Electroluminescence Images for Solar Cell Fault Detection Using Deep Learning for Binary and Multiclass Classification

International Journal of Electrical and Electronics Engineering

© 2024 by SSRG - IJEEE Journal

Volume 11 Issue 5

Year of Publication : 2024

Authors : Rawad Ahmed Ibrahim Almashhadani, Goh Chin Hock, Farah Hani Bt Nordin, Hazem N. Abdulrazzak

10.14445/23488379/IJEEE-V11I5P114

How to Cite?

Rawad Ahmed Ibrahim Almashhadani, Goh Chin Hock, Farah Hani Bt Nordin, Hazem N. Abdulrazzak, "Electroluminescence Images for Solar Cell Fault Detection Using Deep Learning for Binary and Multiclass Classification," SSRG International Journal of Electrical and Electronics Engineering, vol. 11,  no. 5, pp. 150-160, 2024. Crossref, https://doi.org/10.14445/23488379/IJEEE-V11I5P114

Abstract:

In this study, an automatic solar defect detection and classification system using deep learning was proposed. This study focuses on solar faults in photovoltaic systems identified through Electroluminescence (EL) images by employing a deep learning framework that utilizes both traditional Convolutional Neural Networks (CNNs) and a pre-trained VGG16 and VGG19 network for feature extraction. This approach was designed to enhance the accuracy and efficiency of solar defect classification. The framework is structured into three main phases: image preprocessing, feature extraction using CNNs, Histogram of Oriented Gradients (HOG) and Artificial Neural Networks (ANN), and classification through a Deep Neural Network (DNN). During preprocessing, images are scaled down to uniform dimensions to ensure consistent learning. They adopted two classification strategies: binary classification (defective or non-defective) and multiclass classification; the class names are 0%, 33%, 67%, and 100% (here, % represents the percentage of defectiveness), which represents the defect likelihood. To refine the model’s performance, a data augmentation technique has been utilized on the dataset. The effectiveness of the model was evaluated using various metrics, including the precision, recall, F1-score, and accuracy for two and four classes and obtained on, supported by confusion matrices. VGG-19 model outperformed other models and achieved precision, recall, F1-score and accuracy of 90% each for two classes respectively and similarly 94% for four classes. This study compares two classification methods to assess the ability of the deep learning framework to detect and classify solar defect images automatically.

Keywords:

Electroluminescence, Photovoltaic, Deep Neural Network, Feature extraction, Defect detection, Solar cell.

References:

[1] F. Spertino et al., “A Power and Energy Procedure in Operating Photovoltaic Systems to Quantify the Losses According to the Causes,” Solar Energy, vol. 118, pp. 313-326, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Irene Berardone, Juan Lopez Garcia, and Marco Paggi, “Quantitative Analysis of Electroluminescence and Infrared Thermal Images for Aged Monocrystalline Silicon Photovoltaic Modules,” 2017 IEEE 44th Photovoltaic Specialist Conference (PVSC), Washington, USA, pp. 402-417, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Takashi Fuyuki et al., “Analytic Findings in the Electroluminescence Characterization of Crystalline Silicon Solar Cells,” Journal of Applied Physics, vol. 101, no. 2, 2007.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Irene Berardone, Mauro Corrado, and Marco Paggi, “A Generalized Electric Model for Mono and Polycrystalline Silicon in the Presence of Cracks and Random Defects,” Energy Procedia, vol. 55, pp. 22-29, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[5] M. Paggi, M. Corrado, and I. Berardone, “A Global/Local Approach for the Prediction of the Electric Response of Cracked Solar Cells in Photovoltaic Modules under the Action of Mechanical Loads,” Engineering Fracture Mechanics, vol. 168, pp. 40-57, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Moath Alsafasfeh, Ikhlas Abdel-Qader, and Bradley Bazuin, “Fault Detection in Photovoltaic System Using SLIC and Thermal Images,” 2017 8th International Conference on Information Technology (ICIT), Amman, Jordan, pp. 672-676, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Mei-Ping Song et al., “Research on Broken Corner and Black Edge Detection of Solar Cell,” 2018 International Conference on Machine Learning and Cybernetics (ICMLC), Chengdu, China, pp. 80-84, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Yiting Li et al., “Research on a Surface Defect Detection Algorithm Based on MobileNet-SSD,” Applied Sciences, vol. 8, no. 9, pp. 1-17, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Milan Alt et al., “Electroluminescence Imaging and Automatic Cell Classification in Mass Production of Silicon Solar Cells,” 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC) (A Joint Conference of 45th IEEE PVSC, 28th PVSEC & 34th EU PVSEC), Waikoloa, USA, pp. 3298-3304, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Haiyong Chen et al., “Robust Dislocation Defects Region Segmentation for Polysilicon Wafer Image with Random Texture Background,” IEEE Access, vol. 7, pp. 134318-134329, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Keh-Moh Lin et al., “Pseudo Colorization of Electroluminescence Images of Multi-Crystalline Silicon Solar Cells for Defect Inspection,” Modern Physics Letters B, vol. 33, no. 14n15, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Binyi Su et al., “Classification of Manufacturing Defects in Multicrystalline Solar Cells with Novel Feature Descriptor,” IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 12, pp. 4675-4688, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Fan Li et al., “Machine Learning (ML)‐Assisted Design and Fabrication for Solar Cells,” Energy & Environmental Materials, vol. 2, no. 4, pp. 280-291, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Martin Mayr et al., “Weakly Supervised Segmentation of Cracks on Solar Cells Using Normalized Lp Norm,” 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, pp. 1885-1889, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Claire Mantel et al., “Machine Learning Prediction of Defect Types for Electroluminescence Images of Photovoltaic Panels,” Applications of Machine Learning, vol. 11139, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Alireza Saberironaghi, Jing Ren, and Moustafa El-Gindy, “Defect Detection Methods for Industrial Products Using Deep Learning Techniques: A Review,” Algorithms, vol. 16, no. 2, pp. 1-30, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Binbin Ni et al., “Intelligent Defect Detection Method of Photovoltaic Modules Based on Deep Learning” Proceedings of the 2018 International Conference on Transportation & Logistics, Information & Communication, Smart City (TLICSC 2018), 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Alexander Bartler et al., “Automated Detection of Solar Cell Defects with Deep Learning,” 2018 26th European Signal Processing Conference (EUSIPCO), Rome, Italy, pp. 2035-2039, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Haiyong Chen et al., “Solar Cell Surface Defect Inspection Based on Multispectral Convolutional Neural Network,” Journal of Intelligent Manufacturing, vol. 31, no. 2, pp. 453-468, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Mingjian Sun et al., “Defect Detection of Photovoltaic Modules Based on Convolutional Neural Network,” Machine Learning and Intelligent Communications, pp. 122-132, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Sergiu Deitsch et al., “Automatic Classification of Defective Photovoltaic Module Cells in Electroluminescence Images,” Solar Energy, vol. 185, pp. 455-468, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Binhui Liu, Qiangrong Yang, and Yurong Han, “A Photovoltaic Cell Defect Detection Method Using Electroluminescent and Googlenet,” 2019 2nd International Conference on Mechanical Engineering, Industrial Materials and Industrial Electronics (MEIMIE 2019), pp. 158-166, 2019.
[Google Scholar] [Publisher Link]
[23] M. Waqar Akram et al., “CNN Based Automatic Detection of Photovoltaic Cell Defects in Electroluminescence Images,” Energy, vol. 189, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Wenbo Sun et al., “Machine Learning-Assisted Molecular Design and Efficiency Prediction for High-Performance Organic Photovoltaic Materials,” Science Advances, vol. 5, no. 11, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[25] R. Pierdicca et al., “Deep Convolutional Neural Network for Automatic Detection of Damaged Photovoltaic Cells,” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 42, pp. 893-900, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Hemant B. Mahajan, and Anil Badarla, “Experimental Analysis of Recent Clustering Algorithms for Wireless Sensor Network: Application of IoT Based Smart Precision Farming,” Journal of Advanced Research in Dynamical and Control Systems, vol. 11, no. 9, pp. 116-125, 2019.
[Google Scholar] [Publisher Link]
[27] Hemant B. Mahajan, and Anil Badarla, “Detecting HTTP Vulnerabilities in IoT-Based Precision Farming Connected with Cloud Environment Using Artificial Intelligence,” International Journal of Advanced Science and Technology, vol. 29, no. 3, pp. 214-226, 2020.
[Google Scholar] [Publisher Link]
[28] Ashwini B. Gavali, Megha V. Kadam, and Sarita Patil, “Energy Optimization Using Swarm Intelligence for IoT-Authorized Underwater Wireless Sensor Networks,” Microprocessors and Microsystems, vol. 93, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Francisco J. Moreno-Barea, José M. Jerez, and Leonardo Franco, “Improving Classification Accuracy Using Data Augmentation on Small Data Sets,” Expert Systems with Applications, vol. 161, 2020.
[CrossRef] [Google Scholar] [Publisher Link]