Localization of defects in solar cells using luminescence images and deep learning

Defect detection is a critical aspect of assuring the quality and reliability of silicon solar cells and modules. Luminescence imaging has been widely adopted as a fast method for analyzing photovoltaic devices and detecting faults. However, visual inspection of luminescence images is too slow for the expected manufacturing throughput. In this study, we propose a deep learning approach that identifies and localizes defects in electroluminescence images. Images are split into 16 tiles prior to training and treated as separate images for classification. The classified tiles provide both defect labels and their positions within the cell. We demonstrate the use of this novel approach to replace visual inspection of luminescence images in photovoltaic manufacturing lines to achieve fast and accurate defect detection.

[1]  A. Sowmya,et al.  Half and full solar cell efficiency binning by deep learning on electroluminescence images , 2021, Progress in Photovoltaics: Research and Applications.

[2]  S. Wendlandt,et al.  Solar Cell Cracks and Finger Failure Detection Using Statistical Parameters of Electroluminescence Images and Machine Learning , 2020, Applied Sciences.

[3]  Kun Liu,et al.  Deep Learning-Based Solar-Cell Manufacturing Defect Detection With Complementary Attention Network , 2020, IEEE Transactions on Industrial Informatics.

[4]  Dezso Sera,et al.  Drone-Based Daylight Electroluminescence Imaging of PV Modules , 2020, IEEE Journal of Photovoltaics.

[5]  Peng Zhao,et al.  Surface Defect Detection of Solar Cells Based on Feature Pyramid Network and GA-Faster-RCNN , 2019, 2019 2nd China Symposium on Cognitive Computing and Hybrid Intelligence (CCHI).

[6]  Christian Camus,et al.  High-throughput, outdoor characterization of photovoltaic modules by moving electroluminescence measurements , 2019, Optical Engineering.

[7]  Shuying Yang,et al.  Automated Pipeline for Photovoltaic Module Electroluminescence Image Processing and Degradation Feature Classification , 2019, IEEE Journal of Photovoltaics.

[8]  Kun Liu,et al.  Classification of Manufacturing Defects in Multicrystalline Solar Cells With Novel Feature Descriptor , 2019, IEEE Transactions on Instrumentation and Measurement.

[9]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[10]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[11]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[13]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[14]  M. Abdullah,et al.  Micro-crack detection of multicrystalline solar cells featuring an improved anisotropic diffusion filter and image segmentation technique , 2014, EURASIP J. Image Video Process..

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  D. Tsai,et al.  Defect detection of solar cells in electroluminescence images using Fourier image reconstruction , 2012 .

[17]  M. Köntges,et al.  The risk of power loss in crystalline silicon based photovoltaic modules due to micro-cracks , 2011 .

[18]  Thorsten Trupke,et al.  On the detection of shunts in silicon solar cells by photo‐ and electroluminescence imaging , 2008 .

[19]  Hayato Kondo,et al.  Analytic findings in the electroluminescence characterization of crystalline silicon solar cells , 2007 .

[20]  M. Schubert,et al.  Photoluminescence imaging of silicon wafers , 2006 .

[21]  Tim Welschehold,et al.  Microcracks in Silicon Wafers II: Implications on Solar Cell Characteristics, Statistics and Physical Origin , 2016, IEEE Journal of Photovoltaics.

[22]  Mahmoud Abdelhamid,et al.  Review of Microcrack Detection Techniques for Silicon Solar Cells , 2014, IEEE Journal of Photovoltaics.

[23]  Uwe Rau,et al.  Reciprocity relation between photovoltaic quantum efficiency and electroluminescent emission of solar cells , 2007 .