为解决光伏的红外热图像含有大量噪声且不同状态红外图像分布不均衡导致的热斑难以识别的问题,以Vision Transformer（ViT）模型为基础,利用卷积神经网络改进模型特征提取,利用紧凑多头自注意力机制改进模型结构,提出一种光伏红外图像热斑识别模型ConCViT,利用CIFAR-10数据集对注意力权值进行预训练,以低信噪比小样本光伏红外图像为数据集,训练出高准确率的热斑检测模型。实验结果表明,ConCViT模型比传统卷积神经网络的识别准确率高12.02%,比深度卷积自编码网络的识别准确率高4.14%,并具有更快的收敛速度。
Abstract
In order to solve the problem that the infrared thermal image of photovoltaic panels contains a large amount of noise and it is difficult to identify the hot spots caused by the uneven distribution of infrared images in different states, based on the Vision Transformer （ViT） model, the convolution neural network is used to improve the model feature extraction, and the compact multi head self-attention mechanism is used to improve the model structure. A photovoltaic infrared image hot spot recognition model, a compact vision transformer （ConCViT）, is proposed, by which pretrains the attention weight using CIFAR-10 data set. Taking small sample photovoltaic infrared images with low signal-to-noise ratio as the data set, a high accuracy hot spot detection model is trained. The experimental results show that the recognition accuracy of ConCViT model is 12.02% higher than that of traditional convolutional neural network, 4.14% higher than that of deep convolutional self-coding network, and has faster convergence speed.
关键词
光伏组件 /
图像识别 /
卷积神经网络 /
热斑效应 /
自注意力机制 /
预训练
Key words
photovoltaic modules /
image recognition /
convolutional neural network /
hot spot effect /
self-attention mechanism /
pretraining
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 郭宝柱. 光伏阵列热斑的红外图像处理的研究[D]. 天津: 天津理工大学, 2016.
GUO B Z.Research on infrared image processing of photo voltaic array of hot spot[D]. Tianjin: Tianjin University of Technology, 2016.
[2] 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.Research and implementation of solar photo voltaic array identification and hot spot detection technology[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2018.
[3] 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 spot detection of operating PV arrays through IR thermal image[J]. Acta energiae solaris sinica, 2020, 41(08): 180-184.
[4] AFIFAH A N N, INDRABAYU, SUYUTI A, et al. A new approach for hot spot solar cell detection based on multi-level Otsu algorithm[C]// 2021 International Seminar on Intelligent Technology and Its Applications (ISITIA), Surabaya, Indonesia, 2021.
[5] CHEN J, LI Y J, LING Q.Hot-spot detection for thermographic images of solar panels[C]// 2020 Chinese Control and Decision Conference (CCDC), Hefei, China,2020.
[6] SU B Y, CHEN H Y, LIU K, et al.RCAG-net: residual channelwise attention gate network for hot spot defect detection of photovoltaic farms[J]. IEEE transactions on instrumentation and measurement, 2021, 70: 1-14.
[7] 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.
[8] 孙海蓉, 潘子杰, 晏勇. 基于深度卷积自编码网络的小样本光伏热斑识别与定位[J]. 华北电力大学学报(自然科学版), 2021, 48(4): 91-98.
SUN H R, PAN Z J, YAN Y.Identification and location of small sample photovoltaic hot spots based on deep convolution self coding network[J]. Journal of North China Electric Power University (natural science edition), 2021, 48(4): 91-98 .
[9] BAHDANAU D, CHO K, BENGIO Y.Neural machine translation by jointly learning to align and translate[EB/OL]. https://arxiv.org/abs/1409.0473.
[10] VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’ Red Hook, NY , USA, 2017.
[11] KITAEV N, KAISER L, LEVSKAYA A.Reformer:the efficient transformer[EB/OL]. https://arxiv.org/abs/2001.04511, 2020.
[12] MENG L C.Armour: generalizable compact self-attention for vision transformers[EB/OL]. https://arxiv.org/abs/2108.01778.
[13] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al.An image is worth 16×16 words: transformers for image recognition at scale[EB/OL]. https://arxiv.org/abs/2010.11929, 2020.
[14] PAN S J L, YANG Q. A survey on transfer learning[J]. IEEE transactions on knowledge and data engineering, 2010, 22(10): 1345-1359.
[15] KUMAR H, SASTRY P S.Robust loss functions for learning multi-class classifiers[C]//2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Miyazaki-ken, Japan, 2018.
基金
河北省自然科学基金（E2018502111）
PDF(1853 KB)
