DOI QR코드

DOI QR Code

Design of a deep learning model to determine fire occurrence in distribution switchboard using thermal imaging data

열화상 영상 데이터 기반 배전반 화재 발생 판별을 위한 딥러닝 모델 설계

  • 박동준 (동의대학교 ICT융복합연구소) ;
  • 김민영 (동의대학교 ICT융복합연구소)
  • Received : 2023.08.22
  • Accepted : 2023.09.05
  • Published : 2023.09.30

Abstract

This paper discusses a study on developing an artificial intelligence model to detect incidents of fires in distribution switchboard using thermal images. The objective of the research is to preprocess collected thermal images into suitable data for object detection models and design a model capable of determining the occurrence of fires within distribution panels. The study utilizes thermal image data from AI-HUB's industrial complex for training. Two CNN-based deep learning object detection algorithms, namely Faster R-CNN and RetinaNet, are employed to construct models. The paper compares and analyzes these two models, ultimately proposing the optimal model for the task.

본 논문은 열화상 이미지를 활용하여 배전반 화재 발생을 감지하기 위한 인공지능 모델을 개발하는 연구에 대해 다룬다. 연구의 목표는 수집한 열화상 이미지를 전처리하여 객체 탐지 모델에 적합한 데이터로 가공하고, 이를 이용하여 배전반 내 화재 발생 여부를 판단하는 모델을 설계하는 것이다. 연구에서는 AI-HUB의 산업단지 내 학습용 열화상 이미지 데이터를 활용하였으며, CNN 기반 딥러닝 객체 검출 알고리즘 중 대표적인 모델인 Faster R-CNN과 RetinaNet을 사용하여 모델을 구축하고 두 개의 모델을 비교 분석하여 최적의 모델을 제안하고 있다.

Keywords

References

  1. National Fire Data System, fire statistics [Internet] , Available : https://nfds.go.kr/stat/general.do
  2. Deepak Kumar and M.A.Ansari, "Condition monitoring of eletrical assets using digital IRT and AI technique," Journal of Electrical Systems and information Technology, Vol. 5, No.3, pp. 623-634, Dec. 2018. (DOI: https://doi.org/10.1016/j.jesit.2017.10.001)
  3. Joo-Sik Kim, Kyu-Nam Choi, Hyung-Geun Lee and Sung-Woo Kang, "Detection and Diagnosis of Power Distribution Supply Facilities Using Thermal Images," Journal of the Korea Safety Management & Science, Vol. 22, No.1, pp. 1-8, March 2020. (DOI : http://dx.doi.org/10.12812/ksms.2020.22.1.001)
  4. Hyung-Geun Lee, Yong-Min Hong, Sung-Woo Kang, "Identifying Process Capability Index for Electricity Distribution System through Thermal Image Analysis," J Korean Soc Qual Manag Vol. 49, No.3, pp. 327-340, Sep. 2021. (DOI : https://doi.org/10.7469/JKSQM.2021.49.3.327)
  5. Tistory, Grinding Object Detection 4. Faster R-CNN [Internet] , Available : https://yeomko.tistory.com/17
  6. Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," Advances in Neural Information Processing Systems 28 (NIPS 2015), Jan. 2016.
  7. Tsung-Yi Lin, PriyaGoayl, Ross Girchick, Kaiming He and Piotr Dollar, "Focal Loss for Dense Object Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 42, Issue 10, pp.318-327, Feb. 2020. (DOI : 10.1109/TPAMI.2018.2858826)
  8. Yong-Hwan Lee and Young-Seop Kim, "Comparison of CNN and YOLO for Object Detection," Journal of the Semiconductor & Display Technology, Vol. 19, No.1, pp. 85-92, March 2020.
  9. AI Hub, Disaster Safety Environment, Thermal mager image [Internet] , Available : https://aihub.or.kr