Identification of the dynamic characteristics of a wind turbine structure based on deep learning motion amplification

PDF(2787 KB)

Journal of Vibration and Shock ›› 2025, Vol. 44 ›› Issue (14) : 20-31.

VIBRATION THEORY AND INTERDISCIPLINARY RESEARCH

Identification of the dynamic characteristics of a wind turbine structure based on deep learning motion amplification

LI Wanrun*1,2,3，ZHAO Wenhai1，LI Qing1，DU Yongfeng1,2,3

Author information +

History +

Abstract

To effectively solve the problem of low monitoring accuracy that occurs in the visual-based monitoring method, a wind turbine characteristic identification method based on the deep learning motion amplification technology combined with the visual monitoring method was proposed.Firstly, the encoder, operator and decoder were used to construct a deep learning network framework for motion amplification, to realize the generation of arbitrary amplification rate of motion information in the video.Second, the Lucas Kanade optical flow method combined with the Shi-Tomasi corner detection was utilized to enhance the visual robust monitoring capability of the magnified video.Finally, a wind turbine model was used for experimental validation, and the experimental results show that the deep learning-based motion amplification technique combined with visual monitoring can effectively recognize the wind turbine power characteristics under different environment of the wind turbine, and the accuracy can be as high as 98% or more.Through the combination of the motion amplification technology and visual monitoring method, small vibration, long-distance, non-contact and low-cost structural health monitoring can be realized, which provides a basis for the state assessment of large-scale structures such as wind turbines and other heavy industrial installations.

Key words

structural health monitoring / wind turbine structure / motion amplification / dynamic characteristics / deep learning

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LI Wanrun1, 2, 3, ZHAO Wenhai1, LI Qing1, DU Yongfeng1, 2, 3. Identification of the dynamic characteristics of a wind turbine structure based on deep learning motion amplification[J]. Journal of Vibration and Shock, 2025, 44(14): 20-31

References

[1] SUN S, WANG T, CHU F. In-situ condition monitoring of wind turbine blades: A critical and systematic review of techniques, challenges, and futures [J]. Renewable and Sustainable Energy Reviews, 2022, 160: 112326.
[2] ASGHAR A B, LIU X. Adaptive neuro-fuzzy algorithm to estimate effective wind speed and optimal rotor speed for variable-speed wind turbine[J]. Neurocomputing, 2018, 272: 495-504.
[3] WANG L, ZHANG Z. Automatic detection of wind turbine blade surface cracks based on UAV-taken images [J]. IEEE Transactions on Industrial Electronics, 2017, 64(9): 7293-7303.
[4] KAEWNIAM P, CAO M, ALKAYEM N F, et al. Recent advances in damage detection of wind turbine blades: A state-of-the-art review [J]. Renewable and Sustainable Energy Reviews, 2022, 167: 112723.
[5] BEGANOVIC N, SOFFKER D. Structural health management utilization for lifetime prognosis and advanced control strategy deployment of wind turbines: An overview and outlook concerning actual methods, tools, and obtained results [J]. Renewable and Sustainable Energy Reviews, 2016, 64: 68-83.
[6] AMENABAR I, MENDIKUTE A, LOPEZ-ARRAIZA A, et al. Comparison and analysis of non-destructive testing techniques suitable for delamination inspection in wind turbine blades [J]. Composites Part B: Engineering, 2011, 42(5): 1298-1305.
[7] YANG B, SUN D. Testing, inspecting and monitoring technologies for wind turbine blades: A survey [J]. Renewable and Sustainable Energy Reviews, 2013, 22: 515-526.
[8] 王慧, 郭晨林, 王乐, 等. 基于内积矩阵及深度学习的结构健康监测研究[J]. 工程力学, 2022, 39(02): 14-22+75.
WANG Hui, GUO Chenlin, WANG Le, et al. Structural health monitoring based on inner product matrix and deep learning[J]. Engineering Mechanics, 2022, 39(02): 14-22+75.
[9] LYU L F, HIGGINS G D, ZHU W D. A novel robust edge detection method for full-field modal parameter estimation using an image-based tracking continuously scanning laser Doppler vibrometer system [J]. Mechanical Systems and Signal Processing, 2023, 195: 110242.
[10] 付豪, 汤宝平, 黄艺, 等. 机械振动无线传感器簇状网络路径感知同步触发方法[J]. 振动与冲击, 2022, 41(06): 147-152.
FU Hao, TANG Baoping, HUANG Yi, et al. Path perception synchronization trigger method for mechanical vibration wireless sensor cluster network [J]. Journal of Vibration and Shock, 2022, 41(06): 147-152.
[11] 李万润, 范博源, 赵文海, 等. 基于无人机及YOLOX视觉算法的大跨度钢结构吊装过程位移监测[J]. 振动与冲击, 2024, 43(17): 61-70.
LI Wanrun, FAN Boyuan, ZHAO Wenhai, et al. Displacement monitoring of large-span steel structure hoisting process based on drone and YOLOX visual algorithm [J]. Journal of Vibration and Shock, 2024, 43(17): 61-70.
[12] SPENCER JR B F, HOSKERE V, NARAZKI Y. Advances in computer vision-based civil infrastructure inspection and monitoring [J]. Engineering, 2019, 5(2): 199-222.
[13] 周颖, 张立迅, 刘彤, 等.基于计算机视觉的结构系统识别[J]. 土木工程学报, 2018, 51(11):17-23.
ZHOU Ying, ZHANG Lixun, LIU Tong, et al. Structural system identification based on computer vision [J]. China Civil Engineering Journal, 2018, 51(11):17-23. (in Chinese)
[14] 叶肖伟, 董传智. 基于计算机视觉的结构位移监测综述[J]. 中国公路学报, 2019, 32(11): 21-39.
YE Xiaowei, DONG Chuanzhi. Review of computer vision-based structural displacement monitoring [J]. China Journal of Highway and Transport , 2019, 32(11): 21-39.
[15] DONG C Z, YE X W, JIN T. Identification of structural dynamic characteristics based on machine vision technology[J]. Measurement, 2018, 126: 405-416.
[16] FENG D, FENG M Q. Experimental validation of cost-effective vision-based structural health monitoring[J]. Mechanical Systems and Signal Processing, 2017, 88: 199-211.
[17] KHADKA A, FICK B, AFSHAR A, et al. Non-contact vibration monitoring of rotating wind turbines using a semi-autonomous UAV[J]. Mechanical Systems and Signal Processing, 2020, 138: 106446.
[18] WADHWA N, RUBINSTEIN M, DURAND F, et al. Phase-based video motion processing[J]. ACM Transactions on Graphics (ToG), 2013, 32(4): 1-10.
[19] WU H Y, RUBINSTEIN M, SHIH E, et al. Eulerian video magnification for revealing subtle changes in the world[J]. ACM transactions on graphics (TOG), 2012, 31(4): 1-8.
[20] OH T H, JAROENSRI R, KIM C, et al. Learning-based video motion magnification [C]// Proceedings of the European Conference on Computer Vision (ECCV). 2018, 633-648.
[21] ELGHARIB M, HEFEEDA M, DURAND F, et al. Video magnification in presence of large motions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 4119-4127.
[22] CHEN J G, WADHWA N, CHA Y J, et al. Modal identification of simple structures with high-speed video using motion magnification[J]. Journal of Sound and Vibration, 2015, 345: 58-71.
[23] POOZESH P, SARRAFI A, MAO Z, et al. Feasibility of extracting operating shapes using phase-based motion magnification technique and stereo-photogrammetry[J]. Journal of Sound and Vibration, 2017, 407: 350-366.
[24] SARRAFI A, MAO Z, Niezrecki C, et al. Vibration-based damage detection in wind turbine blades using Phase-based Motion Estimation and motion magnification[J]. Journal of Sound and vibration, 2018, 421: 300-318.
[25] ZhAO W, LI W, FAN B, et al. Dynamic Characteristic Monitoring of Wind Turbine Structure Using Smartphone and Optical Flow Method[J]. Buildings, 2022, 12(11): 2021.
[26] 楼文娟, 余江, 潘小涛. 风力机叶片挥舞摆振气弹失稳分析[J]. 工程力学, 2015, 32(11): 236-242.
LOU Wenjuan, YU Jiang, PAN Xiaotao. Calculation for aerodynamic stability response of wind turbine blade in flapwise and edgewise direction[J]. Engineering Mechanics, 2015, 32(11): 236-242.