Electroluminescence image enhancement technology of half-cut photovoltaic module based on DCGANs

HE Xiang

doi:10.5768/JAO202344.0202003

Journal of Applied Optics > 2023 > 44(2): 314-322. > DOI: 10.5768/JAO202344.0202003

HE Xiang. Electroluminescence image enhancement technology of half-cut photovoltaic module based on DCGANs[J]. Journal of Applied Optics, 2023, 44(2): 314-322. DOI: 10.5768/JAO202344.0202003

Citation:

HE Xiang. Electroluminescence image enhancement technology of half-cut photovoltaic module based on DCGANs[J]. Journal of Applied Optics, 2023, 44(2): 314-322. DOI: 10.5768/JAO202344.0202003

Citation:

HE Xiang. Electroluminescence image enhancement technology of half-cut photovoltaic module based on DCGANs[J]. Journal of Applied Optics, 2023, 44(2): 314-322. DOI: 10.5768/JAO202344.0202003

PDF (2628 KB)

Electroluminescence image enhancement technology of half-cut photovoltaic module based on DCGANs

HE Xiang^{1, 2,}

1.
National PV Industry Measurement and Testing Center, Fujian Metrology Institute, Fuzhou 350003 China
2.
Fujian Key Laboratory of Energy Measurement, Fuzhou 350003, China

More Information

Received Date: May 15, 2022
Revised Date: September 22, 2022
Available Online: February 03, 2023

Graphical Abstract

Abstract

Abstract

Aiming at the problem of model overfitting caused by insufficient training samples in the automatic identification process of electroluminescence (EL) defects for half-cut photovoltaic modules, the deep convolutional generative adversarial networks (DCGANs) were adopted to generate the half-cut photovoltaic module EL images with controllable attributes. The similarity between the generated EL images and the captured EL images was evaluated by using the multi-scale structural similarity (MS-SSIM) index. The evaluation results show that the MS-SSIM indexes of all types of EL images generated by DCGANs and captured EL images are greater than 0.55, and most of the MS-SSIM values are near 0.7. In the training process of the classification models, the accuracy of the test set increases with the increase of the number of images generated in the training set. When the number of generated images reaches 6 000, the accuracy of the test set reaches 97.92%. The experimental results show that the DCGANs can generate half-cut photovoltaic module EL images with high quality and controllable attributes, which can better solve the problem of model overfitting caused by the lack of training samples.

FullText(HTML)

References (16)

References

[1]	刘怀广, 刘安逸, 周诗洋, 等. 基于深度神经网络的太阳能电池组件缺陷检测算法研究[J]. 应用光学,2020,41(2):327-336. doi: 10.5768/JAO202041.0202006 LIU Huaiguang, LIU Anyi, ZHOU Shiyang, et al. Research on detection agorithm of solar cell componentdefects based on deep neural network[J]. Journal of Applied Optics,2020,41(2):327-336. doi: 10.5768/JAO202041.0202006
[2]	周颖, 毛立, 张燕, 等. 改进CNN的太阳电池缺陷识别方法研究[J]. 太阳能学报, 2020, 41(12): 69-76. ZHOU Ying, MAO Li, ZHANG Yan, et al. Research on defect detection and classification for solar cells based on improved convolutional neural network[J]. Acta Energiae Solaris Sinica, 2020, 41(12): 69-76.
[3]	刘怀广, 丁晚成, 黄千稳. 基于轻量化卷积神经网络的光伏电池片缺陷检测方法研究[J]. 应用光学,2022,43(1):87-94. LIU Huaiguang, DING Wancheng, HUANG Qianwen. Defects detection method of photovoltaic cells based on lightweight convolutional neural network[J]. Journal of Applied Optics,2022,43(1):87-94.
[4]	那峙雄, 樊涛, 孙涛, 等. 多损失融合的小样本光伏组件隐裂检测算法[J]. 计算机科学与探索,2022,16(2):458-467. doi: 10.3778/j.issn.1673-9418.2111036 NA Zhixiong, FAN Tao, SUN Tao, et al. Micro-cracks detection of solar cells based on few shot samples with multi-loss[J]. Journal of Frontiers of Computer Science & Technology,2022,16(2):458-467. doi: 10.3778/j.issn.1673-9418.2111036
[5]	GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, Dec 8-13, 2014. Cambridge: MIT Press, 2014: 2672-2680.
[6]	丛晓峰, 章军, 胡强. 基于多尺度空洞卷积的对抗去雾网络[J]. 应用光学,2020,41(6):1207-1213. doi: 10.5768/JAO202041.0602004 CONG Xiaofeng, ZHANG Jun, HU Qiang. Adversarial dehazing network based on multi-scale dilated convolution[J]. Journal of Applied Optics,2020,41(6):1207-1213. doi: 10.5768/JAO202041.0602004
[7]	徐英, 谷雨, 彭冬亮, 等. 基于DRGAN和支持向量机的合成孔径雷达图像目标识别[J]. 光学精密工程,2020,28(3):727-735. doi: 10.3788/OPE.20202803.0727 XU Ying, GU Yu, PENG Dongliang, et al. SAR ATR based on disentangled representation learning generative adversarial networks and support vector machine[J]. Optics and Precision Engineering,2020,28(3):727-735. doi: 10.3788/OPE.20202803.0727
[8]	刘坤, 文熙, 黄闽茗, 等. 基于生成对抗网络的太阳能电池缺陷增强方法[J]. 浙江大学学报(工学版),2020,54(4):684-693. doi: 10.3785/j.issn.1008-973X.2020.04.007 LIU Kun, WEN Xi, HUANG Minming, el at. Solar cell defect enhancement method based on generative adversarial network[J]. Journal of Zhejiang University (Engineering Science),2020,54(4):684-693. doi: 10.3785/j.issn.1008-973X.2020.04.007
[9]	周颖, 叶红, 王彤, 等. 基于多尺度CNN的光伏组件缺陷识别[J]. 太阳能学报,2022,43(2):211-216. ZHOU Ying, YE Hong, WANG Tong, et al. Photovoltaic module defect identification based on mul-scale convolution neural network[J]. Acta Energiae Solaris Sinica,2022,43(2):211-216.
[10]	荣丹丹, 蒋京娜, 倪健雄, 等. 半片电池技术在光伏组件中的应用[J]. 新能源进展,2017,5(4):255-258. doi: 10.3969/j.issn.2095-560X.2017.04.003 RONG Dandan, JIANG Jingna, NI Jianxiong, et al. Application of halved cells in PV module[J]. Advances in New and Renewable Enengy,2017,5(4):255-258. doi: 10.3969/j.issn.2095-560X.2017.04.003
[11]	武朝磊, 刘志民, 韦德远, 等. 温度和辐照对半片与叠瓦光伏组件性能的影响[J]. 光学精密工程,2021,29(8):1782-1794. doi: 10.37188/OPE.20212908.1782 WU Chaolei, LIU Zhimin, WEI Deyuan, et al. Effects of ambient temperature and irradiance on performance of half-cut and shingled photovoltaic modules[J]. Optics and Precision Engineering,2021,29(8):1782-1794. doi: 10.37188/OPE.20212908.1782
[12]	中国可再生能源学会光伏专业委员会. 2020年中国光伏技术发展报告——晶体硅太阳电池研究进展(9)[J]. 太阳能,2021(6):5-10. doi: 10.19911/j.1003-0417.tyn2020.09 China Photovoltaic Society. Report on 2020 China PV technology development—research progress of crystalline silicon solar cells(part 9)[J]. Solar Energy,2021(6):5-10. doi: 10.19911/j.1003-0417.tyn2020.09
[13]	梁俊杰, 韦舰晶, 蒋正锋. 生成对抗网络GAN综述[J]. 计算机科学与探索,2020,14(1):1-17. doi: 10.3778/j.issn.1673-9418.1910026 LIANG Junjie, WEI Jianjing, JIANG Zhengfeng. Generative adversarial networks GAN overview[J]. Journal of Frontiers of Computer Science & Technology,2020,14(1):1-17. doi: 10.3778/j.issn.1673-9418.1910026
[14]	RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention. [S. l. ]: [s. n. ], 2015: 234-241.
[15]	RADFORD A, METZ L, CHINTALA S, et al. Unsupervised representation learning with deep convolutional generative adversarial networks[EB/OL]. (2022-05-10)[2016-01-17].https://arxiv.org/abs/1511.06434.
[16]	WANG Z, SIMONCELLI E P, BOVIK A C. Multi-scale structural similarity for image quality assessment[C]//Proceedings of the 37th IEEE Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, Nov 9-12, 2003. Piscataway: IEEE, 2003: 1398-1402.

Cited By

Cited by

Periodical cited type(8)

1.	郭栋，张树玲，甘志颖，郭峰. 类金刚石薄膜膜基结合强度优化技术研究进展. 宁夏工程技术. 2022(01): 84-91 .
2.	张旺玺. 化学气相沉积法合成金刚石的研究进展. 陶瓷学报. 2021(04): 537-546 .
3.	李党娟，王娜，吴慎将，苏俊宏. 不同工艺参数下DLC薄膜的应力状态. 真空科学与技术学报. 2020(05): 421-426 .
4.	胡志方. 简述金刚石人工合成进展. 冶金与材料. 2020(03): 142+145 .
5.	黄彪，张而耕，周琼，陈永康. 石墨靶溅射时间对Ta-C涂层性能的影响. 陶瓷学报. 2019(03): 318-324 .
6.	丁雪兴，赵海红，金海俊，魏龙，金良. 干气密封两种典型螺旋角与DLC薄膜的摩擦性能. 石油化工高等学校学报. 2018(04): 82-89 .
7.	张而耕，黄彪，何澄，周琼. 新型Ta-C涂层铣刀切削性能研究. 表面技术. 2017(06): 125-130 .
8.	董中林，于振华，施毅，李琦，杨木，王永庆，干蜀毅. 脉冲偏压对磁过滤阴极电弧离子镀ta-C薄膜性能的影响. 真空科学与技术学报. 2017(01): 78-82 .

Other cited types(22)

Get Citation

PDF

XML

Article views (194) PDF downloads (32) Cited by(30)

Turn off MathJax

Article Contents

Abstract

References

Electroluminescence image enhancement technology of half-cut photovoltaic module based on DCGANs