针对光伏阵列组串热斑检测因反光而产生虚警的问题,提出一种基于可见光与红外图像的光伏阵列组串热斑检测方法。首先,考虑到光伏电站的复杂背景易导致虚警,该方法结合UNet神经网络和边缘检测算法完成光伏组件的拆分。根据组串热斑亮度较高的特点,利用聚类算法检测异常高亮区域。最后基于归一化互相关系数模板匹配法实现可见光与红外图像的配准,联合可见光图像的反光区域和光伏组串的温度信息,判定并抑制组串热斑虚警。实验结果表明,该方法适用于多种场景下组串热斑的检测,且能有效消除反光的影响。
Abstract
A group hot spot detection method for PV array strings based on visible and infrared images is proposed aiming at the problem of false alarm due to the sunlight reflection of PV array strings. Firstly, considering that the complex background of PV power plants is easy to cause false alarms, the method combines UNet neural network and edge detection algorithm to realize segmentation and extraction of PV modules. Secondly, based on the characteristic that the gray value of group hot spots is higher than that of normal modules, a clustering algorithm is used to detect abnormally bright areas. Finally, the image alignment is completed by the normalized correlation coefficient template matching method, and the suppression of false alarms is realized according to the temperature information and the reflective region on the visible image. Through experimental comparison and analysis, it is demonstrated that that the proposed method is applicable to the detection of group hotspots in various scenes and can effectively eliminate the influence of sunlight reflections.
关键词
光伏组件 /
红外成像 /
故障检测 /
组串热斑 /
聚类
Key words
PV modules /
infrared imageing /
fault detection /
group hot spot /
cluster
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 邓娟娟. 晶硅组件热斑效应的分析[D]. 北京: 北京交通大学, 2015.
DENG J J.Hot spot effect analysis on silicon cell modules[D]. Beijing: Beijing Jiaotong University, 2015.
[2] 唐圣学, 邢玥, 陈丽, 等. 太阳电池组串热斑防治策略研究[J]. 太阳能学报, 2022, 43(4): 226-235.
TANG S X, XING Y, CHEN L, et al.Study on suppressing strategy of hot spot in solar cellseries[J]. Acta energiae solaris sinica, 2022, 43(4): 226-235.
[3] WOHLGEMUTH J H, KURTZ S R.How can we make PV modules safer?[C]//2012 38th IEEE Photovoltaic Specialists Conference. Austin, TX, USA, 2012: 003162-0031658.
[4] 蒋琳, 苏建徽, 施永, 等. 基于红外热图像处理的光伏阵列热斑检测方法[J]. 太阳能学报, 2020, 41(8): 180-184.
JIANG L, SU J H, SHI Y, et al.Hot spots detection of operating pv arrays through IR thermal image[J]. Acta energiae solaris sinica, 2020, 41(8): 180-184.
[5] DOTENCO S, DALSASS M, WINKLER L, et al.Automatic detection and analysis of photovoltaic modules in aerial infrared imagery[C]//2016 IEEE Winter Conference on Applications of Computer Vision (WACV). Lake Placid, NY, USA, 2016: 1-9.
[6] 李永军, 焦子航, 洪流.一种光伏电板红外图像掉串检测方法和系统: CN202210380770.8[P]. 2022.
LI Y G, JIAO Z H, HONG L.A photovoltaic panel infrared image disconnected string detection method and system: CN202210380770.8[P]. 2022.
[7] 周全民, 杜玉杰, 叶征灯, 等. YOLO系列算法在光伏组件缺陷检测中的应用与分析[J]. 新型工业化, 2021, 11(1): 107-108, 123.
ZHOU Q M, DU Y J, YE Z D, et al.Application and analysis of YOLO series algorithms in photovoltaic module defect detection[J]. The journal of new industrialization, 2021, 11(1): 107-108, 123.
[8] 郭梦浩, 徐红伟. 基于Faster RCNN的红外热图像热斑缺陷检测研究[J]. 计算机系统应用, 2019, 28(11): 265-270.
GUO M H, XU H W.Hot spot defect detection based on infrared thermal image and Faster RCNN[J]. Computer systems & applications, 2019, 28(11): 265-270.
[9] 孙海蓉, 李莉, 周映杰, 等. 基于特征金字塔融合高分辨率网络的光伏热斑识别[J]. 太阳能学报, 2023, 44(9): 109-116.
SUN H R, LI L, ZHOU Y J, et al.Photovoltaic hot spot recognition based on feature pyramid fusion high resolution network[J]. Acta energiae solaris sinica, 2023, 44(9): 109-116.
[10] DE OLIVEIRA A K V, AGHAEI M, RÜTHER R. Automatic inspection of photovoltaic power plants using aerial infrared thermography: a review[J]. Energies, 2022, 15(6): 2055.
[11] 杨亚楠. 太阳能光伏阵列识别及热斑检测技术的研究与实现[D]. 南京: 南京邮电大学, 2018.
YANG Y N.Design and implementation of solar photovoltaic array identification and hot spot detection technology[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2018.
[12] 陈辉, 张傲, 孙帅, 等. 基于改进DeepLabv3+的含噪声热红外图像光伏热斑检测方法[J]. 太阳能学报, 2023, 44(11): 23-30.
CHEN H, ZHANG A, SUN S, et al.Photovoltaic thermal spot detection method with noisy thermal infrared image based on improved DeepLabv3+[J]. Acta energiae solaris sinica, 2023, 44(11): 23-30.
[13] RONNEBERGER O, FISCHER P, BROX T.U-net: convolutional networks for biomedical image segmentation[M]. Lecture Notes in Computer Science. Cham: Springer International Publishing, 2015: 234-241.
[14] 王小俊, 刘旭敏, 关永. 基于改进Canny算子的图像边缘检测算法[J]. 计算机工程, 2012, 38(14): 196-198, 202.
WANG X J, LIU X M, GUAN Y.Image edge detection algorithm based on improved Canny operator[J]. Computer engineering, 2012, 38(14): 196-198, 202.
[15] ARTHUR D, VASSILVITSKII S.K-Means++: The advantages of careful seeding[C]// Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2007, New Orleans, Louisiana, USA, January 7-9, 2007. ACM, 2007.
[16] 陈沈轶, 钱徽, 吴铮, 等. 模板图像匹配中互相关的一种快速算法[J]. 传感技术学报, 2007, 20(6): 1325-1329.
CHEN S Y, QIAN H, WU Z, et al.Fast normalized cross-correlation for template matching[J]. Chinese journal of sensors and actuators, 2007, 20(6): 1325-1329.
基金
浙江省“尖兵”“领雁”重点研发计划（2023C01129）
PDF(2587 KB)
