Plan Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Timely and accurate detection of wind turbine blade surface defects is crucial for ensuring operational safety and improving maintenance efficiency with respect to large-scale wind farms. However, existing methods often suffer from poor generalization, background interference, and inadequate real-time performance. To overcome these limitations, we developed an end-to-end defect recognition framework, structured as a three-stage process: blade localization using YOLOv5, robust feature extraction via the large vision model DINOv2, and defect classification using a Stochastic Configuration Network (SCN). Unlike conventional CNN-based approaches, the use of DINOv2 significantly improves the capability for representation under complex textures. The experimental results reveal that the proposed method achieved a classification accuracy of 97.8% and an average inference time of 19.65 ms per image, satisfying real-time requirements. Compared to traditional methods, this framework provides a more scalable, accurate, and efficient solution for the intelligent inspection and maintenance of wind turbine blades.

Schlagwörter

Stichwörter der Autor:innen

DINOv2Stochastic Configuration NetworkYOLOv5 networkdefect detectionwind blades

Autor:innen und Institutionen

  • Key Laboratory of Energy Saving and Controlling in Power System of Liaoning Province, Shenyang Institute of Engineering, Shenyang 110136, China.
  • School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, UK.

ORCID-Profile: Jinghe Tian, Xinfu Pang, Haibo Li

Förderung

  • Natural Science Foundation of Liaoning Province, China
  • Department of Education of Liaoning Province, China
  • Shenyang Science and Technology Plan Project

Zitieren

APA

Li, X., Tian, J., Pang, X., Shen, L., Li, H., & Zheng, Z. (2025). Wind Turbine Blade Defect Recognition Method Based on Large-Vision-Model Transfer Learning. Sensors, 25(14), 4414. https://doi.org/10.3390/s25144414

Vancouver

Li X, Tian J, Pang X, Shen L, Li H, Zheng Z. Wind Turbine Blade Defect Recognition Method Based on Large-Vision-Model Transfer Learning. Sensors. 2025;25(14):4414. doi:10.3390/s25144414

BibTeX
@article{Li2025,
  author = {Li, Xin and Tian, Jinghe and Pang, Xinfu and Shen, Li and Li, Haibo and Zheng, Zedong},
  title = {Wind Turbine Blade Defect Recognition Method Based on Large-Vision-Model Transfer Learning},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {14},
  pages = {4414},
  doi = {10.3390/s25144414}
}
Kostenlos starten →