What question did this study set out to answer?

This research aims to evaluate the effectiveness of various deep learning models for detecting defects in wind turbine blades.

Comparison study of advanced computer vision models for wind turbine blade defect detection

View Full Paper

Ask AI

Bookmark

Authors

Comparison study shows deep learning models improve defect detection in wind turbines, suggesting synthetic data enhances performance.

This research aims to evaluate the effectiveness of various deep learning models for detecting defects in wind turbine blades.
Evaluated single-stage (YOLOv8, YOLOv9, YOLOv10, YOLOv11) and two-stage (Faster R-CNN) models.
Applied StyleGAN2-ADA for data augmentation to address class imbalance.
Assessed detection accuracy, inference speed, and model size using stratified cross-validation.
YOLO models achieved higher mean Average Precision compared to Faster R-CNN.
YOLOv11 had the highest mAP@0.5 score of 0.969 on the holdout test set.
Synthetic data improved performance for minority classes and reduced variance.

Lateef et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark