
浏览全部资源
扫码关注微信
1. 四川文理学院 人工智能与大数据学院, 四川 达州 635000
2. 伊犁师范大学 电子工程学院, 新疆 伊宁 835000
3. 四川文理学院 四川革命老区发展研究中心, 四川 达州 635000
4. 景德镇学院 信息工程学院, 江西 景德镇 334000
郑欣,男,博士,副教授,2015年于电子科技大学获得博士学位,主要从事深度学习及人工智能方面的研究。E-mail: 361368485@qq.com
黄威,男,博士,讲师,2022年于俄罗斯科学院设计与工艺信息学院获得博士学位,主要从计算机应用与计算机视觉方面的研究。E-mail:huangwei0731@163.com
收稿:2026-01-04,
修回:2026-01-22,
纸质出版:2026-02-05
移动端阅览
郑欣, 田琳, 张艳, 等. 基于深度学习的无人机巡检风机叶片表面缺陷智能检测方法[J]. 液晶与显示, 2026,41(2):267-279.
ZHENG Xin, TIAN Lin, ZHANG Yan, et al. Intelligent detection method for surface defects on wind turbine blades based on deep learning UAV inspection[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(2): 267-279.
郑欣, 田琳, 张艳, 等. 基于深度学习的无人机巡检风机叶片表面缺陷智能检测方法[J]. 液晶与显示, 2026,41(2):267-279. DOI: 10.37188/CJLCD.2026-0002. CSTR: 32172.14.CJLCD.2026-0002.
ZHENG Xin, TIAN Lin, ZHANG Yan, et al. Intelligent detection method for surface defects on wind turbine blades based on deep learning UAV inspection[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(2): 267-279. DOI: 10.37188/CJLCD.2026-0002. CSTR: 32172.14.CJLCD.2026-0002.
针对风机叶片表面缺陷人工检测效率低、现有深度学习方法环境适应性弱及多类型缺陷检测性能不足的问题,提出一种基于深度学习的无人机航拍三阶段智能检测方法,以实现高效、精准的缺陷识别。首先,从航拍视频中均匀抽帧,采用改进的EfficientNetV2-S网络实现损伤叶片初筛(准确率87.5%);然后,利用高斯混合聚类算法筛选典型损伤帧以压缩冗余数据;最后,基于集成Transformer模块与动态锚点策略的YOLO-v11网络完成缺陷精确检测。此外,构建包含剥落、裂纹等缺陷的15 000幅图像数据集用于方法验证。实验结果表明,该方法单帧检测召回率达88.4%、精度达71.5%,视频级检测召回率提升至95.0%、精度达86.4%,显著优于对比方法;可有效识别裂纹、剥落等缺陷,突破复杂环境地形限制,实现全叶片覆盖检测。所提方法解决了小目标与环境干扰难题,性能稳定,检测精度高,为风电智能化运维提供了有力支持。
To achieve efficient and accurate defect detection for wind turbine blades, this study develops a UAV-based intelligent inspection system and investigates its core algorithms, including multi-stage defect screening, representative frame selection, and deep learning-based defect recognition. First, based on image features such as structural integrity and texture patterns, an improved EfficientNetV2-S network is proposed for preliminary damage screening (accuracy 87.5%). Next, Gaussian Mixture Clustering is employed to select representative damaged frames from video streams, effectively reducing data redundancy. Then, a YOLO-v11 network integrated with Transformer modules and dynamic anchor strategies is developed for precise defect localization and classification. Additionally, a comprehensive dataset containing 15 000 annotated UAV images of various defects (e.g., cracks, delamination) is established for algorithm validation.Experimental results demonstrate that the system achieves 88.4% recall and 71.5% precision in single-frame detection, while video-level analysis improves to 95.0% recall and 86.4% precision. The method outperforms existing approaches in detecting multiple defect types under complex environmental conditions.The proposed system meets the requirements for non-contact inspection, real-time processing, high accuracy, and strong anti-interference capability, providing an effective solution for intelligent wind turbine maintenance.
刘震宇 , 尹兆磊 , 陈晨 , 等 . 基于WTBD-Det的风机叶片缺陷检测算法 [J]. 激光与光电子学进展 , 2025 , 62 ( 20 ): 20150004 .
LIU Z Y , YI Z L , CHEN C , et al . Wind turbine blade defect detection algorithm based on WTBD-Det [J]. Laser & Optoelectronics Progress , 2025 , 62 ( 20 ): 20150004 . (in Chinese)
董秀芬 , 孙浩东 , 周登科 , 等 . 海上风电风机叶片损伤不停机光电探测及识别 [J]. 激光与光电子学进展 , 2025 , 62 ( 6 ): 0612004 .
DONG X F , SUN H D , ZHOU D K , et al . Offshore fan-blade damage non-stop photoelectric detection and identification [J]. Laser & Optoelectronics Progress , 2025 , 62 ( 6 ): 0612004 . (in Chinese)
何赟泽 , 李响 , 王洪金 , 等 . 基于可见光和热成像的风机叶片全周期无损检测综述 [J]. 机械工程学报 , 2023 , 59 ( 6 ): 32 - 45 . doi: 10.3901/jme.2023.06.032 http://dx.doi.org/10.3901/jme.2023.06.032
HE Y Z , LI X , WANG H J , et al . A review: full-cycle nondestructive testing based on visible light and thermography of wind turbine blade [J]. Journal of Mechanical Engineering , 2023 , 59 ( 6 ): 32 - 45 . (in Chinese) . doi: 10.3901/jme.2023.06.032 http://dx.doi.org/10.3901/jme.2023.06.032
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 ( 9 ): 1496 - 1514 . doi: 10.37188/ope.20253309.1496 http://dx.doi.org/10.37188/ope.20253309.1496
ZHU G , GU C , XU L Y , et al . Improvement of YOLOv8 for multi-scale defect detection in wind turbine blades [J]. Optics and Precision Engineering , 2025 , 33 ( 9 ): 1496 - 1514 . (in Chinese) . doi: 10.37188/ope.20253309.1496 http://dx.doi.org/10.37188/ope.20253309.1496
沈君贤 , 马天池 , 宋狄 , 等 . 基于可解释选择性集成框架的离心风机叶片裂纹损伤检测 [J]. 机械工程学报 , 2024 , 60 ( 12 ): 183 - 193 . doi: 10.3901/jme.2024.12.183 http://dx.doi.org/10.3901/jme.2024.12.183
SHEN J X , MA T C , SONG D , et al . Crack damage detection of centrifugal fan blades based on interpretable ensemble selection framework [J]. Journal of Mechanical Engineering , 2024 , 60 ( 12 ): 183 - 193 . (in Chinese) . doi: 10.3901/jme.2024.12.183 http://dx.doi.org/10.3901/jme.2024.12.183
曾勇杰 , 范必双 , 杨涯文 , 等 . 改进YOLOv8算法在风机叶片缺陷检测上的应用 [J]. 电子测量与仪器学报 , 2024 , 38 ( 8 ): 26 - 35 .
ZENG Y J , FAN B S , YANG Y W , et al . YOLOv8 algorithm is improved in the defect detection of wind turbine blades applications [J]. Journal of Electronic Measurement and Instrumentation , 2024 , 38 ( 8 ): 26 - 35 . (in Chinese)
LI W R , ZHAO W H , DU Y F . Large-scale wind turbine blade operational condition monitoring based on UAV and improved YOLOv5 deep learning model [J]. Mechanical Systems and Signal Processing , 2025 , 226 : 112386 . doi: 10.1016/j.ymssp.2025.112386 http://dx.doi.org/10.1016/j.ymssp.2025.112386
PU J Y , ZHANG Q F , ZHAO W B , et al . Research on refined UAV inspection method of wind/solar power stations based on YOLOv8 [J]. Journal of Engineering and Applied Science , 2025 , 72 ( 1 ): 10 . doi: 10.1186/s44147-025-00576-1 http://dx.doi.org/10.1186/s44147-025-00576-1
ZHANG Z Y , SHU Z R . Unmanned aerial vehicle (UAV)-assisted damage detection of wind turbine blades: a review [J]. Energies , 2024 , 17 ( 15 ): 3731 . doi: 10.3390/en17153731 http://dx.doi.org/10.3390/en17153731
唐震 , 彭业萍 , 王伟江 , 等 . 融合Hough直线检测和Grab-cut的风机叶片自适应分割方法 [J]. 电子测量与仪器学报 , 2021 , 35 ( 4 ): 161 - 168 .
TANG Z , PENG Y P , WANG W J , et al . Adaptive segmentation method for wind turbine blades combining Hough line detection and Grab-cut algorithm [J]. Journal of Electronic Measurement and Instrumentation , 2021 , 35 ( 4 ): 161 - 168 . (in Chinese)
闫浩伟 . 基于无人机的风机叶片表面缺陷自动检测方法 [J]. 计算机测量与控制 , 2024 , 32 ( 11 ): 72 - 79 .
YAN H W . Automatic detection method for surface defects of fan blades based on drones [J]. Computer Measurement & Control , 2024 , 32 ( 11 ): 72 - 79 . (in Chinese)
刘玉淇 , 吴一全 . 基于机器视觉的太阳能电池片缺陷检测算法综述 [J]. 光学 精密工程 , 2024 , 32 ( 6 ): 868 - 900 . doi: 10.37188/ope.20243206.0868 http://dx.doi.org/10.37188/ope.20243206.0868
LIU Y Q , WU Y Q . Review of defect detection algorithms for solar cells based on machine vision [J]. Optics and Precision Engineering , 2024 , 32 ( 6 ): 868 - 900 . (in Chinese) . doi: 10.37188/ope.20243206.0868 http://dx.doi.org/10.37188/ope.20243206.0868
姜晓恒 , 段金忠 , 卢洋 , 等 . 融合先验知识推理的表面缺陷检测 [J]. 图学学报 , 2024 , 45 ( 5 ): 957 - 967 .
JIANG X H , DUAN J Z , LIU Y , et al . Fusing prior knowledge reasoning for surface defect detection [J]. Journal of Graphics , 2024 , 45 ( 5 ): 957 - 967 . (in Chinese)
孙坚 , 杨宇兵 . 基于特征提取和最优加权集成策略的风机叶片结冰故障检测 [J]. 科学技术与工程 , 2024 , 24 ( 11 ): 4501 - 4509 .
SUN J , YANG Y B . Icing fault detection of wind turbine blades based on feature extraction and an optimal weighted ensemble strategy [J]. Science Technology and Engineering , 2024 , 24 ( 11 ): 4501 - 4509 . (in Chinese)
杨彦萍 , 高军伟 , 刘兆龙 , 等 . 基于改进YOLO11的印刷电路板表面缺陷检测算法 [J]. 液晶与显示 , 2025 , 40 ( 10 ): 1545 - 1556 . doi: 10.37188/cjlcd.2025-0137 http://dx.doi.org/10.37188/cjlcd.2025-0137
YANG Y P , GAO J W , LIU Z L , et al . Surface defect detection on printed circuit boards based on improved YOLO11 [J]. Chinese Journal of Liquid Crystals and Displays , 2025 , 40 ( 10 ): 1545 - 1556 . (in Chinese) . doi: 10.37188/cjlcd.2025-0137 http://dx.doi.org/10.37188/cjlcd.2025-0137
LIU Y H , ZHENG Y Q , SHAO Z F , et al . Defect detection of the surface of wind turbine blades combining attention mechanism [J]. Advanced Engineering Informatics , 2024 , 59 : 102292 . doi: 10.1016/j.aei.2023.102292 http://dx.doi.org/10.1016/j.aei.2023.102292
陈名渝 , 谢玥辰 , 吕雄涛 , 等 . 冷轧钢表面与内部缺陷检测研究 [J]. 中国光学(中英文) , 2024 , 17 ( 4 ): 823 - 833 . doi: 10.37188/co.2023-0189 http://dx.doi.org/10.37188/co.2023-0189
CHEN M Y , XIE Y C , LV X T , et al . Detection of surface and internal defects in cold rolled steel [J]. Chinese Optics , 2024 , 17 ( 4 ): 823 - 833 . (in Chinese) . doi: 10.37188/co.2023-0189 http://dx.doi.org/10.37188/co.2023-0189
HUANG C , CHEN M H , WANG L . Semi-supervised surface defect detection of wind turbine blades with YOLOv4 [J]. Global Energy Interconnection , 2024 , 7 ( 3 ): 284 - 292 . doi: 10.1016/j.gloei.2024.06.010 http://dx.doi.org/10.1016/j.gloei.2024.06.010
LIU Y H , ZHENG Y Q , WEI T , et al . Lightweight algorithm based on you only look once version 5 for multiple class defect detection on wind turbine blade surfaces [J]. Engineering Applications of Artificial Intelligence , 2024 , 138 : 109422 . doi: 10.1016/j.engappai.2024.109422 http://dx.doi.org/10.1016/j.engappai.2024.109422
HANG X Y , ZHU X X , GAO X X , et al . Study on crack monitoring method of wind turbine blade based on AI model: integration of classification, detection, segmentation and fault level evaluation [J]. Renewable Energy , 2024 , 224 : 120152 . doi: 10.1016/j.renene.2024.120152 http://dx.doi.org/10.1016/j.renene.2024.120152
MA Y X , YIN J X , HUANG F , et al . Surface defect inspection of industrial products with object detection deep networks: a systematic review [J]. Artificial Intelligence Review , 2024 , 57 ( 12 ): 333 . doi: 10.1007/s10462-024-10956-3 http://dx.doi.org/10.1007/s10462-024-10956-3
AMERI R , HSU C C , BAND S S . A systematic review of deep learning approaches for surface defect detection in industrial applications [J]. Engineering Applications of Artificial Intelligence , 2024 , 130 : 107717 . doi: 10.1016/j.engappai.2023.107717 http://dx.doi.org/10.1016/j.engappai.2023.107717
ZHAO L X , YU J B . Crop-paste and diffusion-based semi-supervised segmentation network for metal defect detection [J]. Knowledge-Based Systems , 2025 , 318 : 113573 . doi: 10.1016/j.knosys.2025.113573 http://dx.doi.org/10.1016/j.knosys.2025.113573
PAN J W , ZENG D Y , WU Z Z , et al . BiDNet: a real-time semantic segmentation network with antifeature interference and detail recovery for industrial defects [J]. IEEE Transactions on Instrumentation and Measurement , 2025 , 74 : 5017916 . doi: 10.1109/tim.2025.3548182 http://dx.doi.org/10.1109/tim.2025.3548182
HOANG D C , TAN P X , NGUYEN A N , et al . Image-based anomaly detection in low-light industrial environments with feature enhancement [J]. Results in Engineering , 2025 , 25 : 104309 . doi: 10.1016/j.rineng.2025.104309 http://dx.doi.org/10.1016/j.rineng.2025.104309
MA W , LI Y , LAN S Y , et al . Semantic-aware normalizing flow with feature fusion for image anomaly detection [J]. Neurocomputing , 2024 , 590 : 127728 . doi: 10.1016/j.neucom.2024.127728 http://dx.doi.org/10.1016/j.neucom.2024.127728
邓万宇 , 袁昭阳 . 基于改进YOLOv8n的光伏板缺陷检测技术 [J]. 液晶与显示 , 2025 , 40 ( 11 ): 1700 - 1709 . doi: 10.37188/cjlcd.2025-0166 http://dx.doi.org/10.37188/cjlcd.2025-0166
DENG W Y , YUAN Z Y . Photovoltaic panel defect detection technology based on improved YOLOv8n [J]. Chinese Journal of Liquid Crystals and Displays , 2025 , 40 ( 11 ): 1700 - 1709 . (in Chinese) . doi: 10.37188/cjlcd.2025-0166 http://dx.doi.org/10.37188/cjlcd.2025-0166
DING W Y , LIU H , CHEN F G . Video segmentation of industrial smoke based on dynamic fully convolutional network-Gaussian mixture model and multi-scale fusion attention module [J]. Journal of Electronic Imaging , 2023 , 32 ( 3 ): 033038 . doi: 10.1117/1.jei.32.3.033038 http://dx.doi.org/10.1117/1.jei.32.3.033038
YAO D P , XIE F Z , XU Y X . Bayesian sparse Gaussian mixture model for clustering in high dimensions [J]. Journal of Machine Learning Research , 2025 , 26 ( 1 ): 50 .
GOHAR I , YEW W K , HALIMI A , et al . Review of state-of-the-art surface defect detection on wind turbine blades through aerial imagery: challenges and recommendations [J]. Engineering Applications of Artificial Intelligence , 2025 , 144 : 109970 . doi: 10.1016/j.engappai.2024.109970 http://dx.doi.org/10.1016/j.engappai.2024.109970
TAN M X , LE Q V . EfficientNetV2: smaller models and faster training [C]// Proceedings of the 38th International Conference on Machine Learning . Online : PMLR , 2021 : 10096 - 10106 .
JOCHER G . Ultralytics YOLO [EB/OL]. 2024 . https://github.com/ultralytics/ultralytics https://github.com/ultralytics/ultralytics .
SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition [C]. 3rd International Conference on Learning Representations . San Diego : ICLR , 2015 : 1556 .
HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas : IEEE , 2016 : 770 - 778 . doi: 10.1109/cvpr.2016.90 http://dx.doi.org/10.1109/cvpr.2016.90
HUANG G , LIU Z , VAN DER MAATEN L , et al . Densely connected convolutional networks [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Honolulu : IEEE , 2017 : 2261 - 2269 . doi: 10.1109/cvpr.2017.243 http://dx.doi.org/10.1109/cvpr.2017.243
SZEGEDY C , IOFFE S , VANHOUCKE V , et al . Inception-v4, inception-ResNet and the impact of residual connections on learning [C]// Proceedings of the 31st AAAI Conference on Artificial Intelligence . San Francisco : AAAI Press , 2017 : 4278 - 4284 . doi: 10.1609/aaai.v31i1.11231 http://dx.doi.org/10.1609/aaai.v31i1.11231
0
浏览量
389
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621