Welcome to visit Acta Energiae Solaris Sinica,Today is Share:
ISSN 0254-0096 CN 11-2082/K

Acta Energiae Solaris Sinica ›› 2023, Vol. 44 ›› Issue (2): 453-459.DOI: 10.19912/j.0254-0096.tynxb.2021-1141

Previous Articles     Next Articles

PHOTOVOLTAIC HOT SPOT RECOGNITION BASED ON ATTENTION MECHANISM

Sun Hairong1, Li Fan1,2   

  1. 1. Department of Automation, North China Electric Power University, Baoding 071003, China;
    2. Hebei Technology Innovation Center of Simulation & Optimized Control for Power Generation, North China Electric Power University,Baoding 071003, China
  • Received:2021-09-22 Online:2023-02-28 Published:2023-08-28

基于注意力机制的光伏热斑识别

孙海蓉1, 李帆1,2   

  1. 1.华北电力大学自动化系,保定 071003;
    2.华北电力大学河北省发电过程仿真与优化控制技术创新中心,保定 071003
  • 通讯作者: 李 帆(1997—),男,硕士,主要从事模式识别、深度学习在发电领域的应用方面的研究。ncepu_lifan@163.com
  • 基金资助:
    河北省自然科学基金(E2018502111)

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.

Key words: photovoltaic modules, image recognition, convolutional neural network, hot spot effect, self-attention mechanism, pretraining

摘要: 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。

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

CLC Number: