EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Insulator Defect Detection Based on ML-YOLOv5 Algorithm

Tong Wang, Yidi Zhai iD, Yuhang Li, Weihua Wang iD, Guoyong Ye, Shaobo Jin

Sensors · 29.12.2023 · 24 (1) · 204

DOI: 10.3390/s24010204 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.12.2023. Verfasst von Tong Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Henan Key Laboratory of Intelligent Manufacturing of Mechanical Equipment, Zhengzhou University of Light Industry, Zhengzhou 450002, China. Die Arbeit wurde bisher 53-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Henan, Key Research and Development Projects of Henan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of balancing accuracy and speed, as well as the parameters and FLOPs in current insulator defect detection, we propose an enhanced insulator defect detection algorithm, ML-YOLOv5, based on the YOLOv5 network. The backbone module incorporates depthwise separable convolution, and the feature fusion C3 module is replaced with the improved C2f_DG module. Furthermore, we enhance the feature pyramid network (MFPN) and employ knowledge distillation using YOLOv5m as the teacher model. Experimental results demonstrate that this approach achieved a 46.9% reduction in parameter count and a 43.0% reduction in FLOPs, while maintaining an FPS of 63.6. It exhibited good accuracy and detection speed on both the CPLID and IDID datasets, making it suitable for real-time inspection of high-altitude insulator defects.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismsconvolutional neural networksfeature fusionobject detection

Autor:innen und Institutionen

  • Henan Key Laboratory of Intelligent Manufacturing of Mechanical Equipment, Zhengzhou University of Light Industry, Zhengzhou 450002, China.
  • College of Mechanical and Electrical Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China.
  • China Special Equipment Inspection and Research Institute, Beijing 100029, China.

ORCID-Profile: Yidi Zhai, Weihua Wang

Förderung

  • Natural Science Foundation of Henan
  • Key Research and Development Projects of Henan Province

Zitieren

APA

Wang, T., Zhai, Y., Li, Y., Wang, W., Ye, G., & Jin, S. (2023). Insulator Defect Detection Based on ML-YOLOv5 Algorithm. Sensors, 24(1), 204. https://doi.org/10.3390/s24010204

Vancouver

Wang T, Zhai Y, Li Y, Wang W, Ye G, Jin S. Insulator Defect Detection Based on ML-YOLOv5 Algorithm. Sensors. 2023;24(1):204. doi:10.3390/s24010204

BibTeX
@article{Wang2023,
  author = {Wang, Tong and Zhai, Yidi and Li, Yuhang and Wang, Weihua and Ye, Guoyong and Jin, Shaobo},
  title = {Insulator Defect Detection Based on ML-YOLOv5 Algorithm},
  journal = {Sensors},
  year = {2023},
  volume = {24},
  number = {1},
  pages = {204},
  doi = {10.3390/s24010204}
}
Kostenlos starten →