ASSESSING DAMAGE RISKS OF SURFACE DEFECTS ON WIND TURBINE BLADES

Wang Jian; Fang Jianhao; Wang Jinxiu; Zhao Yifeng; Hu Weifei; Fan Jia

doi:10.19912/j.0254-0096.tynxb.2024-2333

PDF(2551 KB)

Acta Energiae Solaris Sinica ›› 2026, Vol. 47 ›› Issue (5) : 258-267. DOI: 10.19912/j.0254-0096.tynxb.2024-2333

ASSESSING DAMAGE RISKS OF SURFACE DEFECTS ON WIND TURBINE BLADES

Wang Jian¹, Fang Jianhao², Wang Jinxiu³, Zhao Yifeng², Hu Weifei², Fan Jia¹

Author information +

History +

Abstract

This paper proposes a novel methodology to assess and quantify the risk of surface defects on wind turbine blades. Leveraging advanced image processing and analysis techniques, the approach not only detects surface defects but also accurately evaluates their potential impacts on wind turbine operation, providing an effective tool for condition-based maintenance. A field-collected dataset of wind turbine blade surface defect images was constructed in this paper to verify the feasibility of this method. Experimental results show that for crack defects, the error range in the test set was 0.01 m to 0.21 m （0.43% to 23.81%）, with an average relative error of 7.24%. For the blade leading edge erosion, the error range was 0.00192 m² to 0.0294 m² （1.27% to 30.18%）, with an average relative error of 13.06%. For the paint peeling, the error range was 0.00320 m² to 0.01729 m² （0.65% to 22.81%）, with an average relative error of 9.44%. These results indicate that the proposed method is effective for practical applications.

Key words

wind turbine blades / surface defects / risk assessment image processing / defect detection

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Wang Jian, Fang Jianhao, Wang Jinxiu, Zhao Yifeng, Hu Weifei, Fan Jia. ASSESSING DAMAGE RISKS OF SURFACE DEFECTS ON WIND TURBINE BLADES[J]. Acta Energiae Solaris Sinica. 2026, 47(5): 258-267 https://doi.org/10.19912/j.0254-0096.tynxb.2024-2333

References

[1] 张永贺, 吴砚辉, 马本言, 等. 基于深度学习的风机叶片缺陷识别[J]. 人工智能, 2024(3): 77-84.
ZHANG Y H, WU Y H, MA B Y, et al.Defect identification of qwind turbine blades based on deep learning[J]. AI-view, 2024(3):77-84.
[2] YE X W, DONG C Z, LIU T.A review of machine vision-based structural health monitoring: methodologies and applications[J]. Journal of sensors, 2016, 2016: 7103039.
[3] 王宁, 王雁冰, 杨健, 等. 风机自主巡视的无人机控制策略研究[J]. 中国测试, 2023, 49(10): 156-162,171.
WANG N, WANG Y B, YANG J, et al.Research on control strategy of UAV for autonomous inspection of wind turbine[J]. China measurement & test, 2023,49(10):156-162,171.
[4] SHIHAVUDDIN A, CHEN X, FEDOROV V, et al.Wind turbine surface damage detection by deep learning aided drone inspection analysis[J]. Energies, 2019, 12(4): 676.
[5] GOHAR I, HALIMI A, SEE J, et al.Slice-aided defect detection in ultra high-resolution wind turbine blade images[J]. Machines, 2023, 11(10): 953.
[6] 李哲, 李雨欣, 董秀芬, 等. 基于无人机的风机叶片智能巡检及缺陷检测[J]. 设备管理与维修, 2024(1): 152-157.
LI Z, LI Y X, DONG X F, et al.UAV-based wind turbine blade intelligent inspection and defect detection[J]. Plant maintenance engineering, 2024(1):152-157.
[7] 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.
[8] 蒋兴群, 刘波, 宋力, 等. 基于改进YOLO-v3的风力机叶片表面损伤检测识别[J]. 太阳能学报, 2023, 44(3): 212-217.
JIANG X Q, LIU B, SONG L, et al.Surface damage detection and recognition of wind turbine blade based on improved YOLO-v3[J]. Acta energiae solaris sinica, 2023, 44(3): 212-217.
[9] 邹龙洲, 王文韫, 郭迎福, 等. 基于改进YOLOv4的风力机叶片损伤检测方法[J]. 太阳能学报, 2024, 45(7): 718-723.
ZOU L Z, WANG W Y, GUO Y F, et al.Wind turbine blade damage detection method based on improved YOLOv4[J]. Acta energiae solaris sinica, 2024, 45(7): 718-723.
[10] HE Y, NIU X B, HAO C P, et al.An adaptive detection approach for multi-scale defects on wind turbine blade surface[J]. Mechanical systems and signal processing, 2024, 219: 111592.
[11] TENG S, CHEN G F.Deep convolution neural network-based crack feature extraction, detection and quantification[J]. Journal of failure analysis and prevention, 2022, 22(3): 1308-1321.
[12] JI A K, XUE X L, WANG Y N, et al.Image-based road crack risk-informed assessment using a convolutional neural network and an unmanned aerial vehicle[J]. Structural control and health monitoring, 2021, 28(7): e2749.
[13] 张良, 王高峰, 杨锋平, 等. 基于数字图像的裂纹测量系统在X80管线钢全尺寸弯曲试验中的验证[J]. 工程力学, 2022, 39(11): 157-165.
ZHANG L, WANG G F, YANG F P, et al.Verification of a crack measurement system based on digital images in full-scale bending test of X80 pipeline steel[J]. Engineering mechanics, 2022, 39(11): 157-165.
[14] 邵勇, 张钰婷, 顾桂鹏, 等. 基于最小凸包的直齿圆柱齿轮检测方法研究[J]. 电子测量与仪器学报, 2017, 31(9): 1385-1393.
SHAO Y, ZHANG Y T, GU G P, et al.Research of spur gear detection method based on minimum convex hull[J]. Journal of electronic measurement and instrumentation, 2017, 31(9): 1385-1393.
[15] MA K, HAO P F, ZHANG H X, et al.A strip steel wave-edge detection algorithm based on convex hull detection[C]//Eleventh International Conference on Graphics and Image Processing (ICGIP 2019). Hangzhou, China, 2020: 38.
[16] ZHANG T Y, SUEN C Y.A fast parallel algorithm for thinning digital patterns[J]. Communications of the ACM, 1984, 27(3): 236-239.
[17] HU W F, FANG J H, ZHANG Y X, et al.Digital twin of wind turbine surface damage detection based on deep learning-aided drone inspection[J]. Renewable energy, 2025, 241: 122332.
[18] 王文胜. 宽幅光学遥感图像舰船飞机目标检测识别技术研究[D]. 长春: 中国科学院长春光学精密机械与物理研究所, 2018.
WANG W S.Research on technology of ship and aircraft targets recognition from large-field optical remote sensing image[D]. Changchun: Changchun Insticute of Optics, Fine Mechanics and Physics, CAS, 2018.
[19] GRAHAM R L.An efficient algorith for determining the convex hull of a finite planar set[J]. Information processing letters, 1972, 1(4): 132-133.
[20] 关键, 伍僖杰, 丁昊, 等. 基于三维凹包学习算法的海面小目标检测方法[J]. 电子与信息学报, 2023, 45(5): 1602-1610.
GUAN J, WU X J, DING H, et al.Detection of small targets on sea surface based on 3-D concave hull learning algorith[J]. Journal of electronics & information technology, 2023, 45(5): 1602-1610.