Automated Defect Detection and Localization in Photovoltaic Cells Using Semantic Segmentation of Electroluminescence Images

Fioresi, Joseph; Colvin, Dylan J.; Frota, Rafaela; Gupta, Rohit; Li, Mengjie; Seigneur, Hubert P.; Vyas, Shruti; Oliveira, Sofia; Shah, Mubarak; Davis, Kristopher O.

doi:10.1109/jphotov.2021.3131059

Title: Automated Defect Detection and Localization in Photovoltaic Cells Using Semantic Segmentation of Electroluminescence Images

Journal Article · 13 December 2021 · IEEE Journal of Photovoltaics

DOI: https://doi.org/10.1109/jphotov.2021.3131059 · OSTI ID:2283912

^[1];

^[2]; Frota, Rafaela ^[2];

^[2]; Li, Mengjie ^[3];

^[4]; Vyas, Shruti ^[2]; Oliveira, Sofia ^[2];

^[2];

^[3]

University of Central Florida, Orlando, FL (United States); University of Central Florida
University of Central Florida, Orlando, FL (United States)
University of Central Florida, Orlando, FL (United States); FSEC Energy Research Center, Cocoa, FL (United States)
FSEC Energy Research Center, Cocoa, FL (United States)

In this paper, we propose a deep learning based semantic segmentation model that identifies and segments defects in electroluminescence (EL) images of silicon photovoltaic (PV) cells. The proposed model can differentiate between cracks, contact interruptions, cell interconnect failures, and contact corrosion for both multicrystalline and monocrystalline silicon cells. Our model utilizes a segmentation Deeplabv3 model with a ResNet-50 backbone. It was trained on 17,064 EL images including 256 physically realistic simulated images of PV cells generated to deal with class imbalance. While performing semantic segmentation for five defect classes, this model achieves a weighted F1-score of 0.95, an unweighted F1-score of 0.69, a pixel-level global accuracy of 95.4%, and a mean intersection over union score of 57.3%. In addition, we introduce the UCF EL Defect dataset, a large-scale dataset consisting of 17,064 EL images, which will be publicly available for use by the PV and computer vision research communities.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: University of Central Florida, Orlando, FL (United States)

Sponsoring Organization:: National Science Foundation (NSF); USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office

Grant/Contract Number:: EE0008155

OSTI ID:: 2283912

Journal Information:: IEEE Journal of Photovoltaics, Journal Name: IEEE Journal of Photovoltaics Journal Issue: 1 Vol. 12; ISSN 2156-3381

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (45)

Evolution of cell cracks in PV-modules under field and laboratory conditions Buerhop, Claudia; Wirsching, Sven; Bemm, Andreas Progress in Photovoltaics: Research and Applications, Vol. 26, Issue 4 https://doi.org/10.1002/pip.2975	journal	December 2017
Quantifying and modeling the impact of interconnection failures on the electrical performance of crystalline silicon photovoltaic modules Annigoni, Eleonora; Virtuani, Alessandro; Levrat, Jacques Progress in Photovoltaics: Research and Applications, Vol. 27, Issue 5 https://doi.org/10.1002/pip.3111	journal	January 2019
Deep learning‐based automatic detection of multitype defects in photovoltaic modules and application in real production line Zhao, Yang; Zhan, Ke; Wang, Zhen Progress in Photovoltaics: Research and Applications, Vol. 29, Issue 4 https://doi.org/10.1002/pip.3395	journal	January 2021
Impact of interconnection failure on photovoltaic module performance Colvin, Dylan J.; Schneller, Eric J.; Davis, Kristopher O. Progress in Photovoltaics: Research and Applications, Vol. 29, Issue 5 https://doi.org/10.1002/pip.3401	journal	March 2021
Advanced Series Resistance Imaging for Silicon Solar Cells via Electroluminescence Dost, Georg; Höffler, Hannes; Greulich, Johannes M. physica status solidi (a), Vol. 218, Issue 6 https://doi.org/10.1002/pssa.202000546	journal	January 2021
Fast series resistance imaging for silicon solar cells using electroluminescence: Fast series resistance imaging for silicon solar cells using electroluminescence Haunschild, Jonas; Glatthaar, Markus; Kasemann, Martin physica status solidi (RRL) - Rapid Research Letters, Vol. 3, Issue 7-8 https://doi.org/10.1002/pssr.200903175	journal	June 2009
Luminescence imaging for inline characterisation in silicon photovoltaics Trupke, Thorsten; Nyhus, Jørgen; Haunschild, Jonas physica status solidi (RRL) - Rapid Research Letters, Vol. 5, Issue 4 https://doi.org/10.1002/pssr.201084028	journal	February 2011
Microsoft COCO: Common Objects in Context Lin, Tsung-Yi; Maire, Michael; Belongie, Serge ECCV 2014: Computer Vision – ECCV 2014 https://doi.org/10.1007/978-3-319-10602-1_48	book	January 2014
Segmentation of photovoltaic module cells in uncalibrated electroluminescence images Deitsch, Sergiu; Buerhop-Lutz, Claudia; Sovetkin, Evgenii Machine Vision and Applications, Vol. 32, Issue 4 https://doi.org/10.1007/s00138-021-01191-9	journal	May 2021
CNN based automatic detection of photovoltaic cell defects in electroluminescence images Akram, M. Waqar; Li, Guiqiang; Jin, Yi Energy, Vol. 189 https://doi.org/10.1016/j.energy.2019.116319	journal	December 2019
Structure-aware-based crack defect detection for multicrystalline solar cells Chen, Haiyong; Zhao, Huifang; Han, Da Measurement, Vol. 151 https://doi.org/10.1016/j.measurement.2019.107170	journal	February 2020
Manufacturing metrology for c-Si module reliability and durability Part III: Module manufacturing Schneller, Eric J.; Brooker, R. Paul; Shiradkar, Narendra S. Renewable and Sustainable Energy Reviews, Vol. 59 https://doi.org/10.1016/j.rser.2015.12.215	journal	June 2016
Manufacturing metrology for c-Si module reliability and durability Part II: Cell manufacturing Davis, Kristopher O.; Rodgers, Marianne P.; Scardera, Giuseppe Renewable and Sustainable Energy Reviews, Vol. 59 https://doi.org/10.1016/j.rser.2015.12.217	journal	June 2016
Manufacturing metrology for c-Si photovoltaic module reliability and durability, Part I: Feedstock, crystallization and wafering Seigneur, Hubert; Mohajeri, Nahid; Brooker, R. Paul Renewable and Sustainable Energy Reviews, Vol. 59 https://doi.org/10.1016/j.rser.2015.12.343	journal	June 2016
Automatic classification of defective photovoltaic module cells in electroluminescence images Deitsch, Sergiu; Christlein, Vincent; Berger, Stephan Solar Energy, Vol. 185 https://doi.org/10.1016/j.solener.2019.02.067	journal	June 2019
Deep learning based automatic defect identification of photovoltaic module using electroluminescence images Tang, Wuqin; Yang, Qiang; Xiong, Kuixiang Solar Energy, Vol. 201 https://doi.org/10.1016/j.solener.2020.03.049	journal	May 2020
Segmentation of cell-level anomalies in electroluminescence images of photovoltaic modules Otamendi, Urtzi; Martinez, Iñigo; Quartulli, Marco Solar Energy, Vol. 220 https://doi.org/10.1016/j.solener.2021.03.058	journal	May 2021
Defect detection of solar cells in electroluminescence images using Fourier image reconstruction Tsai, Du-Ming; Wu, Shih-Chieh; Li, Wei-Chen Solar Energy Materials and Solar Cells, Vol. 99 https://doi.org/10.1016/j.solmat.2011.12.007	journal	April 2012
Interstitial oxygen imaging from thermal donor growth—A fast photoluminescence based method Niewelt, T.; Lim, S.; Holtkamp, J. Solar Energy Materials and Solar Cells, Vol. 131 https://doi.org/10.1016/j.solmat.2014.05.011	journal	December 2014
Spatially resolved series resistance of silicon solar cells obtained from luminescence imaging Trupke, T.; Pink, E.; Bardos, R. A. Applied Physics Letters, Vol. 90, Issue 9 https://doi.org/10.1063/1.2709630	journal	February 2007
Series resistance imaging of solar cells by voltage dependent electroluminescence Hinken, David; Ramspeck, Klaus; Bothe, Karsten Applied Physics Letters, Vol. 91, Issue 18 https://doi.org/10.1063/1.2804562	journal	October 2007
Advanced luminescence based effective series resistance imaging of silicon solar cells Kampwerth, H.; Trupke, T.; Weber, J. W. Applied Physics Letters, Vol. 93, Issue 20 https://doi.org/10.1063/1.2982588	journal	November 2008
Evaluating luminescence based voltage images of silicon solar cells Glatthaar, M.; Haunschild, J.; Zeidler, R. Journal of Applied Physics, Vol. 108, Issue 1 https://doi.org/10.1063/1.3443438	journal	July 2010
Voltage calibration of luminescence images of silicon solar cells Höffler, Hannes; Al-Mohtaseb, Hasan; Haunschild, Jonas Journal of Applied Physics, Vol. 115, Issue 3 https://doi.org/10.1063/1.4862400	journal	January 2014
Photoluminescence imaging for determining the spatially resolved implied open circuit voltage of silicon solar cells Hallam, Brett; Tjahjono, Budi; Trupke, Thorsten Journal of Applied Physics, Vol. 115, Issue 4 https://doi.org/10.1063/1.4862957	journal	January 2014
Deep Residual Learning for Image Recognition He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2016.90	conference	June 2016
Weakly Supervised Segmentation of Cracks on Solar Cells Using Normalized L_p Norm Mayr, Martin; Hoffmann, Mathis; Maier, Andreas 2019 IEEE International Conference on Image Processing (ICIP) https://doi.org/10.1109/ICIP.2019.8803116	conference	September 2019
Fracture Probability, Crack Patterns, and Crack Widths of Multicrystalline Silicon Solar Cells in PV Modules During Mechanical Loading Haase, Felix; Kasewieter, Jorg; Nabavi, Seyed Roozbeh IEEE Journal of Photovoltaics, Vol. 8, Issue 6 https://doi.org/10.1109/JPHOTOV.2018.2871338	journal	November 2018
Automated Pipeline for Photovoltaic Module Electroluminescence Image Processing and Degradation Feature Classification Karimi, Ahmad Maroof; Fada, Justin S.; Hossain, Mohammad Akram IEEE Journal of Photovoltaics, Vol. 9, Issue 5 https://doi.org/10.1109/JPHOTOV.2019.2920732	journal	September 2019
A Comprehensive Methodology to Evaluate Losses and Process Variations in Silicon Solar Cell Manufacturing Hossain, Mohammad Jobayer; Gregory, Geoffrey; Schneller, Eric John IEEE Journal of Photovoltaics, Vol. 9, Issue 5 https://doi.org/10.1109/JPHOTOV.2019.2926628	journal	September 2019
Encoder–Decoder Semantic Segmentation Models for Electroluminescence Images of Thin-Film Photovoltaic Modules Sovetkin, Evgenii; Achterberg, Elbert Jan; Weber, Thomas IEEE Journal of Photovoltaics, Vol. 11, Issue 2 https://doi.org/10.1109/JPHOTOV.2020.3041240	journal	March 2021
Quantitative analysis of crystalline silicon wafer PV modules by electroluminescence imaging Guo, Siyu; Schneller, Eric; Davis, Kristopher O. 2016 IEEE 43rd Photovoltaic Specialists Conference (PVSC) https://doi.org/10.1109/PVSC.2016.7750365	conference	June 2016
Evaluating Solar Cell Fracture as a Function of Module Mechanical Loading Conditions Schneller, Eric J.; Gabor, Andrew M.; Lincoln, Jason 2017 IEEE 44th Photovoltaic Specialists Conference (PVSC), 2017 IEEE 44th Photovoltaic Specialist Conference (PVSC) https://doi.org/10.1109/PVSC.2017.8366463	conference	June 2017
EL and I-V Correlation for Degradation of PERC vs. Al-BSF Commercial Modules in Accelerated Exposures Braid, Jennifer L.; Curran, Alan J.; Sun, Jing 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC) (A Joint Conference of 45th IEEE PVSC, 28th PVSEC & 34th EU PVSEC) https://doi.org/10.1109/PVSC.2018.8547420	conference	June 2018
Electroluminescence Based Metrics to Assess the Impact of Cracks on Photovoltaic Module Performance Schneller, Eric J.; Frota, Rafaela; Gabor, Andrew M. 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC) (A Joint Conference of 45th IEEE PVSC, 28th PVSEC & 34th EU PVSEC) https://doi.org/10.1109/PVSC.2018.8547636	conference	June 2018
Feature Extraction, Supervised and Unsupervised Machine Learning Classification of PV Cell Electroluminescence Images Karimi, Ahmad Maroof; Fada, Justin S.; Liu, JiQi 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC) (A Joint Conference of 45th IEEE PVSC, 28th PVSEC & 34th EU PVSEC) https://doi.org/10.1109/PVSC.2018.8547739	conference	June 2018
Movement of Cracked Silicon Solar Cells During Module Temperature Changes Silverman, Timothy J.; Bliss, Martin; Abbas, Ali 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) https://doi.org/10.1109/PVSC40753.2019.8981150	conference	June 2019
Degradation of PERC and Al-BSF Cells with UV Cutoff and White Variations of EVA and POE Encapsulant Curran, Alan J.; Colvin, Dylan; Iqbal, Nafis 2021 IEEE 48th Photovoltaic Specialists Conference (PVSC) https://doi.org/10.1109/PVSC43889.2021.9519110	conference	June 2021
PV Cell Cracks and Impacts on Electrical Performance Whitaker, Carolina M.; Pierce, Benjamin G.; Karimi, Ahmad Maroof 2020 47th IEEE Photovoltaic Specialists Conference (PVSC) https://doi.org/10.1109/PVSC45281.2020.9300374	conference	June 2020
BAF-Detector: An Efficient CNN-Based Detector for Photovoltaic Cell Defect Detection Su, Binyi; Chen, Haiyong; Zhou, Zhong IEEE Transactions on Industrial Electronics, Vol. 69, Issue 3 https://doi.org/10.1109/TIE.2021.3070507	journal	March 2022
Deep Learning-Based Solar-Cell Manufacturing Defect Detection With Complementary Attention Network Su, Binyi; Chen, Haiyong; Chen, Peng IEEE Transactions on Industrial Informatics, Vol. 17, Issue 6 https://doi.org/10.1109/TII.2020.3008021	journal	June 2021
Image Segmentation Using Deep Learning: A Survey Minaee, Shervin; Boykov, Yuri Y.; Porikli, Fatih IEEE Transactions on Pattern Analysis and Machine Intelligence https://doi.org/10.1109/TPAMI.2021.3059968	journal	January 2021
Spatially resolved characterization of optical and recombination losses for different industrial silicon solar cell architectures Schneller, E. J.; Hossain, M. J.; Frota, R. International Journal of Modern Physics B, Vol. 34, Issue 21 https://doi.org/10.1142/s0217979220502045	journal	August 2020
The VIA Annotation Software for Images, Audio and Video Dutta, Abhishek; Zisserman, Andrew MM '19: The 27th ACM International Conference on Multimedia, Proceedings of the 27th ACM International Conference on Multimedia https://doi.org/10.1145/3343031.3350535	conference	October 2019
Automatic Finger Interruption Detection in Electroluminescence Images of Multicrystalline Solar Cells Tseng, Din-Chang; Liu, Yu-Shuo; Chou, Chang-Min Mathematical Problems in Engineering, Vol. 2015 https://doi.org/10.1155/2015/879675	journal	January 2015

Similar Records

Automatic Crack Segmentation and Feature Extraction in Electroluminescence Images of Solar Modules

Journal Article · 2023 · IEEE Journal of Photovoltaics · OSTI ID:1973673

Chen, Xin; Karin, Todd; Libby, Cara; +4 more

Automated defect identification in electroluminescence images of solar modules

Journal Article · 2022 · Solar Energy · OSTI ID:1961821

Chen, Xin; Karin, Todd; Jain, Anubhav

A Benchmark for Crack Segmentation in Electroluminescence Images

Dataset · 2022 · OSTI ID:1871275

Chen, Xin; Karin, Todd; Libby, Cara; +5 more

Related Subjects

14 SOLAR ENERGY
Photovoltaics
deep learning
defect classification
electroluminescence imaging
machine learning
semantic segmentation

Title: Automated Defect Detection and Localization in Photovoltaic Cells Using Semantic Segmentation of Electroluminescence Images

Citation Formats

References (45)

Similar Records

Related Subjects