Deep Learning Based Fault Detection and Diagnosis in Photovoltaic System Using Thermal Images Acquired by UAV

Year 2024, , 91 - 99, 29.02.2024

Barış Kaycı Batıkan Erdem Demir Funda Demir

https://doi.org/10.2339/politeknik.1094586

Cited By: 1

Abstract

Solar power is one of the largest renewable energy sources in the world. With photovoltaic systems, electrical energy can be generated wherever the sun is located. To prevent efficiency losses in photovoltaic systems, these systems should be tested at regular intervals. In this study, it is discussed to detect cell, module and panel faults in panels using thermal images obtained from solar panels. Within the scope of the study, a four-rotor unmanned aerial vehicle (drone) was designed and a thermal camera was placed on the vehicle. Thus, thermal images of the solar panels on the roof of Karabuk University buildings were taken. A thermal data set with cell fault, module fault and panel fault were created using the resulting thermal images. The YOLOv3 deep learning-based convolutional neural network was trained with the created dataset. This training was conducted on Nvidia Jetson TX2, an embedded AI (Artificial Intelligence) computing device. After the completion of the training of the YOLOv3 network, it was concluded that the faults mentioned in the tests were successfully detected.  

Keywords

photovoltaic system, thermography, deep learning, fault detection, unmanned aerial vehicles

Supporting Institution

Karabuk University Scientific Research Projects

Project Number

FYL-2019-2131

Thanks

The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This study was supported by Karabuk University within the scope of Scientific Research Projects with FYL-2019-2131 code.

İHA Tarafından Elde Edilen Termal Görüntüler Kullanılarak Fotovoltaik Sistemde Derin Öğrenme Tabanlı Arıza Tespiti ve Teşhisi

Abstract

Güneş enerjisi, dünyanın en büyük yenilenebilir enerji kaynaklarından biridir. Fotovoltaik sistemler ile güneşin olduğu her yerde elektrik enerjisi üretilebilir. Fotovoltaik sistemlerde verim kayıplarını önlemek için bu sistemlerin düzenli aralıklarla test edilmesi gerekmektedir. Bu çalışmada güneş panellerinden elde edilen termal görüntüler kullanılarak panellerdeki hücre, modül ve panel arızalarının tespiti ele alınmıştır. Çalışma kapsamında dört rotorlu bir insansız hava aracı (drone) tasarlamış ve araca termal bir kamera yerleştirilmiştir. Böylelikle Karabük Üniversitesi binalarının çatısında bulunan güneş panellerinin termal görüntüleri alınmıştır. Elde edilen termal görüntüler kullanılarak hücre hatası, modül hatası ve panel hatasını içeren bir termal veri seti oluşturulmuştur. YOLOv3 derin öğrenme tabanlı evrişimsel sinir ağı, oluşturulan veri seti ile eğitilmiştir. Bu eğitim, gömülü bir yapay zeka bilgi işlem cihazı olan Nvidia Jetson TX2 üzerinde gerçekleştirilmiştir. YOLOv3 ağının eğitiminin tamamlanmasının ardından testlerde bahsedilen arızaların başarıyla tespit edildiği sonucuna ulaşılmıştır.

Keywords

Fotovoltaik sistem, termografi, derin öğrenme, arıza tespiti, insansız hava araçları

Project Number

FYL-2019-2131

References

• [1] Ozturk, C., "Data analysis and energy losses in solar energy systems", Master Thesis, Graduate Education Institute of Hasan Kalyoncu University, (2020).
• [2] Gedik, E., "Experimental investigation of module temperature effect on photovoltaic panels efficiency", Journal of Polytechnic, 19: 569–576, (2016).
• [3] Spagnolo G. S., Del Vecchio P., Makary G., Papalillo D., and Martocchia A., "A review of IR thermography applied to PV systems", in 11th International Conference on Environment and Electrical Engineering, Roma, Italy, 879–884, (2012).
• [4] Köntges M., Kurtz S., Packard C.E., Jahn U., Berger K., Kato K., Friesen T., Liu H., and Van Iseghem M., "Review of failures of photovoltaic modules", Report, IEA-Photovoltaic Power Systems Programme, (2014).
• [5] Li X., Yang Q., Lou Z., and Yan W., "Deep learning based module defect analysis for large-scale photovoltaic farms", IEEE Transactions on Energy Conversion, 34: 520–529, (2019).
• [6] Higuchi Y., and Babasaki T., "Failure detection of solar panels using thermographic images captured by drone", in 7th International Conference on Renewable Energy Research and Applications, Paris, France, 391–396, (2018).
• [7] Pierdicca R., Malinverni E. S., Piccinini, F., Paolanti M., Felicetti A., and Zingaretti P., "Deep convolutional neural network for automatic detection of damaged photovoltaic cells", in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Riva del Garda, Italy, 893–900, (2018).
• [8] Carletti V., Greco A., Saggese A., and Vento M., "An intelligent flying system for automatic detection of faults in photovoltaic plants", J. Ambient Intell. Humaniz. Comput., 11: 2027–2040, (2020).
• [9] Wei S., Li X., Ding S., Yang Q., and Yan W., "Hotspots Infrared detection of photovoltaic modules based on Hough line transformation and Faster-RCNN approach", in 6th International Conference on Control, Decision and Information Technologies, Paris, France, 1209–1214, (2019).
• [10] Akram M. W., Li Guiqiang, Jin Y., Chen, X., Zhu C., and Ahmad A., "Automatic detection of photovoltaic module defects in infrared images with isolated and develop-model transfer deep learning", Solar Energy, 198: 175–186, (2020).
• [11] Díaz J. J. V., Vlaminck M., Lefkaditis D., Vargas S. A. O., and Luong, H., "Solar panel detection within complex backgrounds using thermal images acquired by UAVs", Sensors, 20: 1–16, (2020).
• [12] Huerta Herraiz Á., Pliego Marugán A., and García Márquez F. P., "photovoltaic plant condition monitoring using thermal images analysis by convolutional neural network-based structure", Renewable Energy, 153: 334–348, (2020).
• [13] Henry, C., Poudel, S., Lee, S. W. & Jeong, H. Automatic Detection System of Deteriorated PV Modules Using Drone with Thermal Camera. Appl. Sci. 10, (2020).
• [14] Xie X., Wei X., Wang X., Guo X., Li J., and Cheng Z., "Photovoltaic panel anomaly detection system based on Unmanned Aerial Vehicle platform", IOP Conference Series: Materials Science and Engineering, 768: 1–7, (2020).
• [15] Naveen Venkatesh S., and Sugumaran V., "Fault detection in aerial images of photovoltaic modules based on deep learning", IOP Conference Series: Materials Science and Engineering, 1012: 1–9, (2021).
• [16] Süzen A. A., Duman B., and Şen B., "Benchmark analysis of Jetson TX2, Jetson Nano and Raspberry PI using Deep-CNN", in 2nd International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Ankara, Turkey, 3–7, (2020).
• [17] Rungsuptaweekoon K., Visoottiviseth V., and Takano R., "Evaluating the power efficiency of deep learning inference on embedded GPU systems", in 2nd International Conference on Information Technology, Nakhonpathom, Thailand, 117–121, (2017).
• [18] Şenalp, F. M., and Ceylan, M., "Deep learning based super resolution application for a new data set consisting of thermal facial images", Journal of Polytechnic, 1–1, (2022).
• [19] Ketkar N., and Moolayil J., "Deep Learning with Python", Apress, India, (2017).
• [20] Sözen E., Bardak T., Aydemir D., and Bardak S., "Estimation of deformation in nanocomposites using artificial neural networks and deep learning algorithms", Journal of Bartin Faculty of Forestry, 20: 223–231, (2018).
• [21] Aalami N., "Analysis of images using deep learning methods", Journal of ESTUDAM Information, 1: 17–20, (2020).
• [22] Altan G., "DeepGraphNet : deep learning models in the classification of graphs", European Journal of Science and Technology, 319–329, (2019).
• [23] İnik Ö., and Ülker E., "Deep learning and deep learning models used in image analysis", Gaziosmanpasa Journal of Scientific Research, 6: 85–104 (2017).
• [24] Bayram, F., "Automatic license plate recognition based on deep learning", Journal of Polytechnic, 23: 955–960, (2020).
• [25] Chen Y., Zhao X., and Jia X., "Spectral-Spatial classification of hyperspectral data based on deep belief network", IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 8: 2381–2392, (2015).
• [26] Redmon J., and Farhadi A., "YOLOv3: An Incremental Improvement", arXiv Prepr. arXiv1804.02767, 1-5, (2018).
• [27] Kılıç B., "Automatic nuclei detection with yolov3 algorithm on pleural effusion cytopatology images produced by panorama method", Master Thesis, Graduate Education Institute of Karadeniz Technical University, (2020).
• [28] Yu C. W., Chen Y. L., Lee K. F., Chen, C. H. and Hsiao C. Y., "Efficient intelligent automatic image annotation method based on machine learning techniques", in 2019 IEEE International Conference on Consumer Electronics, 2–3, (2019).
• [29] Kaycı B., "Deep learning based fault detection and diagnosis of solar panels using four-rotor UAV with termography method", Master Thesis, Graduate Education Institute of Karabuk University, (2021).