浏览全部资源
扫码关注微信
1.安徽建筑大学 机械与电气工程学院,安徽 合肥 230601
2.同济大学 机械与能源工程学院,上海 201804
[ "朱 广(1979-),男,安徽颍上人,硕士,副教授,硕士生导师,2003年于安徽理工大学获得学士学位,2007年于中国矿业大学(北京)获得硕士学位,同济大学访问学者(2024级),主要从事机器视觉、图像处理与目标检测等方面的研究。E-mail: guangzhu123@ahjzu.edu.cn" ]
顾 晨(2001-),男,江苏盐城人,硕士研究生,2023年于南通大学获得学士学位,主要从事机器视觉、图像处理与目标检测等方面的研究。E-mail: 1053971760@qq.com
收稿日期:2024-12-16,
修回日期:2025-01-24,
纸质出版日期:2025-05-10
移动端阅览
朱广,顾晨,徐立云等.改进YOLOv8的风机叶片多尺度缺陷检测[J].光学精密工程,2025,33(09):1496-1514.
ZHU Guang,GU Chen,XU Liyun,et al.Improvement of YOLOv8 for multi-scale defect detection in wind turbine blades[J].Optics and Precision Engineering,2025,33(09):1496-1514.
朱广,顾晨,徐立云等.改进YOLOv8的风机叶片多尺度缺陷检测[J].光学精密工程,2025,33(09):1496-1514. DOI: 10.37188/OPE.20253309.1496. CSTR: 32169.14.OPE.20253309.1496.
ZHU Guang,GU Chen,XU Liyun,et al.Improvement of YOLOv8 for multi-scale defect detection in wind turbine blades[J].Optics and Precision Engineering,2025,33(09):1496-1514. DOI: 10.37188/OPE.20253309.1496. CSTR: 32169.14.OPE.20253309.1496.
针对风机叶片在缺陷检测过程中精度较低,存在漏检误检的问题,提出了一种基于YOLOv8的改进算法。首先,提出了一种基于高效多尺度注意力的双卷积核结构代替瓶颈结构形成DE-C2f模块,提升网络对多尺度特征的提取能力。其次,设计全局感受野特征融合模块(GRE-SPPF),帮助网络捕获全局特征信息,扩大网络感受野。最后,在Neck中增设小目标检测层和多尺度特征融合结构,提高对小目标和复杂目标的检测性能,同时,在检测头前引入注意力和卷积融合模块(ACFM),使网络专注于关键信息,并有效抑制背景干扰。在风机叶片缺陷数据集上的实验结果表明,改进算法的mAP@0.5和mAP@0.5:0.95分别达到了91.1%和61.8%,相比于基准算法分别提升了6.2%和6.4%,召回率达到84.9%,增长7.7%,且参数量没有明显增加,能有效应用于风机叶片的缺陷检测中。
To address the challenges of low accuracy, missed detection, and false detection in defect identification of wind turbine blade, an enhanced algorithm based on YOLOv8 is proposed. Initially, a DE-C2f module is introduced, replacing the bottleneck structure with a dual convolution kernel design based on efficient multi-scale attention, thereby improving the network's multi-scale feature extraction capability. Subsequently, a global receptive field feature fusion module (GRE-SPPF) is implemented to enhance the capture of global feature information and expand the receptive field. Further improvements include the addition of a small-object detection layer and a multi-scale feature fusion structure in the Neck, optimizing detection performance for small and complex objects. An attention and convolution fusion module (ACFM) is also integrated before the detection head to prioritize critical information while mitigating background interference. Experimental results on a wind turbine blade defect dataset indicate that the proposed algorithm achieves mAP@0.5 and mAP@0.5∶0.95 values of 91.1% and 61.8%, respectively, marking improvements of 6.2% and 6.4% over the baseline algorithm. The recall rate reaches 84.9%, a 7.7% enhancement, with no substantial increase in computational parameters, demonstrating the algorithm's efficacy for practical wind turbine blade defect detection.
ARCOS JIMÉNEZ A , GÓMEZ MUÑOZ C Q , GARCÍA MÁRQUEZ F P . Dirt and mud detection and diagnosis on a wind turbine blade employing guided waves and supervised learning classifiers [J]. Reliability Engineering & System Safety , 2019 , 184 : 2 - 12 . doi: 10.1016/j.ress.2018.02.013 http://dx.doi.org/10.1016/j.ress.2018.02.013
DOLIŃSKI Ł , KRAWCZUK M , ŻAK A . Detection of delamination in laminate wind turbine blades using one-dimensional wavelet analysis of modal responses [J]. Shock and Vibration , 2018 , 2018 ( 1 ): 4507879 . doi: 10.1155/2018/4507879 http://dx.doi.org/10.1155/2018/4507879
LIU Z , LIU X , ZHU S P , et al . Reliability assessment of measurement accuracy for FBG sensors used in structural tests of the wind turbine blades based on strain transfer laws [J]. Engineering Failure Analysis , 2020 , 112 : 104506 . doi: 10.1016/j.engfailanal.2020.104506 http://dx.doi.org/10.1016/j.engfailanal.2020.104506
WU R , ZHANG D S , YU Q F , et al . Health monitoring of wind turbine blades in operation using three-dimensional digital image correlation [J]. Mechanical Systems and Signal Processing , 2019 , 130 : 470 - 483 . doi: 10.1016/j.ymssp.2019.05.031 http://dx.doi.org/10.1016/j.ymssp.2019.05.031
MORENO S , PENA M , TOLEDO A , et al . A new vision-based method using deep learning for damage inspection in wind turbine blades [C]. 2018 15th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE). September 5 - 7 , 2018 . Mexico City. IEEE , 2018 : 1 - 5 .
SHI L C , LONG Y , WANG Y Z , et al . Evaluation of internal cracks in turbine blade thermal barrier coating using enhanced multi-scale faster R-CNN model [J]. Applied Sciences , 2022 , 12 ( 13 ): 6446 . doi: 10.3390/app12136446 http://dx.doi.org/10.3390/app12136446
ZHANG C , WEN C B , LIU J H . Mask-MRNet: a deep neural network for wind turbine blade fault detection [J]. Journal of Renewable and Sustainable Energy , 2020 , 12 ( 5 ): 053302 . doi: 10.1063/5.0014223 http://dx.doi.org/10.1063/5.0014223
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 (CVPR). June 27 - 30 , 2016 . Las Vegas, NV, USA. IEEE , 2016 : 779 - 788 .
LIU W , ANGUELOV D , ERHAN D , et al . SSD:Single Shot MultiBox Detector [M]. Computer Vision-ECCV 2016. Cham : Springer Internation⁃al Publishing , 2016 : 21 - 37 . doi: 10.1007/978-3-319-46448-0_2 http://dx.doi.org/10.1007/978-3-319-46448-0_2
LV L , YAO Z Y , WANG E M , et al . Efficient and accurate damage detector for wind turbine blade images [J]. IEEE Access , 2022 , 10 : 123378 - 123386 . doi: 10.1109/access.2022.3224446 http://dx.doi.org/10.1109/access.2022.3224446
ZHU X X , HANG X Y , GAO X X , et al . Research on crack detection method of wind turbine blade based on a deep learning method [J]. Applied Energy , 2022 , 328 : 120241 . doi: 10.1016/j.apenergy.2022.120241 http://dx.doi.org/10.1016/j.apenergy.2022.120241
ZHENG Y Q , LIU Y H , WEI T , et al . Wind turbine blades surface crack-detection algorithm based on improved YOLO-v5 model [J]. Journal of Electronic Imaging , 2023 , 32 : 033012 . doi: 10.1117/1.jei.32.3.033012 http://dx.doi.org/10.1117/1.jei.32.3.033012
TONG L , FAN C L , PENG Z B , et al . WTBD-YOLOv8: an improved method for wind turbine generator defect detection [J]. Sustainability , 2024 , 16 ( 11 ): 4467 . doi: 10.3390/su16114467 http://dx.doi.org/10.3390/su16114467
ZHONG J , CHEN J , MIAN A . DualConv: dual convolutional kernels for lightweight deep neural networks [J]. IEEE Trans Neural Netw Learn Syst , 2023 , 34 ( 11 ): 9528 - 9535 . doi: 10.1109/tnnls.2022.3151138 http://dx.doi.org/10.1109/tnnls.2022.3151138
王蕾 , 郭文平 , 陈欣慰 , 等 . 融合多尺度特征的蜗杆表面缺陷检测 [J]. 光学 精密工程 , 2024 , 32 ( 11 ): 1746 - 1758 . doi: 10.37188/ope.20243211.1746 http://dx.doi.org/10.37188/ope.20243211.1746
WANG L , GUO W P , CHEN X W , et al . Worm surface defect detection with fusion of multi-scale features [J]. Optics and Precision Engineering , 2024 , 32 ( 11 ): 1746 - 1758 . (in Chinese) . doi: 10.37188/ope.20243211.1746 http://dx.doi.org/10.37188/ope.20243211.1746
蔡引娣 , 张殿鹏 , 孙梓盟 , 等 . 基于改进YOLOv8模型的增材制造微小气孔缺陷检测及其尺寸测量 [J]. 光学 精密工程 , 2024 , 32 ( 21 ): 3222 - 3230 . doi: 10.37188/ope.20243221.3222 http://dx.doi.org/10.37188/ope.20243221.3222
CAI Y D , ZHANG D P , SUN Z M , et al . YOLOv8 model-based additive manufacturing micro porosity defect detection and its dimension measurement [J]. Optics and Precision Engineering , 2024 , 32 ( 21 ): 3222 - 3230 . (in Chinese) . doi: 10.37188/ope.20243221.3222 http://dx.doi.org/10.37188/ope.20243221.3222
MISRA D . Mish: A self regularized non-monotonic activation function [EB/OL]. ( 2019-08-23 )[ 2025-02-05 ]. https : arxiv . org/abs/ 1908 . 08681 . doi: 10.5244/c.34.191 http://dx.doi.org/10.5244/c.34.191
CHEN Z L , LU S N . Caf-yolo: A robust framework for multi-scale lesion detection in biomedical imagery [EB/OL].( 2024-08-04 )[ 2024-12-10 ]. https : arxiv . org/abs/2408.01897 . doi: 10.1109/icassp49660.2025.10888358 http://dx.doi.org/10.1109/icassp49660.2025.10888358
WOO S , PARK J , LEE J Y , et al . CBAM: convolutional block attention module [C]. Computer Vision-ECCV 2018 . Cham : Springer International Publishing , 2018 : 3 - 19 . doi: 10.1007/978-3-030-01234-2_1 http://dx.doi.org/10.1007/978-3-030-01234-2_1
YU Y , ZHANG Y , CHENG Z Y , et al . MCA: Multidimensional collaborative attention in deep convolutional neural networks for image recognition [J]. Engineering Applications of Artificial Intelligence , 2023 , 126 : 107079 . doi: 10.1016/j.engappai.2023.107079 http://dx.doi.org/10.1016/j.engappai.2023.107079
HU J , SHEN L , SUN G . Squeeze-and-excitation networks [C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 18 - 23 , 2018 . Salt Lake City, UT. IEEE , 2018 : 7132 - 7141 .
LIU Y , SHAO Z , HOFFMANN N . Global attention mechanism: Retain information to enhance channel-spatial interactions [EB/OL].( 2021-12-10 ) [ 2024-12-10 ]. https : arxiv . org/abs/2112.05561 .
崔家礼 , 王涵 , 郑瀚 , 等 . 基于LDI-YOLOv8的融合图像检测方法 [J/OL]. 微电子学与计算机 , 2024 : 1 - 14 . ( 2024-08-09 ). https:kns.cnki.net/kcms/detail/61.1123.tn.
20240808.1049. html .
CUI J L , WANG H , ZHENG H , et al . Fusion image detection method based on LDI-YOLOv8 [J/OL]. Microelectronics & Computer , 2024 : 1 - 14 . ( 2024-08-09 ). https:kns.cnki.net/kcms/detail/61.1123.tn. 20240808.1049 .002.html. (in Chinese)
YU Z P , HUANG H B , CHEN W J , et al . YOLO-FaceV2: a scale and occlusion aware face detector [J]. Pattern Recognition , 2024 , 155 : 110714 . doi: 10.1016/j.patcog.2024.110714 http://dx.doi.org/10.1016/j.patcog.2024.110714
WAN D H , LU R S , SHEN S Y , et al . Mixed local channel attention for object detection [J]. Engineering Applications of Artificial Intelligence , 2023 , 123 : 106442 . doi: 10.1016/j.engappai.2023.106442 http://dx.doi.org/10.1016/j.engappai.2023.106442
LI C , LI L , JIANG H , et al . YOLOv6: A single-stage objectdetection framework for industrial applications [EB/OL].( 2018-04-08 ) [ 2024-12-10 ]. https : arxiv . org/abs/1804.02767 .
WANG C Y , BOCHKOVSKIY A , LIAO H M . YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [C]. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 17 - 24 , 2023 . Vancouver, BC, Canada. IEEE , 2023 : 7464 - 7475 .
张冀 , 王文彬 , 余洋 . 基于RFCARep-YOLOv8n的光伏电池缺陷检测算法 [J]. 计算机工程与应用 , 2025 , 61 ( 3 ): 131 - 143 . doi: 10.14569/ijacsa.2025.0160349 http://dx.doi.org/10.14569/ijacsa.2025.0160349
ZHANG J , WANG W B , YU Y . Defect detection of photovoltaic cells based on RFCARep-YOLOv8n [J]. Computer Engineering and Applications , 2025 , 61 ( 3 ): 131 - 143 . (in Chinese) . doi: 10.14569/ijacsa.2025.0160349 http://dx.doi.org/10.14569/ijacsa.2025.0160349
梁礼明 , 冯耀 , 龙鹏威 , 等 . 融合岛式双向特征金字塔的遥感图像目标检测 [J/OL]. 计算机工程与应用 , 2024 : 1 - 15 . ( 2024-09-06 ). https:kns.cnki.net/kcms/detail/11.2127.TP.
20240906.1356. html .
LIANG L M , FENG Y , LONG P W , et al . Target detection in remote sensing image based on island bidirectional feature pyramid [J/OL]. Computer Engineering and Applications , 2024 : 1 - 15 . ( 2024-09-06 ). https:kns.cnki.net/kcms/detail/11.2127.TP. 20240906.1356 .011.html. (in Chinese)
许德刚 , 王双臣 , 王再庆 , 等 . 改进YOLOv8算法的城市车辆目标检测 [J]. 计算机工程与应用 , 2024 , 60 ( 18 ): 136 - 146 .
XU D G , WANG S C , WANG Z Q , et al . Improved YOLOv8 urban vehicle target detection algorithm [J]. Computer Engineering and Applications , 2024 , 60 ( 18 ): 136 - 146 . (in Chinese)
郭伟 , 闻雯 , 金海波 , 等 . 跨尺度多维协作特征交互的航拍绝缘子多缺陷检测 [J/OL]. 计算机工程与应用 , 2024 : 1 - 15 . ( 2024-08-15 ). https:kns.cnki.net/kcms/detail/11.2127TP. 20240814.1111 .
html .
GUO W , WEN W , JIN H B , et al . Multi-defect detection of aerial insulators based on cross-scale and multi-dimensional cooperative feature interaction [J/OL]. Computer Engineering and Applications , 2024 : 1 - 15 . ( 2024-08-15 ). https:kns.cnki.net/kcms/detail/11.2127TP. 20240814.1111 .002.html. (in Chinese)
齐向明 , 严萍萍 , 姜亮 . 基于YOLOv8n的航拍图像小目标检测算法 [J]. 计算机工程与应用 , 2024 , 60 ( 24 ): 200 - 210 .
QI X M , YAN P P , JIANG L . Small target detection algorithm for aerial images based on YOLOv8n [J]. Computer Engineering and Applications , 2024 , 60 ( 24 ): 200 - 210 . (in Chinese)
ZHAO Y A , LV W Y , XU S L , et al . DETRs beat YOLOs on real-time object detection [C]. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 16 - 22 , 2024 . Seattle, WA, USA. IEEE , 2024 : 16965 - 16974 .
WANG C Y , YEH I H , LIAO H Y M . YOLOv9: Learning what you want to learn using programmable gradient information .[EB/OL]. ( 2024-02-21 )[ 2024-12-10 ]. https : arxiv . org/abs/2402.13616 . doi: 10.1007/978-3-031-72751-1_1 http://dx.doi.org/10.1007/978-3-031-72751-1_1
WANG A , CHEN H , LIU L , et al . Yolov10: Real-time end-to-end object detection [EB/OL]. ( 2024-05-23 )[ 2024-12-10 ]. https : arxiv . org/abs/2405.14458 .
CAI X , WU J . PCB bare board defect detection based on improved YOLOv7-tiny [C]. 2023 China Automation Congress (CAC). November 17 - 19 , 2023 . Chongqing, China. IEEE , 2023 : 5768 - 5773 .
0
浏览量
25
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构