EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Defect Detection Method of Carbon Fiber Unidirectional Band Prepreg Based on Enhanced YOLOv8s

Weipeng Su iD, Mei Sang iD, Yutong Liu iD, Xueming Wang iD

Sensors · 23.04.2025 · 25 (9) · 2665

DOI: 10.3390/s25092665 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.04.2025. Verfasst von Weipeng Su und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: AVIC Composite Corporation LTD, Research and Development funding of AVIC Composite Corporation LTD.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges in existing carbon fiber prepreg surface defect detection processes, specifically difficulties in small target detection and inaccuracies in elongated defects with large aspect ratios, this study proposes an enhanced YOLOv8s-based models for defect detection on the surface of carbon fiber unidirectional band prepreg. The proposed model respectively integrates two attention mechanisms, a Global Attention Mechanism (GAM) and a Deformable Large Kernel Attention (DLKA) Mechanism, into the architecture of YOLOv8s, which is a lightweight version of YOLO optimized for speed. The attention mechanisms are inserted between the backbone network and the detection head, respectively, to enhance feature extraction before target localization. The YOLOv8s-GAM model achieves a mean average precision (mAP@0.5) of 84.4%, precision of 79.3%, and recall of 78.3%, while the YOLOv8s-DLKA model shows improved performance with mAP@0.5 of 86.4%, precision of 82.4%, and recall of 80.2%. Compared with the original YOLOv8s model, these two modified models demonstrate improvements in mAP@0.5 of 1.6% and 3.6%, precision gains of 0.9% and 4.1%, and recall enhancements of 1.4% and 3.6%, respectively. These models provide technical solutions for precise defect identification on the surface of carbon fiber unidirectional band prepreg.

Schlagwörter

Stichwörter der Autor:innen

DLKAGAMYOLOv8scarbon Fiber unidirectional band prepregdeeplearningdefect detection

Autor:innen und Institutionen

  • School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China.
  • Key Laboratory of Opto-Electronics Information Technology, Ministry of Education, Tianjin 300072, China.
  • Composite Test Technology Center, AVIC Composite Corporation Ltd., Beijing 101300, China.

ORCID-Profile: Weipeng Su, Mei Sang, Yutong Liu, Xueming Wang

Förderung

  • AVIC Composite Corporation LTD
  • Research and Development funding of AVIC Composite Corporation LTD

Zitieren

APA

Su, W., Sang, M., Liu, Y., & Wang, X. (2025). Defect Detection Method of Carbon Fiber Unidirectional Band Prepreg Based on Enhanced YOLOv8s. Sensors, 25(9), 2665. https://doi.org/10.3390/s25092665

Vancouver

Su W, Sang M, Liu Y, Wang X. Defect Detection Method of Carbon Fiber Unidirectional Band Prepreg Based on Enhanced YOLOv8s. Sensors. 2025;25(9):2665. doi:10.3390/s25092665

BibTeX
@article{Su2025,
  author = {Su, Weipeng and Sang, Mei and Liu, Yutong and Wang, Xueming},
  title = {Defect Detection Method of Carbon Fiber Unidirectional Band Prepreg Based on Enhanced YOLOv8s},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {9},
  pages = {2665},
  doi = {10.3390/s25092665}
}
Kostenlos starten →