Browse > Article
http://dx.doi.org/10.6109/jkiice.2021.25.12.1777

Implementation of Photovoltaic Panel failure detection system using semantic segmentation  

Shin, Kwang-Seong (Department of Digital Contents Engineering, Wonkwang University)
Shin, Seong-Yoon (Department of Computer Information Engineering, Kunsan National University)
Publication Information
Journal of the Korea Institute of Information and Communication Engineering / v.25, no.12, 2021 , pp. 1777-1783 More about this Journal
Abstract
The use of drones is gradually increasing for the efficient maintenance of large-scale renewable energy power generation complexes. For a long time, photovoltaic panels have been photographed with drones to manage panel loss and contamination. Various approaches using artificial intelligence are being tried for efficient maintenance of large-scale photovoltaic complexes. Recently, semantic segmentation-based application techniques have been developed to solve the image classification problem. In this paper, we propose a classification model using semantic segmentation to determine the presence or absence of failures such as arcs, disconnections, and cracks in solar panel images obtained using a drone equipped with a thermal imaging camera. In addition, an efficient classification model was implemented by tuning several factors such as data size and type and loss function customization in U-Net, which shows robust classification performance even with a small dataset.
Keywords
Segmentation; Photovoltaic panel; UAV; U-Net;
Citations & Related Records
연도 인용수 순위
  • Reference
1 H. Y. Jeong and J. E. Park, "Creating Shared Value Strategies of Public Enterprises in the Era of the Fourth Industrial Revolution: Focusing on the Case ofKorea Water Resources Corporation(K-water)," Korea Business Review, vol. 24. pp. 7-35, 2020.   DOI
2 S. J. Park, J. H. Han, and Y. S. Moon, "Efficient Deep Neural Network Architecture based on Semantic Segmentation for Paved Road Detection," Journal of the Korea Institute of Information and Communication Engineering, vol. 24, no. 11, pp. 1437-1444, 2020.   DOI
3 N, Darapaneni, A. Jagannathan, V. Natarajan, G. V. Swaminathan, S. Subramanian, and A. R. aduri, "Semantic Segmentation of Solar PV Panels and Wind Turbines in Satellite Images Using U-Net," IEEE 15th International Conference on Industrial and Information Systems (ICIIS), pp. 7-12, Nov. 2020.
4 R. Manish, C. Michael, A. Armani, B. Dmitrii, L Alena, and B. Christian, "A comparative analysis of electricity generation costs from renewable, fossil fuel and nuclear sources in G20 countries for the period 2015-2030," Journal of cleaner production, vol. 199, pp. 687-704. 2018.   DOI
5 J. H. Ha, E. Y. Hwangbo, and J. Y. Ahn, "Understanding and Activating the Role of Market Actors in the Process of Mini-PV Installation in Seoul: Based on Practice Theory," New & Renewable Energy, vol. 17, no. 1, pp. 7-18, 2021.   DOI
6 S. J. Jang and J. W. Jang, "Deep Learning Image Processing Technology for Vehicle Occupancy Detection," The Korea Institute of Information and Communication EngineeringJournal of the Korea Institute of Information and Communication Engineering, vol. 25, no. 8, pp. 1026-1031, Aug. 2021.
7 H. Y. Lim, Y. R. Lee, M. K. Jee, M. H. Go, H. D. Kim, and W. I. Kim, "Efficient inference of image objects using semantic segmentation," Journal of Broadcast Engineering, vol. 24, no. 1, pp. 67-76, 2019.   DOI
8 S. K. Choi, S. K. Lee, Y. B. Kang, S. K. Seong, D. Y. Choi, and G. H. Kim, "Applicability of Image Classification Using Deep Learning in Small Area: Case of Agricultural Lands Using UAV Image," Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, vol. 38, no. 1, pp. 23-33, 2020.   DOI
9 J. Nie, T. Luo, and H. Li, "Automatic hotspots detection based on UAV infrared images for large-scale PV plant," Electronics Letters, vol. 56, no. 19, pp. 993-995, 2020.   DOI
10 S. H. Lee and J. S. Kim, "Land cover classification using sematic image segmentation with deep learning," Korean Journal of Remote Sensing, vol. 35, no. 2, pp. 279-288, 2019.   DOI