针对海上风力机微小振动难以识别问题,提出一种结合相位运动放大技术（PBMM）与模板匹配算法（TM）的视觉识别新方法（PBMM-TM）。基于NREL 5 MW风力机缩尺模型,研究结构在微振动情况下光照、分辨率、背景对比度等因素对结构动力特性识别精度的影响,评估PBMM-TM法在不良环境下的识别性能并通过珠海某风力机现场实测进一步验证了该方法的适用性。结果表明,在风力机振幅微小情况下,PBMM-TM法能精准捕捉并准确识别结构动力参数。在不利光照条件和低对比度环境下,该算法的识别精度相比传统方法提升约50%;在低分辨率条件下,该算法仍能准确跟踪结构特征点,易于实现风电机组的远距离监测。
Abstract
To address the challenge of identifying micro-vibrations in offshore wind turbines, this study proposes a novel visual recognition methodology integrating phase-based motion magnification （PBMM） and template matching （TM）, herein referred to as the PBMM-TM framework. This paper utilizes a scaled-down model of the NREL 5 MW wind turbine to systematically evaluate the influence of parameters such as illumination, resolution, and background contrast on the precision of dynamic characteristic identification under micro-vibration conditions. The efficacy of the PBMM-TM method under adverse environmental conditions is rigorously analyzed, and its applicability is further corroborated by field measurements obtained from a wind turbine situated in Zhuhai, China. Results demonstrate that the PBMM-TM algorithm can accurately capture and identify dynamic structural parameters, even with minimal vibration amplitude. Compared to traditional methods, this approach enhances recognition accuracy by nearly 50% in low-light and low-contrast settings. The algorithm also maintains accurate feature point tracking at low resolutions, enabling efficient long-range monitoring of offshore wind turbines.
关键词
海上风力机 /
结构健康监测 /
模板匹配法 /
动力响应 /
视觉识别 /
相位放大技术
Key words
offshore wind turbines /
structural health monitoring /
template matching /
dynamic response /
visual recognition /
phase-based motion magnification
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 王华, 孟欢, 李萍. 风力发电机塔筒晃动位移监测新方法[J]. 噪声与振动控制, 2022, 42(1): 250-254.
WANG H, MENG H, LI P.A new method for monitoring the shaking displacement of wind turbine towers[J]. Noise and vibration control, 2022, 42(1): 250-254.
[2] 刘家瑞, 杨国田, 杨锡运. 基于深度卷积自编码器的风电机组故障预警方法研究[J]. 太阳能学报, 2022, 43(11): 215-223.
LIU J R, YANG G T, YANG X Y.Research on wind turbine fault warning method based on deep convolution auto-encoder[J]. Acta energiae solaris sinica, 2022, 43(11): 215-223.
[3] 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.
[4] ZHANG C, YANG T, YANG J.Image recognition of wind turbine blade defects using attention-based MobileNetv1-YOLOv4 and transfer learning[J]. Sensors, 2022, 22(16): 6009.
[5] BAQERSAD J, POOZESH P, NIEZRECKI C, et al.Photogrammetry and optical methods in structural dynamics: a review[J]. Mechanical systems and signal processing, 2017, 86: 17-34.
[6] 李万润, 赵文海, 杨明翰, 等. 基于DSST计算机视觉算法的风力机叶片动力特性测试[J]. 太阳能学报, 2023, 44(7): 469-477.
LI W R, ZHAO W H, YANG M H, et al.Dynamic characteristics test of wind turbine blades based on DSST computer vision algorithm[J]. Acta energiae solaris sinica, 2023, 44(7): 469-477.
[7] OZBEK M, RIXEN D J, ERNE O, et al.Feasibility of monitoring large wind turbines using photogrammetry[J]. Energy, 2010, 35(12): 4802-4811.
[8] POOZESH P, BAQERSAD J, NIEZRECKI C, et al.Large-area photogrammetry based testing of wind turbine blades[J]. Mechanical systems and signal processing, 2017, 86: 98-115.
[9] JAVED A, PARK J, LEE H, et al.Vibration signal separation of rotating cylindrical structure through target-less photogrammetric approach[J]. Journal of sound and vibration, 2023, 547: 117540.
[10] BAHAGHIGHAT M, ABEDINI F, XIN Q, et al.Using machine learning and computer vision to estimate the angular velocity of wind turbines in smart grids remotely[J]. Energy reports, 2021, 7: 8561-8576.
[11] 叶肖伟, 张小明, 倪一清, 等. 基于机器视觉技术的桥梁挠度测试方法[J]. 浙江大学学报(工学版), 2014, 48(5): 813-819.
YE X W, ZHANG X M, NI Y Q, et al.Bridge deflection measurement method based on machine vision technology[J]. Journal of Zhejiang University (engineering science), 2014, 48(5): 813-819.
[12] 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.
[13] 孔烜, 罗奎, 邓露, 等. 基于宽带相位运动放大与机器视觉的结构振动频率识别[J]. 土木工程学报, 2023, 56(10): 105-117.
KONG X, LUO K, DENG L, et al.Structural frequency identification based on broad-band phase-based motion magnification and computer vision[J]. China civil engineering journal, 2023, 56(10): 105-117.
[14] CHEN J G, DAVIS A, WADHWA N, et al.Video camera-based vibration measurement for civil infrastructure applications[J]. Journal of infrastructure systems, 2017, 23(3): B4016013.
[15] LIU C, TORRALBA A, FREEMAN W T, et al.Motion magnification[J]. ACM transactions on graphics, 2005, 24(3): 519-526.
[16] WU H Y, RUBINSTEIN M, SHIH E, et al.Eulerian video magnification for revealing subtle changes in the world[J]. ACM transactions on graphics, 2012, 31(4): 1-8.
[17] WADHWA N, RUBINSTEIN M, DURAND F, et al.Phase-based video motion processing[J]. ACM transactions on graphics, 2013, 32(4): 1-10.
[18] WANG Z W, LU S X, WU N Y, et al.Experimental study on identification of aerodynamic damping matrix for the tower of an operating wind turbine by artificial excitation[J]. Wind energy, 2025, 28: e2959.
基金
国家自然科学基金（52378507）; 湖南省自然科学基金（2023JJ30129）; 湖南省“十大技术攻关项目”项目（2023GK1030）; 国家自然科学基金杰出青年基金项目（52025082）
PDF(2693 KB)
