Enhancing wind turbine blade damage detection with YOLO-Wind

Abstract This study presents an enhanced YOLOv8n framework for wind turbine surface damage detection, achieving 83.9% mAP@0.5 on the DTU dataset—a 2.3% improvement over baseline models. The architecture replaces standard convolutions with depthwise separable convolutions (DWConv) to optimize computa...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhao Zhanfang, Li Tuo
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-03639-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850231489847885824
author Zhao Zhanfang
Li Tuo
author_facet Zhao Zhanfang
Li Tuo
author_sort Zhao Zhanfang
collection DOAJ
description Abstract This study presents an enhanced YOLOv8n framework for wind turbine surface damage detection, achieving 83.9% mAP@0.5 on the DTU dataset—a 2.3% improvement over baseline models. The architecture replaces standard convolutions with depthwise separable convolutions (DWConv) to optimize computational efficiency without compromising detection accuracy. The C2f module is restructured by integrating MobileNetV2’s MBConv blocks with efficient channel attention (ECA), which improves gradient flow and enhances discriminative feature extraction for sub-pixel defects. Furthermore, a newly added P2 detection layer enhances multi-scale defect recognition in complex environments. Cross-dataset evaluations validate the model’s robustness and adaptability, with 15.2–16.3% mAP@0.5 improvements in blade damage detection and a 3.1% accuracy gain in agricultural defect identification. Although the performance on steel surface datasets varies, the systematic integration of DWConv, MBConv, and ECA mechanisms establishes a methodological advancement for industrial vision applications. The proposed framework demonstrates an effective trade-off between precision and efficiency, contributing to real-world computer vision solutions for wind energy infrastructure maintenance.
format Article
id doaj-art-72f0248f52ba483caa0d565b8556daa1
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-72f0248f52ba483caa0d565b8556daa12025-08-20T02:03:31ZengNature PortfolioScientific Reports2045-23222025-05-0115112610.1038/s41598-025-03639-8Enhancing wind turbine blade damage detection with YOLO-WindZhao Zhanfang0Li Tuo1School of Information Engineering, Hebei GEO UniversitySchool of Information Engineering, Hebei GEO UniversityAbstract This study presents an enhanced YOLOv8n framework for wind turbine surface damage detection, achieving 83.9% mAP@0.5 on the DTU dataset—a 2.3% improvement over baseline models. The architecture replaces standard convolutions with depthwise separable convolutions (DWConv) to optimize computational efficiency without compromising detection accuracy. The C2f module is restructured by integrating MobileNetV2’s MBConv blocks with efficient channel attention (ECA), which improves gradient flow and enhances discriminative feature extraction for sub-pixel defects. Furthermore, a newly added P2 detection layer enhances multi-scale defect recognition in complex environments. Cross-dataset evaluations validate the model’s robustness and adaptability, with 15.2–16.3% mAP@0.5 improvements in blade damage detection and a 3.1% accuracy gain in agricultural defect identification. Although the performance on steel surface datasets varies, the systematic integration of DWConv, MBConv, and ECA mechanisms establishes a methodological advancement for industrial vision applications. The proposed framework demonstrates an effective trade-off between precision and efficiency, contributing to real-world computer vision solutions for wind energy infrastructure maintenance.https://doi.org/10.1038/s41598-025-03639-8Wind turbineYOLOv8nDepthwise separable convolutionsEfficient channel attentionDamage detection
spellingShingle Zhao Zhanfang
Li Tuo
Enhancing wind turbine blade damage detection with YOLO-Wind
Scientific Reports
Wind turbine
YOLOv8n
Depthwise separable convolutions
Efficient channel attention
Damage detection
title Enhancing wind turbine blade damage detection with YOLO-Wind
title_full Enhancing wind turbine blade damage detection with YOLO-Wind
title_fullStr Enhancing wind turbine blade damage detection with YOLO-Wind
title_full_unstemmed Enhancing wind turbine blade damage detection with YOLO-Wind
title_short Enhancing wind turbine blade damage detection with YOLO-Wind
title_sort enhancing wind turbine blade damage detection with yolo wind
topic Wind turbine
YOLOv8n
Depthwise separable convolutions
Efficient channel attention
Damage detection
url https://doi.org/10.1038/s41598-025-03639-8
work_keys_str_mv AT zhaozhanfang enhancingwindturbinebladedamagedetectionwithyolowind
AT lituo enhancingwindturbinebladedamagedetectionwithyolowind