CNN based automatic detection of photovoltaic cell defects in electroluminescence images

Abstract Automatic defect detection is gaining huge importance in photovoltaic (PV) field due to limited application of manual/visual inspection and rising production quantities of PV modules. This study is conducted for automatic detection of PV module defects in electroluminescence (EL) images. We presented a novel approach using light convolutional neural network architecture for recognizing defects in EL images which achieves state of the art results of 93.02% on solar cell dataset of EL images. It requires less computational power and time. It can work on an ordinary CPU computer while maintaining real time speed. It takes only 8.07 ms for predicting one image. For proposing light architecture, we perform extensive experimentation on series of architectures. Moreover, we evaluate data augmentation operations to deal with data scarcity. Overfitting appears a significant problem; thus, we adopt appropriate strategies to generalize model. The impact of each strategy is presented. In addition, cracking patterns and defects that can appear in EL images are reviewed; which will help to label new images appropriately for predicting specific defect types upon availability of large data. The proposed framework is experimentally applied in lab and can help for automatic defect detection in field and industry.

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

[2]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[3]  Changan Zhu,et al.  Thermo-mechanical behavior assessment of smart wire connected and busbarPV modules during production, transportation, and subsequent field loading stages , 2019, Energy.

[4]  Shivkumar Kalyanaraman,et al.  DeepSolarEye: Power Loss Prediction and Weakly Supervised Soiling Localization via Fully Convolutional Networks for Solar Panels , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[5]  Yunze He,et al.  Noncontact Electromagnetic Induction Excited Infrared Thermography for Photovoltaic Cells and Modules Inspection , 2018, IEEE Transactions on Industrial Informatics.

[6]  Stefan Rein,et al.  Deep Learning Approach to Inline Quality Rating and Mapping of Multi-Crystalline Si-Wafers , 2018 .

[7]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[8]  Hiroki Sato,et al.  Fault diagnosis of photovoltaic modules using AC impedance spectroscopy , 2016, 2016 IEEE International Conference on Renewable Energy Research and Applications (ICRERA).

[9]  Qiang Yang,et al.  Deep Learning Based Module Defect Analysis for Large-Scale Photovoltaic Farms , 2019, IEEE Transactions on Energy Conversion.

[10]  Seeram Ramakrishna,et al.  Potential-induced degradation in photovoltaic modules: a critical review , 2017 .

[11]  N. Rahim,et al.  Investigation of the potential induced degradation of on-site aged polycrystalline PV modules operating in Malaysia , 2018 .

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

[13]  S. Dietrich,et al.  Investigations on crack development and crack growth in embedded solar cells , 2011, Optics + Photonics for Sustainable Energy.

[14]  M. Paggi,et al.  Fatigue degradation and electric recovery in Silicon solar cells embedded in photovoltaic modules , 2014, Scientific Reports.

[15]  Enhong Chen,et al.  Novel multi-convolutional neural network fusion approach for smile recognition , 2018, Multimedia Tools and Applications.

[16]  A. Martocchia,et al.  A review of IR thermography applied to PV systems , 2012, 2012 11th International Conference on Environment and Electrical Engineering.

[17]  Pavel Tománek,et al.  Detection and Localization of Defects in Monocrystalline Silicon Solar Cell , 2010 .

[18]  Kun Liu,et al.  Solar cell surface defect inspection based on multispectral convolutional neural network , 2018, Journal of Intelligent Manufacturing.

[19]  Bernd Eichberger,et al.  Detecting Defects in Photovoltaic Panels With the Help of Synchronized Thermography , 2018, IEEE Transactions on Instrumentation and Measurement.

[20]  Christoph J. Brabec,et al.  A Benchmark for Visual Identification of Defective Solar Cells in Electroluminescence Imagery , 2018 .

[21]  Du-Ming Tsai,et al.  Defect Detection in Solar Modules Using ICA Basis Images , 2013, IEEE Transactions on Industrial Informatics.

[22]  C. Brabec,et al.  Verifying defective PV‐modules by IR‐imaging and controlling with module optimizers , 2018 .

[23]  Christian Riess,et al.  Segmentation of Photovoltaic Module Cells in Electroluminescence Images , 2018, ArXiv.

[24]  C. Buerhop-Lutz,et al.  Electroluminescence and Infrared Imaging for Quality Improvements of PV Modules , 2008 .

[25]  Changan Zhu,et al.  Improved outdoor thermography and processing of infrared images for defect detection in PV modules , 2019, Solar Energy.

[26]  Andreas Maier,et al.  Enhanced Crack Segmentation (eCS): A Reference Algorithm for Segmenting Cracks in Multicrystalline Silicon Solar Cells , 2019, IEEE Journal of Photovoltaics.

[27]  Qiang Yang,et al.  Transfer Learning based Photovoltaic Module Defect Diagnosis using Aerial Images , 2018, 2018 International Conference on Power System Technology (POWERCON).

[28]  S. Nold,et al.  Micro-Cracks in Silicon Wafers and Solar Cells: Detection and Rating of Mechanical Strength and Electrical Quality , 2014 .

[29]  François Chollet,et al.  Deep Learning with Python , 2017 .

[30]  Qiang Yang,et al.  IET Renewable Power Generation Special Issue: Performance Assessment and Condition Monitoring of Photovoltaic Systems for Improved Energy Yield Visible defects detection based on UAV-based inspection in large-scale photovoltaic systems , 2020 .

[31]  Bradley J. Bazuin,et al.  Unsupervised Fault Detection and Analysis for Large Photovoltaic Systems Using Drones and Machine Vision , 2018, Energies.

[32]  Yan Wang,et al.  Quantitative Electroluminescence Imaging Analysis for Performance Estimation of PID-Influenced PV Modules , 2018, IEEE Journal of Photovoltaics.

[33]  S. Zamini,et al.  Defect Analysis in Different Photovoltaic Modules Using Electroluminescence (EL) and Infrared (IR)-Thermography , 2010 .

[34]  Thomas Brox,et al.  Microcracks in Silicon Wafers I: Inline Detection and Implications of Crack Morphology on Wafer Strength , 2016, IEEE Journal of Photovoltaics.

[35]  Christian Camus,et al.  Evolution of cell cracks in PV‐modules under field and laboratory conditions , 2018 .

[36]  Christian Riess,et al.  Automatic Classification of Defective Photovoltaic Module Cells in Electroluminescence Images , 2018, Solar Energy.

[37]  P. Würfel.  Physics of solar cells : from principles to new concepts , 2005 .

[38]  R. Gottschalg,et al.  Electroluminescence Imaging of PV Devices: Advanced Vignetting Calibration , 2018, IEEE Journal of Photovoltaics.