Journal of Information Processing Systems

  • 제19권6호
  • /
  • Pages.791-802
  • /
  • 2023
  • /
  • 1976-913X(pISSN)
  • /
  • 2092-805X(eISSN)
한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

Hot Spot Detection of Thermal Infrared Image of Photovoltaic Power Station Based on Multi-Task Fusion

  • Xu Han (School of Automation, Chongqing University of Posts and Telecommunications) ;
  • Xianhao Wang (School of Automation, Chongqing University of Posts and Telecommunications) ;
  • Chong Chen (Chongqing SPIC ZINENG Science & Technology Co. Ltd.) ;
  • Gong Li (School of Automation, Chongqing University of Posts and Telecommunications) ;
  • Changhao Piao (School of Automation, Chongqing University of Posts and Telecommunications)
  • 투고 : 2021.02.01
  • 심사 : 2022.04.06
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

The manual inspection of photovoltaic (PV) panels to meet the requirements of inspection work for large-scale PV power plants is challenging. We present a hot spot detection and positioning method to detect hot spots in batches and locate their latitudes and longitudes. First, a network based on the YOLOv3 architecture was utilized to identify hot spots. The innovation is to modify the RU_1 unit in the YOLOv3 model for hot spot detection in the far field of view and add a neural network residual unit for fusion. In addition, because of the misidentification problem in the infrared images of the solar PV panels, the DeepLab v3+ model was adopted to segment the PV panels to filter out the misidentification caused by bright spots on the ground. Finally, the latitude and longitude of the hot spot are calculated according to the geometric positioning method utilizing known information such as the drone's yaw angle, shooting height, and lens field-of-view. The experimental results indicate that the hot spot recognition rate accuracy is above 98%. When keeping the drone 25 m off the ground, the hot spot positioning error is at the decimeter level.

키워드

과제정보

We thank Chongqing University of Posts and Telecommunications, Chongqing Zhongdian Energy Technology Co. Ltd., State Power Investment Group Information Technology Co. Ltd., and Guizhou Xiaoguanshan Solar Photovoltaic Power Station for providing the experimental data.

참고문헌

  1. W. Liu, L. Zhao, Y. Zhou, S. Zong, and Y. Luo, "Deep learning based unmanned aerial vehicle landcoverimage segmentation method," Transactions of the Chinese Society of Agricultural Machinery, vol. 51, no. 2, pp. 221-229, 2020.
  2. M. W. Y. Tu, C. Li, H. Yu, and H. Yao, "Non-adiabatic Hall effect at Berry curvature hot spot," 2D Materials, vol. 7, no. 4, article no. 045004, 2020. https://doi.org/10.1088/2053-1583/ab89e8
  3. D. Li "Research on intelligent patrol inspection technology of photovoltaic power plant based on augmented reality," Automation Application, vol. 2019, no. 6, pp. 120-121+124, 2019. https://doi.org/10.19769/j.zdhy.2019.06.048
  4. R. S. Eckard, B. A. Bergamaschi, B. A. Pellerin, T. Kraus, and P. J. Hernes, "Trihalomethane precursors: land use hot spots, persistence during transport, and management options," Science of The Total Environment, vol. 742, article no. 140571, 2020. https://doi.org/10.1016/j.scitotenv.2020.140571
  5. J. Wen, K. Guo, H. Wang, D. Yuan, and M. Mao, "Research on the online detection method of photovoltaic array hot spot fault," Electronic Products, vol. 2019, no. 15, pp. 55-58+76, 2019.
  6. M. H. Guo and H. W. Xu, "Research on hot spot defect detection of infrared thermal image based on Faster RCNN," Computer Systems & Applications, vol. 28, no. 11, pp. 265-270, 2019.
  7. J. Redmon and A. Farhadi, "YOLOv3: an incremental improvement," 2018 [Online]. Available:https://arxiv.org/abs/1804.02767.
  8. M. Liu, X. Wang, A. Zhou, X. Fu, Y. Ma, and C. Piao, "UAV-YOLO: small object detection on unmanned aerial vehicle perspective," Sensors, vol. 20, no. 8, article no. 2238, 2020. https://doi.org/10.3390/s20082238
  9. L. C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, "Encoder-decoder with Atrous separable convolution for semantic image segmentation," 2018 [Online]. Available: https://arxiv.org/abs/1802.02611.
  10. D. Wu, X. Yin, B. Jiang, M. Jiang, Z. Li, and H. Song, "Detection of the respiratory rate of standing cows by combining the Deeplab V3+ semantic segmentation model with the phase-based video magnification algorithm," Biosystems Engineering, vol. 192, pp. 72-89, 2020. https://doi.org/10.1016/j.biosystemseng.2020.01.012
  11. M. T. N. Truong and S. Kim, "A study on visual saliency detection in infrared images using Boolean map approach," Journal of Information Processing Systems, vol. 16, no. 5, pp. 1183-1195, 2020. https://doi.org/10.3745/JIPS.02.0145
  12. X. Feng and K. Hu, "Perceptual fusion of infrared and visible image through variational multiscale with guide filtering," Journal of Information Processing Systems, vol. 15, no. 6, pp. 1296-1305, 2019. https://doi.org/10.3745/JIPS.04.0144
  13. D. Cao, Z. Chen, and L. Gao, "An improved object detection algorithm based on multi-scaled and deformable convolutional neural networks," Human-centric Computing and Information Sciences, vol. 10, article no. 14, 2020. https://doi.org/10.1186/s13673-020-00219-9