A Multi-scale Defect Detection Network for Wind Turbines Utilizing Margin Aware Features

SI, Yuxin, DING, Yunfei, GE, FuDi, WU, Xingtao, LIU, Jinglin, DING, Dong and ZHANG, Hongwei (2025). A Multi-scale Defect Detection Network for Wind Turbines Utilizing Margin Aware Features. Measurement Science and Technology, 36 (9): 095416. [Article]

Documents
36184:1050198
[thumbnail of Si+et+al_2025_Meas._Sci._Technol._10.1088_1361-6501_ae08db.pdf]
Preview
PDF
Si+et+al_2025_Meas._Sci._Technol._10.1088_1361-6501_ae08db.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (2MB) | Preview
Abstract
The long-term operation of wind turbines (WTs) leads to multi-scale surface defects that critically compromise operational reliability. Drone-based defect detection offers a viable approach for real-time assessment of WT operational status. However, the current deployment of UAV-based detection systems struggles to simultaneously achieve both sensitivity and positioning accuracy for such multi-scale defects. To address this limitation, we propose a novel Defect Marginal-aware and Multi-scale Collaborative Attention Network (DMCA-Net). First, we propose a Defect Marginal Detail Transfer backbone (DMDT) to enhance edge information in shallow features, which can be fused with multi-scale features. Second, a Triple-layer Anchor Attention Feature Selection and Fusion Pyramid Network (TAAFSFPN) is introduced to optimize channel-space interactions, which can dynamically balance local details and global features, thereby improving defect localization accuracy. In addition, a Histogram-based Synergistic Attention Head encoder (HSAH) is designed to detect small object defects by co-optimizing frequency-domain split-box attention and cross-box attention to enhance the feature intensity of small object defects. Finally, the Normalized Wasserstein Distance–Inner Distance–IoU (NWD-InnerDIoU) loss is introduced to enhance model generalization and mitigate severe data imbalance, effectively reducing performance fluctuations resulting from interactions among multi-scale targets. Experimental results demonstrate that DMCA-Net achieves state-of-the-art performance with 83.1% mAP50, representing a 3.1% improvement over baseline, while maintaining real-time detection capability at 81.3 FPS on the WT defect dataset. Especially, it outperforms commonly used detection models in terms of detection performance.
More Information
Statistics

Downloads

Downloads per month over past year

View more statistics

Metrics

Altmetric Badge

Dimensions Badge

Share
Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email

Actions (login required)

View Item View Item