–
AI-Based PV Panels Inspection using an Advanced YOLO Algorithm
Agus HAERUMAN, Sami Ul HAQ, Mohamed MOHANDES, Shafiqur REHMAN, Sheikh Sharif Iqbal MITU
download PDFAbstract. The rapid growth of solar photovoltaic (PV) systems as green energy sources has gained momentum in recent years. However, the anomalies of PV panel defects can reduce its efficiency and minimize energy harvesting from the plant. The manual inspection of PV panel defects throughout the plant is costly and time-consuming. Thus, implementing more intelligent ways to inspect solar panel defects will provide more benefits than traditional ones. This study presents an implementation of a deep learning model to detect solar panel defects using an advanced object detection algorithm called You Look Only Once, version 7 (YOLOv7). YOLO is a popular algorithm in computer vision for classification and localization. The dataset utilized in this study was sourced from ROBOFLOW, consisting of 1660 infrared images showcasing thermal defects in PV panels. The model was constructed to identify a broader range of images with heterogeneity, leveraging the aforementioned dataset. Following validation, the model demonstrates a mean Average Precision (mAP) of 85.9%. With this accuracy, the model is relevant for real-world applications. This assertion is affirmed by testing the model with additional data from separate video-capturing PV panels. The video was recorded using a drone equipped with a thermal camera.
Keywords
Solar Energy, PV Panel Thermal Inspection, Artificial Intelligence, Deep Learning, Object Detection, YOLOv7
Published online 7/15/2024, 8 pages
Copyright © 2024 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Agus HAERUMAN, Sami Ul HAQ, Mohamed MOHANDES, Shafiqur REHMAN, Sheikh Sharif Iqbal MITU, AI-Based PV Panels Inspection using an Advanced YOLO Algorithm, Materials Research Proceedings, Vol. 43, pp 230-237, 2024
DOI: https://doi.org/10.21741/9781644903216-30
The article was published as article 30 of the book Renewable Energy: Generation and Application
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] S. Djordjevic, D. Parlevliet, and P. Jennings. Detectable faults on recently installed solar modules in Western Australia. Renewable Energy, 67:215-221, 2014. https://doi.org/10.1016/j.renene.2013.11.036
[2] Ronnie O Serfa Juan and Jeha Kim. Photovoltaic cell defect detection model based on extracted electroluminescence images using SVM classifier. In 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pages 578-582. IEEE, 2020. https://doi.org/10.1109/ICAIIC48513.2020.9065065
[3] M Waqar Akram, Guiqiang Li, Yi Jin, Xiao Chen, Changan Zhu, and Ashfaq Ahmad. Automatic detection of photovoltaic module defects in infrared images with isolated and develop-model transfer deep learning. Solar Energy, 198:175-186, 2020. https://doi.org/10.1016/j.solener.2020.01.055
[4] Alvaro Huerta Herraiz, Alberto Pliego Marugan, and Fausto Pedro Garcia Marquez. Photovoltaic plant condition monitoring using thermal images analysis by convolutional neural network-based structure. Renewable Energy, 153:334-348, 2020. https://doi.org/10.1016/j.renene.2020.01.148
[5] Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
[6] Long Wen, X Li, Xinyu Li, and Liang Gao. A new transfer learning based on VGG-19 network for fault diagnosis. In 2019 IEEE 23rd international conference on computer supported cooperative work in design (CSCWD), pages 205-209. IEEE, 2019. https://doi.org/10.1109/CSCWD.2019.8791884
[7] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1-9, 2015. https://doi.org/10.1109/CVPR.2015.7298594
[8] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770-778, 2016.
[9] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pages 234-241. Springer, 2015. https://doi.org/10.1007/978-3-319-24574-4_28
[10] Tsung-Yi Lin, Piotr Dollar, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2117-2125, 2017.
[11] Abhishek Chaurasia and Eugenio Culurciello. Linknet: Exploiting encoder representations for efficient semantic segmentation. In 2017 IEEE visual communications and image processing (VCIP), pages 1-4. IEEE, 2017. https://doi.org/10.1109/VCIP.2017.8305148
[12] Mingxing Tan and Quoc Le. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105-6114. PMLR, 2019.
[13] Minhhuy Le, Dang Khoa Nguyen, Van-Duong Dao, Ngoc Hung Vu, Hong Ha Thi Vu, et al. Remote anomaly detection and classification of solar photovoltaic modules based on deep neural network. Sustainable Energy Technologies and Assessments, 48:101545, 2021. https://doi.org/10.1016/j.seta.2021.101545
[14] Hazem Munawer Al-Otum. Deep learning-based automated defect classification in electroluminescence images of solar panels. Advanced Engineering Informatics, 58:102147, 2023. https://doi.org/10.1016/j.aei.2023.102147
[15] Minhhuy Le, DucVu Le, and Hong Ha Thi Vu. Thermal inspection of photovoltaic modules with deep convolutional neural networks on edge devices in AUV. Measurement, 218:113135, 2023. https://doi.org/10.1016/j.measurement.2023.113135
[16] Mustafa Yusuf Demirci, Nurettin Besli, and Abdulkadir Gumuscu. Efficient deep feature extraction and classification for identifying defective photovoltaic module cells in electroluminescence images. Expert Systems with Applications, 175:114810, 2021. https://doi.org/10.1016/j.eswa.2021.114810
[17] Stefan Bordihn, Andreas Fladung, Jan Schlipf, and Marc Kontges. Machine learning based identification and classification of field-operation caused solar panel failures observed in electroluminescence images. IEEE Journal of Photovoltaics, 12(3):827-832, 2022. https://doi.org/10.1109/JPHOTOV.2022.3150725
[18] Harsh Rajesh Parikh, Yoann Buratti, Sergiu Spataru, Frederik Villebro, Gisele Alves Dos Reis Benatto, Peter B. Poulsen, Stefan Wendlandt, Tamas Kerekes, Dezso Sera, and Ziv Hameiri. Solar cell cracks and finger failure detection using statistical parameters of electroluminescence images and machine learning. Applied Sciences, 10(24), 2020. https://doi.org/10.3390/app10248834
[19] Ronnie O. Serfa Juan and Jeha Kim. Photovoltaic cell defect detection model based on extracted electroluminescence images using SVM classifier. In 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pages 578-582, 2020. https://doi.org/10.1109/ICAIIC48513.2020.9065065
[20] Sergiu Deitsch, Vincent Christlein, Stephan Berger, Claudia BuerhopLutz, Andreas K. Maier, Florian Gallwitz, and Christian Riess. Automatic classification of defective photovoltaic module cells in electroluminescence images. ArXiv, abs/1807.02894, 2018.
[21] Abraham Kaligambe and Goro Fujita. A deep learning-based framework for automatic detection of defective solar photovoltaic cells in electroluminescence images using transfer learning. In 2023 4th International Conference on High Voltage Engineering and Power Systems (ICHVEPS), pages 81-85, 2023. https://doi.org/10.1109/ICHVEPS58902.2023.10257399
[22] Christine Dewi, Abbott Po Shun Chen, and Henoch Juli Christanto. Deep learning for highly accurate hand recognition based on yolov7 model. Big Data and Cognitive Computing, 7(1), 2023. https://doi.org/10.3390/bdcc7010053
[23] Solveview. Thermal defects dataset. https://universe.roboflow.com/solveview/thermal-defects , Aug 2023. visited on 2023-11-20.
[24] Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7464-7475, 2023.
[25] Xiang Long, Kaipeng Deng, Guanzhong Wang, Yang Zhang, Qingqing Dang, Yuan Gao, Hui Shen, Jianguo Ren, Shumin Han, Errui Ding, et al. Pp-yolo: An effective and efficient implementation of object detector. arXiv preprint arXiv:2007.12099, 2020.
[26] www.ThermalCamUSA.com. Infrared solar panel inspection by drone. https://www.youtube.com/watch?v=1E-_N-KtQTQ, Feb 2018. visited on 2023-11-20.
