Research Article
BibTex RIS Cite

DETECTION OF DUST ON SOLAR PANELS WITH DEEP LEARNING

Year 2024, , 1451 - 1464, 03.12.2024

Tuba Sefer , Mahmut Kaya

https://doi.org/10.17780/ksujes.1493906

Abstract

Solar energy is an environmentally friendly, clean, and sustainable alternative. The widespread use of this energy source offers excellent environmental and economic benefits. However, some factors affect the efficiency of solar panels. One of these factors is dust. When dust accumulates on the surface of solar panels, it can significantly reduce the efficiency of energy production. Therefore, detecting and quickly removing dust from solar panels is crucial. Managing this process with unmanned artificial intelligence systems, especially in large areas, will provide significant advantages in terms of time and cost. In recent years, convolutional neural networks have achieved significant success in image classification. In particular, transfer learning methods have proven their success in this field. In this study, we aim to solve a new task with limited data using pre-trained deep learning models (EfficientNetB3, ResNet50, MobileNet, VGG19, Xception, InceptionResNetV2, VGG16, ResNet101, DenseNet201, EfficientNetB7) to classify dirty and clean solar panels. These models were chosen because they each have different strengths and have performed well on various tasks. The models with the best performance among these models are combined to improve classification prediction. The proposed ensemble learning approach achieved 99.31% classification accuracy by considering the prediction results of the models with a voting approach. As a result, this approach aims to optimize the maintenance processes of solar energy systems, improve energy efficiency, and support sustainable energy use in the long term.

Keywords

Deep learning energy efficiency sustainable energy transfer learning ensemble learning

Thanks

This article is based on Tuba SEFER's Master's thesis entitled “Dust detection on solar panels with deep learning”, conducted under the supervision of Dr. Mahmut KAYA at Siirt University, Institute of Science and Technology, Department of Computer Engineering.

References

  • Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. IEEE conference on computer vision and pattern recognition (pp. 1251-1258).
  • Çetin, S., Turan, E., & Bayrakdar, E. (2019). Türkiye'nin güneş enerjisi politikaları. Third Sector Social Economic Review, Ankara, 54(2), 949-968. http://dx.doi.org/10.15659/3.sektor-sosyal-ekonomi.19.04.1118
  • Canbay, Y., İsmetoğlu A., Canbay, P., (2021). Covid-19 Hastalığının Teşhisinde Derin Öğrenme ve Veri Mahremiyeti, Mühendislik Bilimleri ve Tasarım Dergisi, 9(2), 701-715. https://doi.org/10.21923/jesd.870263
  • Davaadorj, U., Yoo, K. H., Choi, S. H., & Nasridinov, A. (2021). The Soiling Classification of Solar Panel using Deep Learning. International Conference on Convergence Content, (pp. 59-60).
  • Dwivedi, D., Babu, K. V. S. M., Yemula, P. K., Chakraborty, P., & Pal, M. (2024). Identifying surface defects on solar PV panels and wind turbine blades using an attention-based deep learning model. Engineering Applications of Artificial Intelligence, 1-28, https://doi.org/10.1016/j.engappai.2023.107836.
  • Ferrell, D. & Anderson, E. (2023). Adapting and Generalizing Convolutional Neural Networks in Detecting Dust on Solar Panels, preprint researchgate, 1-6.
  • He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
  • Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861. https://doi.org/10.48550/arXiv.1704.04861
  • Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).
  • Kanani, P., & Padole, M. (2019). Deep learning to detect skin cancer using google colab. International Journal of Engineering and Advanced Technology Regular Issue, 8(6), 2176-2183. https://doi.org/10.35940/ijeat.F8587.088619
  • Kaya, Y., Yiner, Z., Kaya, M., & Kuncan, F. (2022). A new approach to COVID-19 detection from X-ray images using angle transformation with GoogleNet and LSTM. Measurement Science and Technology, 33(12), 124011. https://doi.org/10.1088/1361-6501/ac8ca4
  • LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
  • Maity, R., Shamaun Alam, M., & Pati, A. (2020). An Approach for Detection of Dust on Solar Panels Using CNN from RGB Dust Image to Predict Power Loss. Cognitive Computing in Human Cognition: Perspectives and Applications, 41-48. https://doi.org/10.1007/978-3-030-48118-6_4
  • Mete, S., Çakır, O., Bayat, O., Duru, D. G., & Duru, A. D. (2020). Gözbebeği hareketleri temelli duygu durumu sınıflandırılması. Bilişim Teknolojileri Dergisi, 13(2), 137-144. https://doi.org/10.17671/gazibtd.563830
  • Onim, M. S. H., Sakif, Z. M. M., Ahnaf, A., Kabir, A., Azad, A. K., Oo, A. M. T., & Ali, M. S. (2023). Solnet: A convolutional neural network for detecting dust on solar panels. Energies, 16(1), 155. https://doi.org/10.3390/en16010155
  • Pan, S. J., & Yang, Q. (2009). A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10), 1345-1359. https://doi.org/10.1109/TKDE.2009.191
  • Prabhakaran, S., Uthra, R. A., & Preetharoselyn, J. (2023). Deep Learning-Based Model for Defect Detection and Localization on Photovoltaic Panels. Computer Systems Science and Engineering, 44(3), 2683-2700. http://dx.doi.org/10.32604/csse.2023.028898
  • Saqlain, M., Jargalsaikhan, B., & Lee, J. Y. (2019). A voting ensemble classifier for wafer map defect patterns identification in semiconductor manufacturing. IEEE Transactions on Semiconductor Manufacturing, 32(2), 171–182. https://doi.org/10.1109/TSM.2019.2904306
  • Selvi, S., Devaraj, V., Prabha, R. P. S., & Subramani, K. (2023). Detection of Soiling on PV Module using Deep Learning. SSRG International Journal of Electrical and Electronics Engineering, 10(7), 93-101. https://doi.org/10.14445/23488379/IJEEE-V10I7P108
  • Sewell, M. (2008). Ensemble learning. RN, 11(02), 1-34.
  • Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. https://doi.org/10.48550/arXiv.1409.1556
  • Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006, December). Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. Australasian joint conference on artificial intelligence (pp. 1015-1021). https://doi.org/10.1007/11941439_114
  • Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017, February). Inception-v4, inception-resnet and the impact of residual connections on learning. Thirsty-First AAAI conference on artificial intelligence, (pp. 4278-4284) https://doi.org/10.1609/aaai.v31i1.11231
  • Şenol, A., Canbay, Y., & Kaya, M. (2021). Trends in Outbreak Detection in Early Stage by Using Machine Learning Approaches. Bilişim Teknolojileri Dergisi, 14(4), 355-366. https://doi.org/10.17671/gazibtd.878089
  • Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. International conference on machine learning (pp. 6105-6114).
  • Utku, A., & Akcayol, M. A. (2024). Spread patterns of COVID-19 in European countries: hybrid deep learning model for prediction and transmission analysis. Neural Computing and Applications, 36, 10201–10217. https://doi.org/10.1007/s00521-024-09597-y
  • Yarğı, V., & Postalcıoğlu, S. (2021). EEG işareti kullanılarak bağımlılığa yatkınlığın makine öğrenmesi teknikleri ile analizi. El-Cezeri, 8(1), 142-154. https://doi.org/10.31202/ecjse.787726
  • Zyout, I. & Oatawneh, A. (2020), February. Detection of PV solar panel surface defects using transfer learning of the deep convolutional neural networks. Advances in Science and Engineering Technology International Conferences (ASET), (pp. 1-4). https://doi.org/10.1109/ASET48392.2020.9118384

GÜNEŞ PANELLERİ ÜZERİNDEKİ TOZUN DERİN ÖĞRENME İLE TESPİTİ

Year 2024, , 1451 - 1464, 03.12.2024

Tuba Sefer , Mahmut Kaya

https://doi.org/10.17780/ksujes.1493906

Abstract

Güneş enerjisi, temiz ve sürdürülebilir bir enerji kaynağı olarak çevre dostu bir alternatiftir. Bu enerji kaynağının yaygınlaşması, hem çevre hem de ekonomik açıdan büyük faydalar sunar. Ancak, güneş panellerinin verimliliğini etkileyen bazı unsurlar vardır. Bu unsurlardan biri de tozdur. Toz, güneş panellerinin yüzeyine biriktiğinde enerji üretim verimliliğini önemli ölçüde düşürebilir. Bu nedenle, güneş panellerindeki tozun tespiti ve hızlı bir şekilde temizlenmesi büyük önem taşır. Özellikle geniş alanlarda bu sürecin insansız yapay zekâ sistemleriyle yönetilmesi, hem zaman hem de maliyet açısından önemli avantajlar sağlayacaktır. Son yıllarda evrişimsel sinir ağları görüntü sınıflandırma konusunda önemli başarılar elde etmiştir. Özellikle transfer öğrenme yöntemleri bu alanda başarısını kanıtlamıştır. Bu çalışmada, kirli ve temiz güneş panellerini sınıflandırmak için önceden eğitilmiş derin öğrenme modellerini (EfficientNetB3, ResNet50, MobileNet, VGG19, Xception, InceptionResNetV2, VGG16, ResNet101, DenseNet201, EfficientNetB7) kullanarak sınırlı veri ile yeni bir görevi çözme amaçlanmaktadır. Bu modellerin seçilme nedeni, her birinin farklı güçlü yönlere sahip olması ve çeşitli görevlerde başarılı performans sergilemiş olmalarıdır. Bu modeller arasında en iyi performansa sahip modeller, sınıflandırma tahminini iyileştirmek için birleştirilmiştir. Önerilen topluluk öğrenme yaklaşımı, modellerin tahmin sonuçlarını oylama yaklaşımıyla ele alarak %99,31 sınıflandırma doğruluğuna ulaşmıştır. Sonuç olarak, bu yaklaşım güneş enerjisi sistemlerinin bakım süreçlerini optimize etmeyi, enerji verimliliğini artırmayı ve uzun vadede sürdürülebilir enerji kullanımını desteklemeyi amaçlamaktadır.

Keywords

Derin öğrenme enerji verimliliği sürdürülebilir enerji transfer öğrenme topluluk öğrenme

References

  • Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. IEEE conference on computer vision and pattern recognition (pp. 1251-1258).
  • Çetin, S., Turan, E., & Bayrakdar, E. (2019). Türkiye'nin güneş enerjisi politikaları. Third Sector Social Economic Review, Ankara, 54(2), 949-968. http://dx.doi.org/10.15659/3.sektor-sosyal-ekonomi.19.04.1118
  • Canbay, Y., İsmetoğlu A., Canbay, P., (2021). Covid-19 Hastalığının Teşhisinde Derin Öğrenme ve Veri Mahremiyeti, Mühendislik Bilimleri ve Tasarım Dergisi, 9(2), 701-715. https://doi.org/10.21923/jesd.870263
  • Davaadorj, U., Yoo, K. H., Choi, S. H., & Nasridinov, A. (2021). The Soiling Classification of Solar Panel using Deep Learning. International Conference on Convergence Content, (pp. 59-60).
  • Dwivedi, D., Babu, K. V. S. M., Yemula, P. K., Chakraborty, P., & Pal, M. (2024). Identifying surface defects on solar PV panels and wind turbine blades using an attention-based deep learning model. Engineering Applications of Artificial Intelligence, 1-28, https://doi.org/10.1016/j.engappai.2023.107836.
  • Ferrell, D. & Anderson, E. (2023). Adapting and Generalizing Convolutional Neural Networks in Detecting Dust on Solar Panels, preprint researchgate, 1-6.
  • He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
  • Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861. https://doi.org/10.48550/arXiv.1704.04861
  • Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).
  • Kanani, P., & Padole, M. (2019). Deep learning to detect skin cancer using google colab. International Journal of Engineering and Advanced Technology Regular Issue, 8(6), 2176-2183. https://doi.org/10.35940/ijeat.F8587.088619
  • Kaya, Y., Yiner, Z., Kaya, M., & Kuncan, F. (2022). A new approach to COVID-19 detection from X-ray images using angle transformation with GoogleNet and LSTM. Measurement Science and Technology, 33(12), 124011. https://doi.org/10.1088/1361-6501/ac8ca4
  • LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
  • Maity, R., Shamaun Alam, M., & Pati, A. (2020). An Approach for Detection of Dust on Solar Panels Using CNN from RGB Dust Image to Predict Power Loss. Cognitive Computing in Human Cognition: Perspectives and Applications, 41-48. https://doi.org/10.1007/978-3-030-48118-6_4
  • Mete, S., Çakır, O., Bayat, O., Duru, D. G., & Duru, A. D. (2020). Gözbebeği hareketleri temelli duygu durumu sınıflandırılması. Bilişim Teknolojileri Dergisi, 13(2), 137-144. https://doi.org/10.17671/gazibtd.563830
  • Onim, M. S. H., Sakif, Z. M. M., Ahnaf, A., Kabir, A., Azad, A. K., Oo, A. M. T., & Ali, M. S. (2023). Solnet: A convolutional neural network for detecting dust on solar panels. Energies, 16(1), 155. https://doi.org/10.3390/en16010155
  • Pan, S. J., & Yang, Q. (2009). A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10), 1345-1359. https://doi.org/10.1109/TKDE.2009.191
  • Prabhakaran, S., Uthra, R. A., & Preetharoselyn, J. (2023). Deep Learning-Based Model for Defect Detection and Localization on Photovoltaic Panels. Computer Systems Science and Engineering, 44(3), 2683-2700. http://dx.doi.org/10.32604/csse.2023.028898
  • Saqlain, M., Jargalsaikhan, B., & Lee, J. Y. (2019). A voting ensemble classifier for wafer map defect patterns identification in semiconductor manufacturing. IEEE Transactions on Semiconductor Manufacturing, 32(2), 171–182. https://doi.org/10.1109/TSM.2019.2904306
  • Selvi, S., Devaraj, V., Prabha, R. P. S., & Subramani, K. (2023). Detection of Soiling on PV Module using Deep Learning. SSRG International Journal of Electrical and Electronics Engineering, 10(7), 93-101. https://doi.org/10.14445/23488379/IJEEE-V10I7P108
  • Sewell, M. (2008). Ensemble learning. RN, 11(02), 1-34.
  • Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. https://doi.org/10.48550/arXiv.1409.1556
  • Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006, December). Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. Australasian joint conference on artificial intelligence (pp. 1015-1021). https://doi.org/10.1007/11941439_114
  • Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017, February). Inception-v4, inception-resnet and the impact of residual connections on learning. Thirsty-First AAAI conference on artificial intelligence, (pp. 4278-4284) https://doi.org/10.1609/aaai.v31i1.11231
  • Şenol, A., Canbay, Y., & Kaya, M. (2021). Trends in Outbreak Detection in Early Stage by Using Machine Learning Approaches. Bilişim Teknolojileri Dergisi, 14(4), 355-366. https://doi.org/10.17671/gazibtd.878089
  • Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. International conference on machine learning (pp. 6105-6114).
  • Utku, A., & Akcayol, M. A. (2024). Spread patterns of COVID-19 in European countries: hybrid deep learning model for prediction and transmission analysis. Neural Computing and Applications, 36, 10201–10217. https://doi.org/10.1007/s00521-024-09597-y
  • Yarğı, V., & Postalcıoğlu, S. (2021). EEG işareti kullanılarak bağımlılığa yatkınlığın makine öğrenmesi teknikleri ile analizi. El-Cezeri, 8(1), 142-154. https://doi.org/10.31202/ecjse.787726
  • Zyout, I. & Oatawneh, A. (2020), February. Detection of PV solar panel surface defects using transfer learning of the deep convolutional neural networks. Advances in Science and Engineering Technology International Conferences (ASET), (pp. 1-4). https://doi.org/10.1109/ASET48392.2020.9118384
There are 28 citations in total.

Details

Primary Language English
Subjects Deep Learning, Neural Networks
Journal Section Computer Engineering
Authors

Tuba Sefer 0009-0002-5650-1683

Mahmut Kaya 0000-0002-7846-1769

Publication Date December 3, 2024
Submission Date June 1, 2024
Acceptance Date July 19, 2024
Published in Issue Year 2024

Cite

APA Sefer, T., & Kaya, M. (2024). DETECTION OF DUST ON SOLAR PANELS WITH DEEP LEARNING. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 27(4), 1451-1464. https://doi.org/10.17780/ksujes.1493906