[1]李冰,魏乐涛,张易牧,等.融合边缘增强与多尺度特征聚合的风机叶片缺陷检测算法[J].智能系统学报,2026,21(3):701-712.[doi:10.11992/tis.202504011]
LI Bing,WEI Letao,ZHANG Yimu,et al.Algorithm for wind turbine blade defect detection by integrating edge enhancement and multi-scale feature aggregation[J].CAAI Transactions on Intelligent Systems,2026,21(3):701-712.[doi:10.11992/tis.202504011]
点击复制
LI Bing,WEI Letao,ZHANG Yimu,et al.Algorithm for wind turbine blade defect detection by integrating edge enhancement and multi-scale feature aggregation[J].CAAI Transactions on Intelligent Systems,2026,21(3):701-712.[doi:10.11992/tis.202504011]
融合边缘增强与多尺度特征聚合的风机叶片缺陷检测算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
21
期数:
2026年第3期
页码:
701-712
栏目:
学术论文—机器感知与模式识别
出版日期:
2026-05-05
- Title:
- Algorithm for wind turbine blade defect detection by integrating edge enhancement and multi-scale feature aggregation
- Keywords:
- wind turbine blade; defect detection; irregular defects; complex backgrounds; small targets; adaptive multi-head attention; feature aggregation; deep convolution
- 分类号:
- TP183
- 文献标志码:
- 2026-3-13
- 摘要:
- 在对风机叶片进行无人机巡检的过程中，航拍图像往往存在背景复杂、目标小、尺度不一、形态不规则等问题，导致现有的目标检测算法出现漏检和误检现象的频率较高。为解决以上问题，提出了一种融合边缘增强与多尺度特征聚合的风机叶片缺陷检测算法。本文提出边缘增强特征提取(edge-enhanced feature extraction, EEFE)模块，使模型能够更精准地感知目标边界，从而提升模型对不规则缺陷的特征提取能力；设计自适应多头注意力(adaptive multi-head attention, AMHA)并融入层级池化的SPPELAN结构，形成SPPELAN-AMHA模块，以增强模型对全局信息的捕获能力并降低复杂背景干扰；提出多尺度特征聚合(multi-scale feature aggregation, MFA)模块并设计一种全新的聚合扩散特征金字塔网络(aggregation diffusion feature pyramid network, ADFPN)，利用不同感受野的深度卷积提取多尺度上下文信息，改善模型对小目标的检测性能。实验表明，所提算法对表面侵蚀、裂纹和凝胶漆涂层脱落3类缺陷的AP值较原始的YOLOv8n模型分别提高1.7%、8.3%和4.1%，mAP50提高了4.7%，证明了所提算法对风机叶片缺陷检测的有效性。
- Abstract:
- Unmanned aerial vehicle (UAV) inspections of wind turbine blades yield aerial images characterized by complex backgrounds, small and variably scaled targets, and irregular defect shapes. These factors often cause high rates of missed detections and false alarms in existing object detection methods. To overcome these challenges, this study presents a novel defect detection framework that combines edge enhancement with multi-scale feature aggregation. First, an edge enhancement feature extraction (EEFE) module is proposed to improve the model’s ability to capture defect boundaries, thereby enhancing the representation of irregular defects. Next, an adaptive multi-head attention (AMHA) mechanism is integrated into a hierarchical spatial pyramid pooling efficient layer aggregation network (SPPELAN) architecture, forming the SPPELAN-AMHA module, which strengthens global context modeling and reduces interference from complex backgrounds. In addition, a multi-scale feature aggregation (MFA) module and an aggregation diffusion feature pyramid network (ADFPN) are designed to extract multi-scale contextual information through deep convolutions with diverse receptive fields, improving detection performance on small targets. Experimental results demonstrate that the proposed approach improves average precision by 1.7%, 8.3%, and 4.1% for surface erosion, crack, and gelcoat peeling defects, respectively, and achieves a 4.7% gain in mean average precision at intersection over union threshold 50 (mAP50) compared with the baseline YOLOv8n model, confirming its effectiveness for wind turbine blade defect detection.
- 参考文献/References:
-
[1] 曹锦纲, 杨国田, 杨锡运. 基于RPCA和视觉显著性的风机叶片表面缺陷检测[J]. 图学学报, 2019, 40(4): 704-710 CAO Jingang, YANG Guotian, YANG Xiyun. Surface defect detection of wind turbine blades based on RPCA and visual saliency[J]. Journal of graphics, 2019, 40(4): 704-710
[2] ROGA S, BARDHAN S, KUMAR Y, et al. Recent technology and challenges of wind energy generation: a review[J]. Sustainable energy technologies and assessments, 2022, 52: 102239
[3] WANG Wenjie, XUE Yu, HE Chengkuan, et al. Review of the typical damage and damage-detection methods of large wind turbine blades[J]. Energies, 2022, 15(15): 5672
[4] 白健鹏, 王巍, 陈雨溪, 等. 基于轻量型YOLOv5的风机桨叶检测与空间定位[J]. 智能系统学报, 2022, 17(6): 1173-1181 BAI Jianpeng, WANG Wei, CHEN Yuxi, et al. Detection and spatial location of wind turbine blades based on lightweight YOLOv5[J]. CAAI transactions on intelligent systems, 2022, 17(6): 1173-1181
[5] CHATTERJEE J, DETHLEFS N. Scientometric review of artificial intelligence for operations & maintenance of wind turbines: The past, present and future[J]. Renewable and sustainable energy reviews, 2021, 144: 111051
[6] 贺斌, 贾建华, 赵峰, 等. 无人机在风机叶片检测中的应用[J]. 电工技术, 2019(13): 64-65 HE Bin, JIA Jianhua, ZHAO Feng, et al. Application of UAV in detection of wind turbine blades[J]. Electric engineering, 2019(13): 64-65
[7] TCHERNIAK D, M?LGAARD L L. Active vibration-based structural health monitoring system for wind turbine blade: Demonstration on an operating Vestas V27 wind turbine[J]. Structural health monitoring, 2017, 16(5): 536-550
[8] 郑浩, 周丽婷, 王湘明, 等. 电磁超声检测风机叶片缺陷的有限元仿真研究[J]. 电子测量技术, 2021, 44(23): 24-29 ZHENG Hao, ZHOU Liting, WANG Xiangming, et al. Finite element simulation study on electromagnetic ultrasonic detection of wind turbine blade[J]. Electronic measurement technology, 2021, 44(23): 24-29
[9] 马敏敏, 刘昊, 高毓欣, 等. 基于无人机与人工智能的风机叶片全自主巡检[J]. 电气时代, 2023(S2): 44-48 MA Minmin, LIU Hao, GAO Yuxin, et al. Automatic inspection of fan blades based on UAV and artificial intelligence[J]. Electric age, 2023(S2): 44-48
[10] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Computer Vision–ECCV 2016. Cham: Springer, 2016: 21-37.
[11] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 779-788.
[12] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 6517-6525.
[13] REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. (2018-04-08)[2025-01-01]. https://arxiv.org/abs/1804.02767.
[14] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 580-587.
[15] GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2016: 1440-1448.
[16] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(6): 1137-1149
[17] ZHANG Chao, WEN Chuanbo, LIU Jihui. Mask-MRNet: a deep neural network for wind turbine blade fault detection[J]. Journal of renewable and sustainable energy, 2020, 12(5): 053302
[18] LYU Liang, YAO Zhongyuan, WANG Enming, et al. Efficient and accurate damage detector for wind turbine blade images[J]. IEEE access, 2022, 10: 123378-123386
[19] RAN Xiukang, ZHANG Shang, WANG Hengtao, et al. An improved algorithm for wind turbine blade defect detection[J]. IEEE access, 2022, 10: 122171-122181
[20] 汤占军, 张朝杰, 王健, 等. 基于改进YOLOv7的风机叶片缺陷检测研究[J/OL]. 北京航空航天大学学报, 1-15. TANG Zhanjun, ZHANG Chaojie, WANG Jian, et al. Research on wind turbine blade defect detection based on improved Yolov7[J/OL]. Journal of Beijing University of Aeronautics and Astronautics, 1-15.
[21] 付军军, 陈林, 童华敏, 等. 基于改进EfficientNet的海上风机叶片早期缺陷检测及分类[J]. 电子测量技术, 2024, 47(16): 110-119 FU Junjun, CHEN Lin, TONG Huamin, et al. Early defect detection and classification of offshore wind turbine blades based on improved EfficientNet[J]. Electronic measurement technology, 2024, 47(16): 110-119
[22] BOCHKOVSKIY A, WANG C Y, LIAO H M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. (2020-04-23)[2025-01-01]. https://arxiv.org/abs/2004.10934.
[23] LIN T Y, DOLL?R P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 936-944.
[24] 闫建红, 冉同霄. 基于YOLOv8的轻量化无人机图像目标检测算法[J]. 图学学报, 2024, 45(6): 1328-1337 YAN Jianhong, RAN Tongxiao. Lightweight UAV image target detection algorithm based on YOLOv8[J]. Journal of graphics, 2024, 45(6): 1328-1337
[25] 赵振兵, 郭广学, 王艺衡, 等. 融合边缘感知与统计纹理知识的输电线路金具锈蚀检测[J]. 智能系统学报, 2024, 19(5): 1228-1237 ZHAO Zhenbing, GUO Guangxue, WANG Yiheng, et al. Rust detection in transmission line fittings via fusion of edge perception and statistical texture knowledge[J]. CAAI transactions on intelligent systems, 2024, 19(5): 1228-1237
[26] CHOLLET F. Xception: deep learning with depthwise separable convolutions[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 1800-1807.
[27] 赵振兵, 韩钰, 唐辰康. 基于改进YOLOv8的配电线路绝缘子缺陷级联检测方法[J]. 图学学报, 2025, 46(1): 1-12 ZHAO Zhenbing, HAN Yu, TANG Chenkang. Cascade detection method for insulator defects in distribution lines based on improved YOLOv8[J]. Journal of graphics, 2025, 46(1): 1-12
[28] WANG C Y, YEH I H, MARK LIAO H Y. YOLOv9: learning what you want toLearn using programmable gradient information[C]//Computer Vision–ECCV 2024. Cham: Springer, 2025: 1-21.
[29] YANG Guoyu, LEI Jie, ZHU Zhikuan, et al. AFPN: asymptotic feature pyramid network for object detection[C]//2023 IEEE International Conference on Systems, Man, and Cybernetics. Honolulu: IEEE, 2024: 2184-2189.
[30] TAN Mingxing, PANG Ruoming, LE Q V. EfficientDet: scalable and efficient object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 10778-10787.
[31] 凌均健, 徐东华, 朱胜山, 等. 改进YOLOv8的无人机建筑外墙缺陷检测方法[J/OL]. 光通信研究, 1-9. LING Junjian, XU Donghua, ZHU Shengshan, et al. Improved UAV-Based Building Facade Defect Detection Method Using YOLOv8[J/OL]. Study on optical communications, 1-9.
[32] ZHAO Yian, LYU Wenyu, XU Shangliang, et al. DETRs beat YOLOs on real-time object detection[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 16965-16974.
- 相似文献/References:
-
[1]吴家伟,严京旗,方志宏,等.基于图像显著性特征的铸坯表面缺陷检测[J].智能系统学报,2012,7(1):75.
WU Jiawei,YAN Jingqi,FANG Zhihong,et al.Defect detection on a steel slab surface based on the characteristics of an image’s saliency region[J].CAAI Transactions on Intelligent Systems,2012,7():75.
[2]逄增治,郑修楠,李金屏.全钢子午线轮胎X光图像的缺陷检测研究现状[J].智能系统学报,2019,14(4):793.[doi:10.11992/tis.201806014]
PANG Zengzhi,ZHENG Xiunan,LI Jinping.Research status of defect detection in X-ray images of all-steel radial tires[J].CAAI Transactions on Intelligent Systems,2019,14():793.[doi:10.11992/tis.201806014]
[3]王凯旋,任福继,倪红军,等.面向电力设备红外图像的温度值识别算法[J].智能系统学报,2022,17(3):617.[doi:10.11992/tis.202105043]
WANG Kaixuan,REN Fuji,NI Hongjun,et al.Temperature value recognition algorithm for the infrared image of power equipment[J].CAAI Transactions on Intelligent Systems,2022,17():617.[doi:10.11992/tis.202105043]
[4]戚银城,耿劭锋,赵振兵,等.基于特征迁移的螺栓图像超分辨率处理方法[J].智能系统学报,2023,18(4):858.[doi:10.11992/tis.202201009]
QI Yincheng,GENG Shaofeng,ZHAO Zhenbing,et al.A method for super resolution processing of bolt image based on feature transfer[J].CAAI Transactions on Intelligent Systems,2023,18():858.[doi:10.11992/tis.202201009]
[5]高海洋,张明川,葛泉波,等.基于点集匹配的缺陷样本图像生成方法[J].智能系统学报,2023,18(5):1030.[doi:10.11992/tis.202209028]
GAO Haiyang,ZHANG Mingchuan,GE Quanbo,et al.Method of defect sample image generation based on point set matching[J].CAAI Transactions on Intelligent Systems,2023,18():1030.[doi:10.11992/tis.202209028]
[6]王延春秋,葛泉波,刘华平.石板材表面缺陷检测的无监督学习方法[J].智能系统学报,2023,18(6):1344.[doi:10.11992/tis.202212006]
WANG Yanchunqiu,GE Quanbo,LIU Huaping.Unsupervised learning method for surface defect detection of slate materials[J].CAAI Transactions on Intelligent Systems,2023,18():1344.[doi:10.11992/tis.202212006]
[7]吴瑞林,葛泉波,刘华平.基于YOLOX的类增量印刷电路板缺陷检测方法[J].智能系统学报,2024,19(4):1061.[doi:10.11992/tis.202309044]
WU Ruilin,GE Quanbo,LIU Huaping.Class-incremental printed circuit board defect detection method based on YOLOX[J].CAAI Transactions on Intelligent Systems,2024,19():1061.[doi:10.11992/tis.202309044]
[8]吴一全,庞雅轩.手机表面缺陷的机器视觉检测方法研究进展[J].智能系统学报,2025,20(1):33.[doi:10.11992/tis.202312036]
WU Yiquan,PANG Yaxuan.Research progress of mobile phone surface defect detection based on machine vision[J].CAAI Transactions on Intelligent Systems,2025,20():33.[doi:10.11992/tis.202312036]
[9]杨奡飞,续欣莹,谢刚,等.印刷电路板缺陷持续检测与定位方法研究[J].智能系统学报,2025,20(1):219.[doi:10.11992/tis.202310024]
YANG Aofei,XU Xinying,XIE Gang,et al.Research on continual detection and localization method for printed circuit board defect[J].CAAI Transactions on Intelligent Systems,2025,20():219.[doi:10.11992/tis.202310024]
[10]蒋世杰,夏秀山,翟伟,等.基于ODE扩散模型的多类异常检测和定位[J].智能系统学报,2025,20(2):376.[doi:10.11992/tis.202402022]
JIANG Shijie,XIA Xiushan,ZHAI Wei,et al.ODE diffusion model for multiclass anomaly detection and localization[J].CAAI Transactions on Intelligent Systems,2025,20():376.[doi:10.11992/tis.202402022]
备注/Memo
收稿日期:2025-4-18。
基金项目:国家自然科学基金项目(62373151)；国家自然科学基金联合基金重点支持项目(U21A20486)；河北省自然科学基金项目(F2023502010)；中央高校基本科研业务费专项(2024MS136).
作者简介:李冰，副教授，博士，主要研究方向为模式识别与计算机视觉。主持中央高校基金面上项目2项、横向科研项目5项。获发明授权专利4项、发表学术论文30余篇。E-mail：li_bing@ncepu.edu.cn。;魏乐涛，硕士研究生，主要研究方向为电力视觉及目标检测。E-mail：wlt13792808712@163.com。;翟永杰，教授，博士生导师，主要研究方向为电力视觉。主持国家自然科学基金面上项目2项、河北省自然科学基金项目2项、横向科研项目20余项。编著教材1部，参编教材1部、著作3部，发表学术论文30余篇。E-mail：zhaiyongjie@ncepu.edu.cn。
通讯作者:翟永杰. E-mail：zhaiyongjie@ncepu.edu.cn
更新日期/Last Update:
1900-01-01