Wind Turbine Blades Defect Detection Based on Improved YOLOv8
Sensors and Materials · 2026-05-12 · 38 (5) · 2381
DOI: 10.18494/sam5877 ↗At a glance
Journal article in Sensors and Materials, published on 2026-05-12. Written by Wen Wang and 8 co-authors.
Abstract (original language)
for bounding box regression, which significantly improves detection performance for small targets while ensuring regression accuracy and stability. Experimental results on a wind turbine blade crack defect dataset demonstrate that the proposed method achieves improvements in precision of 9.3% and in mean average precision of 7.3% compared with the baseline YOLOv8 model. These findings validate that the enhanced You Only Look Once v8 (YOLOv8) detection method exhibits superior detection effectiveness, accuracy, and reliability.
Cite
APA
Wang, W., Xiao, L., He, L., Jiang, J., Lyu, Y., Zou, W., Xiong, H., Chi, B., & Fu, W. (2026). Wind Turbine Blades Defect Detection Based on Improved YOLOv8. Sensors and Materials, 38(5), 2381. https://doi.org/10.18494/sam5877
Vancouver
Wang W, Xiao L, He L, Jiang J, Lyu Y, Zou W, et al. Wind Turbine Blades Defect Detection Based on Improved YOLOv8. Sensors and Materials. 2026;38(5):2381. doi:10.18494/sam5877
BibTeX
@article{Wang2026,
author = {Wang, Wen and Xiao, Litao and He, Lifu and Jiang, Ji and Lyu, Yang and Zou, Wen and Xiong, Haowei and Chi, Baotong and Fu, Wenlong},
title = {Wind Turbine Blades Defect Detection Based on Improved YOLOv8},
journal = {Sensors and Materials},
year = {2026},
volume = {38},
number = {5},
pages = {2381},
doi = {10.18494/sam5877}
}
EUVIMED