Efficient Busbar Slip Defects Detection in Photovoltaic Cell Electroluminescence Images

Yıl 2024, , 363 - 377, 31.08.2024

Sahra Simsek Kaya , Abdülkadir Gümüşçü , Nurettin Beşli

https://doi.org/10.54365/adyumbd.1494765

Öz

PV panel quality control is crucial for their efficient and long-lasting operation. Detecting defects in PV panels during production is essential. Electroluminescence imaging is a commonly used method for fault detection in PV panels. This study focuses on detecting busbar slippage, a specific PV panel malfunction. Automatic error detection was researched using machine learning methods on a dataset of 500 EL images taken from the production line. Feature extraction was performed using two pre-trained deep learning architectures: ResNet and SqueezeNet. Additionally, the study aimed to observe the impact of combining features from different deep learning architectures on success parameters. The highest accuracy rate of 0.9920 was achieved using deep features extracted by Relu34 and Relu25+Conv10 layers.

Anahtar Kelimeler

Deep Learning, Busbar slip, Defect Detection, Electroluminescence, Solar cell classification.

Destekleyen Kurum

Harran University Scientific Research Projects Commission

Proje Numarası

22256

Teşekkür

We would like to thank to Harran University Scientific Research Projects Commission for supporting our study (Project No:22256).

Fotovoltaik Hücre Elektrolüminesans Görüntülerinde Verimli Bara Kayma Kusurlarının Tespiti

Öz

PV panellerin kalite kontrolü, verimli ve uzun ömürlü çalışmaları için çok önemlidir. PV panellerdeki kusurların üretim sırasında tespit edilmesi de ayrıca önem arz etmektedir. Elektrolüminesans görüntüleme, PV panellerde arıza tespiti için yaygın olarak kullanılan bir yöntem olarak karşımıza çıkmaktadır. Bu çalışma, spesifik bir PV panel arızası olan bara kaymasının tespitine odaklanmaktadır. Üretim hattından alınan 500 EL görüntüsünden oluşan bir veri seti üzerinde makine öğrenmesi yöntemleri kullanılarak otomatik hata tespiti araştırılmıştır. Özellik çıkarma, önceden eğitilmiş ResNet ve SqueezeNet derin öğrenme mimarileri kullanılarak gerçekleştirilmiştir. Ayrıca çalışmada, farklı derin öğrenme mimarilerindeki özellikleri birleştirmenin başarı parametreleri üzerindeki etkisini gözlemlenmiştir. En yüksek doğruluk oranı olan 0,9920, Relu34 ve Relu25+Conv10 katmanları tarafından çıkarılan derin özellikler kullanılarak elde edilmiştir.

Anahtar Kelimeler

Derin Öğrenme, Bara Kayması, Elektrolüminesans, Güneş Hücreleri Sınıflandırma

Destekleyen Kurum

Harran University Scientific Research Projects Commission

Proje Numarası

22256

Teşekkür

We would like to thank to Harran University Scientific Research Projects Commission for supporting our study (Project No:22256).

Kaynakça

• Anwar, S. A., and Abdullah, M. Z. (2014). Micro-crack detection of multicrystalline solar cells featuring an improved anisotropic diffusion filter and image segmentation technique. EURASIP Journal on Image and Video Processing, 2014(1). https://doi.org/10.1186/1687-5281-2014-15
• Benda, V., and Cerna, L. (2020). PV cells and modules state of the art, limits and Trends. Heliyon, 6(12). https://doi.org/10.1016/j.heliyon.2020.e05666
• Akram, M. W., Li, G., Jin, Y., Chen, X., Zhu, C., Zhao, X., Khaliq, A., Faheem, M., and Ahmad, A. (2019). CNN based automatic detection of photovoltaic cell defects in electroluminescence images. Energy, 189,116319. https://doi.org/10.1016/j.energy.2019.116319
• Köntges, M., Kunze, I., Kajari-Schröder, S., Breitenmoser, X., and Bjrneklett, B. (2011). Quantifying the risk of power loss in PV modules due to micro cracks. Solar Energy Materials and Solar Cells, vol. 95, no. 4, pp. 1131- 1137.
• Santhakumari, M., Sagar, N. (2019). A review of the environmental factors degrading the performance of silicon wafer-based photovoltaic modules: Failure detection methods and essential mitigation techniques. Renewable and Sustainable Energy Reviews,110, pp. 83-100.
• Gerger M, Gümüşçü A (2022) Diagnosis of Parkinson’s disease using spiral test based on pattern recognition. Romanian J Information Sci Technol 25(1):100–113
• Gümüşçü, A., Taşaltın, R. ve Aydilek, İ.B. (2016) C4.5 Karar ağaçlarında genetik algoritma ile budama, Dicle Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 5(2): 77-80.
• Gümüşçü A, Karadağ K, Tenekecı ME et al (2017) Genetic algorithm based feature selection on diagnosis of Parkinson disease via vocal analysis. In: 2017 25th Signal processing and communications applications conference (SIU). IEEE, pp 1–4
• Deitsch, S., et al. (2019). Automatic classification of defective photovoltaic module cells in electroluminescence images. Sol. Energy,185, pp. 455–468.
• Karimi, A. M., Fada, J. S., Parrilla, N. A., Pierce, B. G., Koyutürk, M., French, R. H., Braid, J. L. (2020). Generalized and Mechanistic PV Module Performance Prediction From Computer Vision and Machine Learning on Electroluminescence Images. IEEE Journal of Photovoltaics, 10(3), 878– 887.
• Demirci, M.Y., Beşli, N., Gümüşçü, A., 2019. Defective PV cell detection using deep transfer learning and EL imaging. In: Proceedings Book, p. 311.
• Demirci, M.Y., Beşli, N., and Gümüşçü, A. (2019). Defective PV Cell Detection Using DeepTransfer Learning and EL Imaging. In Proceedings of the International Conference on DataScience, Machine Learning and Statistics -2019 pp. 311-314.
• Demirci, M.Y., Beşli, N., and Gümüşçü, A. (2021). Efficient deep feature extraction and classification for identifying defective photovoltaic module cells in Electroluminescence images. Expert Systems with Applications, vol. 175, 114810.
• Li, X., Li, W., Yang, Q., Yan, W., and Zomaya,A. Y. (2019). Building an Online Defect Detection System for Large scale Photovoltaic Plants. in Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, pp. 253–262.
• Li, X., Yang, Q., Wang, J., Chen, Z., and Yan, W. (2018). Intelligent fault pattern recognition of aerial photovoltaic module images based on deep learning technique. J. Syst. Cybern. Inf, 16, pp. 67–71
• Balzategui, J., Eciolaza, L., Arana-Arexolaleiba, N., Altube, J., Aquerre, J.P., Legarda-Ere ̃no, I., Apraiz, A. (2019). Semi-automatic quality inspection of solar cell based on convolutional neural networks. in 2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), pp. 529–535.
• Bartler, A., Mauch, L., Yang, B., Reuter, M., Stoicescu, L. (2018). Automated detection of solarcell defects with deep learning. European Signal Processing Conference, 2035–2039,10.23919/EUSIPCO.2018.8553025.
• Chen, H., Zhao, H., Han, D., and Liu, K. (2019). Accurate and robust crack detection using steerable evidence filtering in electroluminescence images of solar cells. Opt. Lasers Eng., 118, pp. 22-33.
• Qian, X., Li, J., Cao, J., Wu, Y., and Wang, W. (2020). Micro-cracks detection of solar cells surfacevia combing short-term and long-term deep features. Neural Networks,127, pp. 132-140.
• Deitsch, S., et al. (2019). Automatic classification of defective photovoltaic module cells in electroluminescence images. Sol. Energy,185, pp. 455–468.
• Luo, Z., Cheng, S.Y., and Zheng, Q.Y. (2019). GAN-Based Augmentation for Improving CNN Performance of Classification of Defective Photovoltaic Module Cells in Electroluminescence Images. 2019 International Conference on New Energy and Future Energy System, IOP Conf. Ser.: Earth Environ. Sci. 354 01210
• Du, B., He,Y., Duan, J., and Zhang, Y. (2019). Intelligent classification of silicon photovoltaic cell defects based on eddy current thermography and convolution neural network. IEEE Trans. Ind. Informatics, 16(10), pp. 6242-6251.
• Akram, M.W., Li, G., Jin, Y., Chen, X., Zhu, C., Zhao, X., Khaliq, A., Faheem, M., Ahmad, A. (2019). CNN based automatic detection of photovoltaic cell defects in electroluminescence images. Energy, 189, pp.116319.
• Zhang, X., Hao, Y., Shangguan, H., Zhang, P., and Wang, A. (2020). Detection of surface defects on solar cells by fusing Multi-channel convolution neural networks. Infrared Phys. Technol, 108, pp. 103334.
• Mathias, N., Shaikh, F., Thakur, C., Shetty, S., Dumane P., and Chavan, S. (2020). Detection of Micro-Cracks in Electroluminescence Images of Photovoltaic Modules. Proceedings of the 3rd International Conference on Advances in Science and Technology (ICAST), Available at: http://dx.doi.org/10.2139/ssrn.3563821
• Koziarski, M., and Cyganek, B. (2017). Image recognition with deep neural networks in presence of noise – Dealing with and taking advantage of distortions. Integr. Comput. Aided. Eng., 24, pp. 337–349.
• Fawzi, A., Samulowitz, H., Turaga, D., And Frossard, P. (2016). Adaptive data augmentation for image classification. in 2016 IEEE International Conference on Image Processing (ICIP), pp. 3688– 3692.
• Banda, P., and Barnard, L. (2018). A deep learning approach to photovoltaic cell defect classification. in Proceedings of the Annual Conference of the South African Institute of Computer Scientists and Information Technologists, pp. 215–221.
• Sun, M., Lv, S., Zhao, X., Li, R., Zhang, W., and Zhang, X. (2017). Defect detection of photovoltaic modules based on convolutional neural network. in International Conference on Machine Learning and Intelligent Communications, pp. 122–132.
• Su, B., Chen, H., and Zhou, Z. (2020). BAF-Detector: An Efficient CNN- Based Detector for Photovoltaic Solar Cell Defect Detection. arXiv Prepr. arXiv2012.10631.
• Sarker, I.H. Machine Learning: Algorithms, Real-World Applications and Research Directions. SN COMPUT. SCI. 2, 160 (2021). https://doi.org/10.1007/s42979-021-00592-x
• He, K., Zhang, X., Ren, S., Sun, J. 2016, Deep residual learning for image recognition , InProceedings of the IEEE conference on computer vision and pattern recognition pp. 770-778.
• Iandola, F.N, Han S., Moskewicz M.W., Ashraf K., Dally W.J., Keutzer, K. SqueezeNet: AlexNetlevel accuracy with 50x fewer parameters. 3th International Conference on Learning Representations. Toulon: ICLR;2016. p.1-13.
• Cover T. , Hart P., 1967. Nearest Neighbor Pattern Classification, IEEE Transactions On Information Theory 13:21–27.
• Ben-Bassat, M., Klove, K. L., & Weil, M. H. (1980). Sensitivity analysis in Bayesian classification models: Multiplicative deviations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2, 261–266.