针对传统风力机叶片监测以人巡检为主耗时、费力且效率低下的问题,提出一种基于计算机视觉的风力机叶片动力特性自动识别方法。首先,对比颜色匹配算法、模板匹配算法和分辨尺度空间跟踪器（DSST）算法的性能,提出基于DSST动力特性识别算法,并对其性能进行对比分析;其次,结合叶片振动视频,利用叶片固有角点或边缘进行跟踪,在叶片表面无附加任何标志物的情况下,识别风力机叶片的动态位移;最后,基于视觉方法识别风力机叶片的动态数据对叶片结构进行评估,并与传统监测手段分析结果进行试验对比。结果表明：采用基于DSST计算机视觉算法可准确识别风力机叶片的动力特性,并在时域和频域均有较高精度,可为风力机叶片的状态评估提供依据。
Abstract
The traditional wind turbine blade has been always associated with the issues concerning its monitoring time, laborious and inefficient. Here in an automatic identification method for the dynamic characteristics based on computer vision is proposed. In the beginning , the performance of color matching algorithm, template matching algorithm and DSST（Discriminative Scale Space Tracker） algorithm is compared, and a dynamic characteristic recognition algorithm based on DSST is proposed, and its performance is compared and analyzed. Secondly, in combination with the blade vibration video, the dynamic displacement of the wind turbine blade was identified without any markers attached to the blade surface, where this was accomplished through tracking the fixed corners or edges of the blade. Finally, the blade structure was evaluated based on the dynamic data of the wind turbine blades which identified by the visual method, followed by comparing experimental results with the analysis results of the traditional monitoring methods. The results showed that the DSST based computer vision algorithm can accurately identify the dynamic characteristics of wind turbine blades, and has high precision in time domain and frequency domain, which can provide a evaluation of wind turbine blades performance.
关键词
结构健康监测 /
风力机叶片 /
计算机视觉 /
分辨尺度空间跟踪器算法 /
动力特性
Key words
structural health monitoring /
wind turbine blades /
computer vision /
DSST algorithm /
dynamic characteristics
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] HERNADEZ-ESTRADA E, LASTRES-DANGUILLECOURT O,ROBLES- OCAMPO J B,et al.Considerations for the structural analysis and design of wind turbine towers: a review[J]. Renewable and sustainable energy reviews, 2021, 137: 110447.
[2] DU Y,ZHOU S X,JING X J,et al.Damage detection techniques for wind turbine blades: a review[J]. Mechanical systems and signal processing, 2020, 141: 106445.
[3] SONY S,LAVENTURE S, SADHU A.A literature review of next-generation smart sensing technology in structural health monitoring[J]. Structural control and health monitoring, 2019, 26(3): e2321.
[4] FENG D M, SUN H, FENG M Q.Simultaneous identification of bridge structural parameters and vehicle loads[J]. Computers & structures, 2015, 157: 76-88.
[5] 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 Y,ZHANG L X, LIU T, et al.Structural system recognition based on computer vision[J]. China civil engineering journal, 2018, 51(11): 17-23.
[6] 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 X W,DONG C Z.Review of computer vision-based structural displacement monitoring[J]. China journal of highway and transport, 2019, 32(11): 21-39.
[7] 郑树彬, 彭乐乐, 李立明, 等. 机器视觉与惯性信息融合的轨道线形检测[J]. 振动、测试与诊断, 2018, 38(2): 394-400, 425-426.
ZHENG S B,PENG L L,LI L M,et al. Muti-sensors fusion of machine vision and inertial measurement[J]. Journal of vibration,measurement & diagnosis, 2018, 38(2): 394-400, 425-426.
[8] SPENCER B F Jr, HOSKERE V, NARAZAKI Y. Advances in computer vision-based civil infrastructure inspection and monitoring[J]. Engineering, 2019, 5(2): 199-222.
[9] FENG D M, FENG M Q.Experimental validation of costeffective vision-based structural health monitoring[J]. Mechanical systems and signal processing, 2017, 88: 199-211.
[10] DONG C Z, CELIK O, CATBAS F N.Marker-free monitoring of the grandstand structures and modal identification using computer vision methods[J]. Structural health monitoring, 2019, 18(5-6): 1491-1509.
[11] DONG C Z,YE X W, JIN T.Identification of structural dynamic characteristics based on machine vision technology[J]. Measurement, 2018, 126: 405-416.
[12] 邱志成, 汪先锋. 基于双目视觉的振动测量及控制[J]. 振动、测试与诊断, 2018, 38(1): 51-58, 205.
QIU Z C, WANG X F.Vibration measurement and control based on binocular vision[J]. Journal of vibration, measurement & diagnosis, 2018, 38(1): 51-58, 205.
[13] 李万润, 张建斐, 王雪平, 等. 基于图像处理技术的风电叶片表面划痕特征提取方法研究[J]. 太阳能学报, 2020, 41(12): 278-287.
LI W R, ZHANG J F, WANG X P, et al.Feature extraction method of wind turbine blade surface scratches based on image processing[J]. Acta energiae solaris sinica, 2020, 41(12): 278-287.
[14] 王雪平, 张建斐, 李万润, 等. 基于机器视觉的风电叶片风沙侵蚀程度检测方法研究[J]. 太阳能学报, 2020, 41(5): 166-173.
WANG X P, ZHANG J F, LI W R, et al.Study on monitoring method of wind power blades erosion severity wind-sand storm based on machine vision technology[J]. Acta energiae solaris sinica, 2020, 41(5): 166-173.
[15] 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.
[16] 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.
[17] XU Y, BROWNJOHN J M W. Review of machine-vision based methodologies for displacement measurement in civil structures[J]. Journal of civil structural health monitoring, 2018, 8: 91-110.
[18] 朱前坤, 陈建邦, 张琼, 等. 基于计算机视觉人行桥挠度影响线非接触式识别[J]. 工程力学, 2021, 38(8): 145-153.
ZHU Q K, CHEN J B, ZHANG Q, et al.A non-contact recognition for deflection influence line of footbridge based on computer vision[J]. Engineering mechanics, 2021, 38(8): 145-153.
[19] KHUC T, CATBAS F N.Completely contactless structural health monitoring of real-life structures using cameras and computer vision[J]. Structural control and health monitoring, 2017, 24(1): e1852.
[20] DANELLJAN M, HAGER G, KHAN F S, et al.Accurate scale estimation for robust visual tracking[C]//British Machine Vision Conference, Nottingham, UK, 2014.
[21] YE X W, DONG C Z, LIU T.Image-based structural dynamic displacement measurement using different multi-object tracking algorithms[J]. Smart structures and systems, 2016, 17(6): 935-956.
[22] 董传智, 叶肖伟, 刘坦. 非接触式结构动力特性识别方法及试验验证[J]. 振动与冲击, 2017, 36(1): 188-193.
DONG C Z, YE X W, LIU T.Noncontact structural dynamic characteristics identification method and its test verification[J]. Journal of vibration and shock, 2017, 36(1): 188-193.
[23] 陈建平, 侯楠, 申振腾. 风力机叶片运行状态机器视觉监测技术研究[J]. 太阳能学报, 2020, 41(12): 238-244.
CHEN J P, HOU N, SHEN Z T.Research on machine vision monitoring technology for operational status of wind turbine blade[J]. Acta energiae solaris sinica, 2020, 41(12): 238-244.
[24] 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 W J, YU J, PAN X T.Calculation for aerodynamic stability response of wind turbine blade in flapwise and edgewise direction[J]. Engineering mechanics, 2015, 32(11): 236-242.
基金
国家自然科学基金（52068049; 51568041）; 甘肃省杰出青年基金（21JR7RA267）; 兰州理工大学红柳优秀青年人才支持计划
PDF(2996 KB)
