Güneş Paneli Kusurlarının Derin Öğrenme Tabanlı Sınıflandırılması

Öz

Yenilenemez enerji kaynaklarının çevreye ve ekolojiye verdiği zararlar, yenilenebilir enerji kaynaklarına olan ilginin artmasına neden olmaktadır. Fotovoltaik (FV) enerji üretimi, temiz ve sürdürülebilir enerji üretimi için mükemmel enerji alternatiflerinden biridir. Fotovoltaik paneller üzerindeki kar, toz, gölge, kuş pisliği, mekaniksel ve fiziksel arıza gibi etkenler enerji üretimindeki verimi azaltmaktadır ve bu yüzden panel bakımı düzenli olarak yapılmalıdır. Bakımlar manuel olarak yapıldığında hatalar olmakta ve uzun zaman almaktadır. Bu nedenle güneş paneli kusurları son zamanlarda geliştirilen görüntü işleme ve derin öğrenme algoritmaları kullanılarak tespit edilebilmektedir. Bu çalışmada, derin öğrenme tekniği kullanılarak güneş panelleri üzerinde hasar tespiti sınıflandırması yapılmıştır. Çalışma iki aşamadan oluşmaktadır. İlk aşama, ön işleme aşamasıdır ve bu aşamada veri seti yetersiz olması nedeniyle veri çoğaltma teknikleri kullanılarak arttırılmıştır. İkinci aşama olan eğitim aşamasında ise çoğaltılan veri seti önerilen derin öğrenme modeliyle eğitilmiştir. Eğitim sonucunda önerilen modelin 7 farklı kusurun sınıflandırılmasında %96.56 başarı elde ettiği gözlenmiştir.

Anahtar Kelimeler

• Derin öğrenme
• Güneş panelleri
• Fotovoltaik
• Veri çoğaltma
• Sınıflandırma

Kaynakça

1. “Times of 1500 PV system has come” URL: https://www.mornsun-power.com/html/news-detail/blog-posts/213.html
2. “Times of 1500 PV system has come” URL: https://www.mornsun-power.com/html/news-detail/blog-posts/213.html
3. Platon, R., Martel, J. T., Woodruff, N., & Chau, T. Y. (2015b). Online fault detection in PV systems. IEEE Transactions on Sustainable Energy, 6(4), 1200–1207. https://doi.org/10.1109/tste.2015.2421447
4. Platon, R., Martel, J. T., Woodruff, N., & Chau, T. Y. (2015b). Online fault detection in PV systems. IEEE Transactions on Sustainable Energy, 6(4), 1200–1207. https://doi.org/10.1109/tste.2015.2421447
5. Li, B., Delpha, C., Diallo, D., & Migan Dubois, A. (2021). Application of artificial neural networks to photovoltaic fault detection and diagnosis: A review. Renewable & Sustainable Energy Reviews, 138, 110512. https://doi.org/10.1016/j.rser.2020.110512
6. Li, B., Delpha, C., Diallo, D., & Migan Dubois, A. (2021). Application of artificial neural networks to photovoltaic fault detection and diagnosis: A review. Renewable & Sustainable Energy Reviews, 138, 110512. https://doi.org/10.1016/j.rser.2020.110512
7. Tang, W., Yang, Q., Xiong, K., & Yan, W. (2020). Deep learning based automatic defect identification of photovoltaic module using electroluminescence images. Solar Energy, 201, 453–460. https://doi.org/10.1016/j.solener.2020.03.049
8. Tang, W., Yang, Q., Xiong, K., & Yan, W. (2020). Deep learning based automatic defect identification of photovoltaic module using electroluminescence images. Solar Energy, 201, 453–460. https://doi.org/10.1016/j.solener.2020.03.049

9. Jordan, D., Kurtz, S., VanSant, K., & Newmiller, J. (2016). Compendium of photovoltaic degradation rates. progress in photovoltaics, 24(7), 978–989. https://doi.org/10.1002/pip.2744
10. Jordan, D., Kurtz, S., VanSant, K., & Newmiller, J. (2016). Compendium of photovoltaic degradation rates. progress in photovoltaics, 24(7), 978–989. https://doi.org/10.1002/pip.2744
11. Korkmaz, D., & Açıkgöz, H. (2022). An efficient fault classification method in solar photovoltaic modules using transfer learning and multi-scale convolutional neural network. Engineering Applications of Artificial Intelligence, 113, 104959. https://doi.org/10.1016/j.engappai.2022.104959
12. Korkmaz, D., & Açıkgöz, H. (2022). An efficient fault classification method in solar photovoltaic modules using transfer learning and multi-scale convolutional neural network. Engineering Applications of Artificial Intelligence, 113, 104959. https://doi.org/10.1016/j.engappai.2022.104959
13. Espinosa, A. R., Bressan, M., & Giraldo, L. F. (2020). Failure signature classification in solar photovoltaic plants using RGB images and convolutional neural networks. Renewable Energy,162,249–256. https://doi.org/10.1016/j.renene.2020.07.154
14. Espinosa, A. R., Bressan, M., & Giraldo, L. F. (2020). Failure signature classification in solar photovoltaic plants using RGB images and convolutional neural networks. Renewable Energy,162,249–256. https://doi.org/10.1016/j.renene.2020.07.154
15. Kayci, B., Demir, B. E., & Demir, F. (2022). İHA tarafından elde edilen termal görüntüler kullanılarak fotovoltaik sistemde derin öğrenme tabanlı arıza tespiti ve teşhisi. Politeknik Dergisi, 1, 1. https://doi.org/10.2339/politeknik.1094586
16. Kayci, B., Demir, B. E., & Demir, F. (2022). İHA tarafından elde edilen termal görüntüler kullanılarak fotovoltaik sistemde derin öğrenme tabanlı arıza tespiti ve teşhisi. Politeknik Dergisi, 1, 1. https://doi.org/10.2339/politeknik.1094586
17. Pierdicca, R., Malinverni, E. S., Piccinini, F., Paolanti, M., Felicetti, A., & Zingaretti, P. (2018). Deep convolutıonal neural network for automatıc detectıon of damaged photovoltaıc cells. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII–2, 893–900. https://doi.org/10.5194/isprs-archives-xlii-2-893-2018
18. Pierdicca, R., Malinverni, E. S., Piccinini, F., Paolanti, M., Felicetti, A., & Zingaretti, P. (2018). Deep convolutıonal neural network for automatıc detectıon of damaged photovoltaıc cells. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII–2, 893–900. https://doi.org/10.5194/isprs-archives-xlii-2-893-2018
19. Li, X., Yang, Q., Lou, Z., & Yan, W. (2019). Deep learning based module defect analysis for large-scale photovoltaic farms. IEEE Transactions on Energy Conversion, 34(1), 520–529. https://doi.org/10.1109/tec.2018.2873358
20. Li, X., Yang, Q., Lou, Z., & Yan, W. (2019). Deep learning based module defect analysis for large-scale photovoltaic farms. IEEE Transactions on Energy Conversion, 34(1), 520–529. https://doi.org/10.1109/tec.2018.2873358
21. S. Wei, X. Li, S. Ding, Q. Yang and W. Yan, (2019). Hotspots Infrared detection of photovoltaic modules based on hough line transformation and faster-rcnn approach, 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 1266-1271, https://doi.org/10.1109/codit.2019.8820333
22. S. Wei, X. Li, S. Ding, Q. Yang and W. Yan, (2019). Hotspots Infrared detection of photovoltaic modules based on hough line transformation and faster-rcnn approach, 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 1266-1271, https://doi.org/10.1109/codit.2019.8820333
23. Herráiz, Á. H., Marugán, A. P., & Márquez, F. P. G. (2020). Photovoltaic plant condition monitoring using thermal images analysis by convolutional neural network-based structure. Renewable Energy, 153, 334–348. https://doi.org/10.1016/j.renene.2020.01.148
24. Herráiz, Á. H., Marugán, A. P., & Márquez, F. P. G. (2020). Photovoltaic plant condition monitoring using thermal images analysis by convolutional neural network-based structure. Renewable Energy, 153, 334–348. https://doi.org/10.1016/j.renene.2020.01.148
25. Venkatesh, S., & Sugumaran, V. (2021). Fault detection in aerial images of photovoltaic modules based on deep learning. IOP Conference Series, 1012(1), 012030. https://doi.org/10.1088/1757-899x/1012/1/012030
26. Venkatesh, S., & Sugumaran, V. (2021). Fault detection in aerial images of photovoltaic modules based on deep learning. IOP Conference Series, 1012(1), 012030. https://doi.org/10.1088/1757-899x/1012/1/012030
27. Xie, X., Wei, X., Wang, X., Guo, X., Ju, L., & Cheng, Z. (2020). Photovoltaic panel anomaly detection system based on unmanned aerial vehicle platform. IOP Conference Series, 768(7), 072061. https://doi.org/10.1088/1757-899x/768/7/072061
28. Xie, X., Wei, X., Wang, X., Guo, X., Ju, L., & Cheng, Z. (2020). Photovoltaic panel anomaly detection system based on unmanned aerial vehicle platform. IOP Conference Series, 768(7), 072061. https://doi.org/10.1088/1757-899x/768/7/072061
29. Díaz, J. J. V., Vlaminck, M., Lefkaditis, D., Vargas, S. a. O., & Luong, H. (2020). Solar panel detection within complex backgrounds using thermal images acquired by UAVs. Sensors, 20(21), 6219. https://doi.org/10.3390/s20216219
30. Díaz, J. J. V., Vlaminck, M., Lefkaditis, D., Vargas, S. a. O., & Luong, H. (2020). Solar panel detection within complex backgrounds using thermal images acquired by UAVs. Sensors, 20(21), 6219. https://doi.org/10.3390/s20216219
31. Akram, M. W., Li, G., Jin, Y., Xiao, C., Zhu, C., & Ahmad, A. (2020). Automatic detection of photovoltaic module defects in infrared images with isolated and develop-model transfer deep learning. solar energy, 198, 175–186. https://doi.org/10.1016/j.solener.2020.01.055
32. Akram, M. W., Li, G., Jin, Y., Xiao, C., Zhu, C., & Ahmad, A. (2020). Automatic detection of photovoltaic module defects in infrared images with isolated and develop-model transfer deep learning. solar energy, 198, 175–186. https://doi.org/10.1016/j.solener.2020.01.055
33. Kurukuru, V. S. B., Haque, A., Khan, M. A., & Tripathy, A. K. (2019). Fault classification for photovoltaic modules using thermography and machine learning techniques, 2019 International Conference on Computer and Information Sciences (ICCIS), pp. 1-6, https://doi.org/10.1109/iccisci.2019.8716442
34. Kurukuru, V. S. B., Haque, A., Khan, M. A., & Tripathy, A. K. (2019). Fault classification for photovoltaic modules using thermography and machine learning techniques, 2019 International Conference on Computer and Information Sciences (ICCIS), pp. 1-6, https://doi.org/10.1109/iccisci.2019.8716442
35. Zaki, S. A., Zhu, H., Fakih, M. A., Sayed, A. R., & Yao, J. (2021). Deep learning–based method for faults classification of PV system. Iet Renewable Power Generation, 15(1), 193–205. https://doi.org/10.1049/rpg2.12016
36. Zaki, S. A., Zhu, H., Fakih, M. A., Sayed, A. R., & Yao, J. (2021). Deep learning–based method for faults classification of PV system. Iet Renewable Power Generation, 15(1), 193–205. https://doi.org/10.1049/rpg2.12016
37. Deitsch, S., Christlein, V., Berger, S., Buerhop Lutz, C., Maier, A., Gallwitz, F., & Rieß, C. (2019). Automatic classification of defective photovoltaic module cells in electroluminescence images. Solar Energy, 185, 455–468. https://doi.org/10.1016/j.solener.2019.02.067
38. Deitsch, S., Christlein, V., Berger, S., Buerhop Lutz, C., Maier, A., Gallwitz, F., & Rieß, C. (2019). Automatic classification of defective photovoltaic module cells in electroluminescence images. Solar Energy, 185, 455–468. https://doi.org/10.1016/j.solener.2019.02.067
39. Tang, W., Yang, Q., Xiong, K., & Yan, W. (2020b). Deep learning based automatic defect identification of photovoltaic module using electroluminescence images. Solar Energy, 201, 453–460. https://doi.org/10.1016/j.solener.2020.03.049
40. Tang, W., Yang, Q., Xiong, K., & Yan, W. (2020b). Deep learning based automatic defect identification of photovoltaic module using electroluminescence images. Solar Energy, 201, 453–460. https://doi.org/10.1016/j.solener.2020.03.049
41. Solar panel clean and faulty images. (2023, May 16).Kaggle. https://www.kaggle.com/datasets/pythonafroz/solar-panel-clean-and-faulty-images
42. Solar panel clean and faulty images. (2023, May 16).Kaggle. https://www.kaggle.com/datasets/pythonafroz/solar-panel-clean-and-faulty-images
43. LeCun, Y., Bengio, Y., & Hinton, G. E. (2015b). Deep learning. nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
44. LeCun, Y., Bengio, Y., & Hinton, G. E. (2015b). Deep learning. nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
45. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84–90. https://doi.org/10.1145/3065386
46. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84–90. https://doi.org/10.1145/3065386
47. İnik, Ö. & Ülker, E. (2017). Derin öğrenme ve görüntü analizinde kullanılan derin öğrenme modelleri, Gaziosmanpaşa Bilimsel Araştırma Dergisi, c. 6, sayı. 3, ss. 85-104. http://dergipark.gov.tr/download/article-file/380999
48. İnik, Ö. & Ülker, E. (2017). Derin öğrenme ve görüntü analizinde kullanılan derin öğrenme modelleri, Gaziosmanpaşa Bilimsel Araştırma Dergisi, c. 6, sayı. 3, ss. 85-104. http://dergipark.gov.tr/download/article-file/380999
49. Scherer, D., Müller, A., & Behnke, S. (2010). Evaluation of pooling operations in convolutional architectures for object recognition. ın proceedings of the International Greece, Springer: Berlin/Heidelberg, Germany, 2010; pp. 92–101.
50. Scherer, D., Müller, A., & Behnke, S. (2010). Evaluation of pooling operations in convolutional architectures for object recognition. ın proceedings of the International Greece, Springer: Berlin/Heidelberg, Germany, 2010; pp. 92–101.