Solar Cell Cracks and Finger Failure Detection Using Statistical Parameters of Electroluminescence Images and Machine Learning
Source abstract
Abstract
A wide range of defects, failures, and degradation can develop at different stages in the lifetime of photovoltaic modules. To accurately assess their effect on the module performance, these failures need to be quantified. Electroluminescence (EL) imaging is a powerful diagnostic method, providing high spatial resolution images of solar cells and modules. EL images allow the identification and quantification of different types of failures, including those in high recombination regions, as well as series resistance-related problems. In this study, almost 46,000 EL cell images are extracted from photovoltaic modules with different defects. We present a method that extracts statistical parameters from the histogram of these images and utilizes them as a feature descriptor. Machine learning algorithms are then trained using this descriptor to classify the detected defects into three categories: (i) cracks (Mode B and C), (ii) micro-cracks (Mode A) and finger failures, and (iii) no failures. By comparing the developed methods with the commonly used one, this study demonstrates that the pre-processing of images into a feature vector of statistical parameters provides a higher classification accuracy than would be obtained by raw images alone. The proposed method can autonomously detect cracks and finger failures, enabling outdoor EL inspection using a drone-mounted system for quick assessments of photovoltaic fields.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Photovoltaic System Optimization Techniques · Integrated Circuits and Semiconductor Failure Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Energy Technology, AAU, 9220 Aalborg, Denmark
School of Photovoltaic and Renewable Energy Engineering, UNSW, Kensington, NSW 2052, Australia
Department of Photonics Engineering, Technical University of Denmark, 4000 Roskilde, Denmark
PI Photovoltaik-Institut Berlin AG, Wrangelstr. 100, D-10997 Berlin, Germany
School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD 4000, Australia
Funding
Innovation Fund Denmark
References (50)
Show source-provided references
1. Terawatt-scale photovoltaics: Transform global energy10.1126/science.aaw1845 ↗
2. Photovoltaic technology and visions for the future10.1088/2516-1083/ab0fa8 ↗
3. Köntges, M., Kurtz, S., Packard, C., Jahn, U., Berger, K., Kato, K., Kazuhilo, F., Thomas, F., Liu, H., and van Iseghem, M. (2014). IEA-PVPS Task 13: Review of Failures of Photovoltaic Modules, SUPSI.
4. Spataru, S., Hacke, P., and Sera, D. (2016, January 5–10). Automatic detection and evaluation of solar cell micro-cracks in electroluminescence images using matched filters. Proceedings of the 2016 IEEE 43rd Photovoltaic Specialists Conference (PVSC); Institute of Electrical and Electronics Engineers (IEEE), Portland, OR, USA.10.1109/PVSC.2016.7749891 ↗
5. Spataru, S., Hacke, P., Sera, D., Glick, S., Kerekes, T., and Teodorescu, R. (2015, January 14–19). Quantifying solar cell cracks in photovoltaic modules by electroluminescence imaging. Proceedings of the 2015 IEEE 42nd Photovoltaic Specialist Conference (PVSC), Institute of Electrical and Electronics Engineers (IEEE), New Orleans, LA, USA.10.1109/PVSC.2015.7356124 ↗
6. The impact of cracks on photovoltaic power performance10.1016/j.jsamd.2017.05.005 ↗
7. Criticality of Cracks in PV Modules10.1016/j.egypro.2012.07.125 ↗
8. CNN based automatic detection of photovoltaic cell defects in electroluminescence images10.1016/j.energy.2019.116319 ↗
9. A methodology to account for the finger interruptions in solar cell performance10.1016/j.microrel.2012.07.014 ↗
10. Detection of Finger Interruptions in Silicon Solar Cells Using Line Scan Photoluminescence Imaging10.1109/JPHOTOV.2017.2732220 ↗
11. Can luminescence imaging replace lock-in thermography on solar cells and wafers?10.1109/JPHOTOV.2011.2169394 ↗
12. Photographic surveying of minority carrier diffusion length in polycrystalline silicon solar cells by electroluminescence10.1063/1.1978979 ↗
13. The risk of power loss in crystalline silicon based photovoltaic modules due to micro-cracks10.1016/j.solmat.2010.10.034 ↗
14. Automatic classification of defective photovoltaic module cells in electroluminescence images10.1016/j.solener.2019.02.067 ↗
15. Fada, J.S., Hossain, M.A., Braid, J.L., Yang, S., Peshek, T.J., and French, R.H. (2017, January 25–30). Electroluminescent Image Processing and Cell Degradation Type Classification via Computer Vision and Statistical Learning Methodologies. Proceedings of the 2017 IEEE 44th Photovoltaic Specialist Conference (PVSC), Institute of Electrical and Electronics Engineers (IEEE), Washington, DC, USA.10.1109/PVSC.2017.8366291 ↗
16. Outdoor photoluminescence imaging of photovoltaic modules with sunlight excitation10.1002/pip.2946 ↗
17. Alpaydin, E. (2010). Introduction to Machine Learning, The MIT Press.
18. Bishop, C.M. (2006). Pattern Recognition and Machine Learning (Information Science and Statistics), Springer.
19. Karimi, A.M., Fada, J.S., Liu, J., Braid, J.L., Koyuturk, M., and French, R.H. (2018, January 10–15). Feature Extraction, Supervised and Unsupervised Machine Learning Classification of PV Cell Electroluminescence Images. Proceedings of the 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC) (A Joint Conference of 45th IEEE PVSC, 28th PVSEC & 34th EU PVSEC), Institute of Electrical and Electronics Engineers (IEEE), Waikoloa Village, HI, USA.10.1109/PVSC.2018.8547739 ↗
20. Sun, M.-J., Lv, S., Zhao, X., Li, R., Zhang, W., and Zhang, X. (2018). Defect Detection of Photovoltaic Modules Based on Convolutional Neural Network. Proceedings of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, Springer Science and Business Media LLC.10.1007/978-3-319-73564-1_13 ↗
21. Automatic Finger Interruption Detection in Electroluminescence Images of Multicrystalline Solar Cells
22. Mantel, C., Villebro, F., Benatto, G.A.D.R., Parikh, H.R., Wendlandt, S., Hossain, K., Poulsen, P.B., Spataru, S., Sera, D., and Forchhammer, S. (2019). Machine learning prediction of defect types for electroluminescence images of photovoltaic panels. Applications of Machine Learning, International Society for Optics and Photonics.10.1117/12.2528440 ↗
23. CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data10.1109/TMM.2017.2745702 ↗
24. Defect Detection in Solar Modules Using ICA Basis Images10.1109/TII.2012.2209663 ↗
25. Micro-crack detection of multi-crystalline solar cells featuring an improved anisotropic diffusion filter and image segmentation technique10.1186/1687-5281-2014-15 ↗
26. Intelligent fault pattern recognition of aerial photovoltaic module images based on deep learning technique
27. Deep Learning Based Module Defect Analysis for Large-Scale Photovoltaic Farms10.1109/TEC.2018.2873358 ↗
28. Ding, S., Yang, Q., Li, X., Yan, W., and Ruan, W. (2018, January 6–8). Transfer learning based PV module defect diagnosis using aerial images. Proceedings of the 2018 International Conference on Power System Technology (POWERCON), Guangzhou, China.10.1109/POWERCON.2018.8602188 ↗
29. Solar cell surface defect inspection based on multi-spectral convolutional neural network10.1007/s10845-018-1458-z ↗
30. GAN-Based Augmentation for Improving CNN Performance of Classification of Defective Photovoltaic Module Cells in Electroluminescence Images10.1088/1755-1315/354/1/012106 ↗
31. Least median of squares regression10.1080/01621459.1984.10477105 ↗
32. Malis, E., and Vargas, M. (2007). Deeper Understanding of the Homography Decomposition for Vision-Based Control, INRIA.
33. Szeliski, R. (2010). Computer Vision: Algorithms and Applications, Springer-Verlag.10.1007/978-1-84882-935-0 ↗
34. (2020, April 05). Perspective Control Correction with Mathworks. Available online: https://se.mathworks.com/matlabcentral/fileexchange/35531-perspective-control-correction/.
35. Method for Estimation and Correction of Perspective Distortion of Electroluminescence Images of Photovoltaic Panels10.1109/JPHOTOV.2020.3019949 ↗
36. Ali, U., and Mahmood, M.T. (2018). Analysis of Blur Measure Operators for Single Image Blur Segmentation. Appl. Sci., 8.10.3390/app8050807 ↗
37. Segmentation of photovoltaic module cells in electroluminescence images
38. Support vector machines10.1109/5254.708428 ↗
39. (2020, August 21). Applying Supervised Learning with Mathworks. Available online: https://se.mathworks.com/campaigns/offers/machine-learning-with-matlab.html.
40. Linge, S., and Langtangen, H.P. (2016). Programming for Computations—Python: A Gentle Introduction to Numerical Simulations with Python, Springer.10.1007/978-3-319-32428-9 ↗
41. Pandas: A foundational python library for data analysis and statistics
42. An introduction to statistical learning with applications
43. Supervised machine learning: A review of classification techniques
44. Random forests10.1023/A:1010933404324 ↗
45. Breiman, L., Freidman, J., Stone, C.J., and Olshen, R.A. (1984). Classification and Regression Trees, CRC Press.
46. VanderPlas, J. (2016). Python Data Science Handbook, O’Reilly Media Inc.
47. Evaluation: From precision, recall and f-factor to ROC, informedness, markedness, and correlation
48. Buratti, Y., Dick, J., Le Gia, Q., and Hameiri, Z. (2019, January 16–21). A Machine Learning Approach to Defect Parameters Extraction: Using Random Forests to Inverse the Shockley-Read-Hall Equation. Proceedings of the 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC), Institute of Electrical and Electronics Engineers (IEEE), Chicago, IL, USA.10.1109/PVSC40753.2019.8980717 ↗
49. Spataru, S., Parikh, H., Hacke, P., Benatto, G.A.d.R., and Sera, D. (2017, January 25–29). Quantification of solar cell failure signatures based on statistical analysis of electroluminescence images. Proceedings of the 33rd European Photovoltaic Solar Energy Conference and Exhibition: EU PVSEC, Amsterdam, The Netherlands.
50. (2020, September 09). Statistical Functions Using Scipy.Stats. Available online: https://docs.scipy.org/doc/scipy/reference/stats.html.