为了提高光伏系统的可靠性和性能,提出一种基于红外图像和改进MobileNet-V3的光伏组件故障诊断方法。首先,分析开源光伏组件缺陷图像及其存在的问题;然后,基于存在的问题,对光伏组件红外缺陷图像进行图像增强、数据增强处理,使红外图像满足图片可用性及样本数量丰富性的要求;最后,对基本MobileNet-V3网络进行改进,实现光伏组件故障分类。实验结果显示：与传统CNN、基础MobileNet-V3相比,所提故障分类方法不仅准确率高、诊断速度快,且对各种故障类别的识别率高,具有较好的实用性和应用价值。
Abstract
In order to improve the reliability and performance of photovoltaic systems, a fault diagnosis method for photovoltaic modules based on infrared images and improved MobileNet-V3 is proposed. Firstly, the defect images of open-source photovoltaic modules and their existing problems are analyzed. Then, image and data enhancement are performed on the infrared defect images of photovoltaic modules aiming at the existing problems, so that the infrared images meet the requirements of image availability and sample quantity. Finally, the basic MobileNet-V3 network is improved to realize fault classification of photovoltaic modules. The experimental results show that, compared with the traditional CNN and the basic MobileNet-V3, the proposed fault classification method not only has high accuracy and fast diagnosis speed, but also has a high recognition rate for various fault categories, which has good practicability and application value.
关键词
光伏组件 /
红外成像 /
图像增强 /
故障诊断 /
改进MobileNet-V3算法
Key words
photovoltaic modules /
infrared imaging /
image enhancement /
fault diagnosis /
improved MobileNet-V3 algorithm
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 马铭遥, 张志祥, 刘恒, 等. 基于I-V特性分析的晶硅光伏组件故障诊断[J]. 太阳能学报, 2021, 42(6): 130-137.
MA M Y, ZHANG Z X, LIU H, et al.Fault diagnosis of crystalline silicon photovoltaic module based on I-V characteristic analysis[J]. Acta energiae solaris sinica, 2021, 42(6): 130-137.
[2] 马纪梅, 张志耀, 张启然. 基于改进RBF神经网络的光伏组件故障诊断[J]. 电测与仪表, 2021, 58(2): 118-124.
MA J M, ZHANG Z Y, ZHANG Q R.Fault diagnosis of photovoltaic modules based on improved RBF neural network[J]. Electrical measurement & instrumentation, 2021, 58(2): 118-124.
[3] 王道累, 李超, 李明山, 等. 基于深度卷积神经网络的光伏组件热斑检测[J]. 太阳能学报, 2022, 43(1): 412-417.
WANG D L, LI C, LI M S, et al.Solar photovoltaic modules hot spot detection based on deep convolutional neural networks[J]. Acta energiae solaris sinica, 2022, 43(1): 412-417.
[4] HWANG P C, KUC C Y, CHAN J C.Soiling detection for photovoltaic modules based on an intelligent method with image processing[C]//2020 IEEE International Conference on Consumer Electronics, Taoyuan, Taiwan, China, 2020.
[5] FONSECA ALVES R H, DE DEUS G A, MARRA E G, et al. Automatic fault classification in photovoltaic modules using convolutional neural networks[J]. Renewable energy, 2021, 179: 502-516.
[6] MILLENDORF M, OBROPTA E, VADHAVKAR N.Infrared solar module dataset for anomaly detection[C]//International Conference on Learning Representations(ICLR), online, 2020.
[7] ALFARO-MEJIA E, LOAIZA-CORREA H, FRANCO-MEJIA E, et al.Dataset for recognition of snail trails and hot spot failures in monocrystalline Si solar panels[J]. Data in brief, 2019, 26: 104441.
[8] BUERHOP C, DEITSCH S, MAIRER A, et al.A benchmark for visual identification of defective solar cells in electroluminescence imagery[C]//35th European PV Solar Energy Conference and Exhibition, Frankfurt, Germany, 2018.
[9] 张铮, 王孙强, 熊盛辉, 等. 结合小波变换和CLAHE的图像增强算法[J]. 现代电子技术, 2022, 45(3): 48-51.
ZHANG Z, WANG S Q,XIONG S H, et al.Image enhancement algorithm based on wavelet transform and CLAHE[J]. Modern electronics technique, 2022, 45(3):48-51.
[10] LIANG D J, YANG F, ZHANG T, et al.Understanding mixup training methods[J]. IEEE access, 2018, 6: 58774-58783.
[11] QIAN S Y, NING C R, HU Y P.MobileNetV3 for image classification[C]//2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering(ICBAIE), Nanchang, China, 2021.
[12] CHEN P Y, JIAN Q, WU P L, et al.A multi-domain fusion human motion recognition method based on lightweight network[J]. IEEE geoscience and remote sensing letters, 2022, 19: 1-5.
[13] LIU X Y, DI X G.TanhExp: a smooth activation function with high convergence speed for lightweight neural networks[J]. IET computer vision, 2021, 15(2): 136-150.
[14] 何俊, 刘跃, 李倡洪, 等. 基于改进的深度残差网络的表情识别研究[J]. 计算机应用研究, 2020, 37(5): 1578-1581.
HE J, LIU Y, LI C H, et al.Research on expression recognition based on improved deep residual network[J]. Application research of computers, 2020, 37(5): 1578-1581.
PDF(2267 KB)
