항공우주시스템공학회지 (Journal of Aerospace System Engineering)

  • 제18권3호
  • /
  • Pages.41-47
  • /
  • 2024
  • /
  • 1976-6300(pISSN)
  • /
  • 2508-7150(eISSN)
항공우주시스템공학회 (The Society for Aerospace System Engineering)
권호 표지
DOI QR코드

DOI QR Code

U-Net을 이용한 무인항공기 비정상 비행 탐지 기법 연구

Abnormal Flight Detection Technique of UAV based on U-Net

  • 송명재 (경상국립대학교 일반대학원 기계항공우주공학부) ;
  • 최은주 (한국항공우주연구원 항공연구소) ;
  • 김병수 (경상국립대학교 일반대학원 기계항공우주공학부) ;
  • 문용호 (경상국립대학교 일반대학원 기계항공우주공학부)
  • Myeong Jae Song (School of Mechanical and Aerospace Engineering, Gyeongsang National University) ;
  • Eun Ju Choi (Korea Aerospace Research Institute) ;
  • Byoung Soo Kim (School of Mechanical and Aerospace Engineering, Gyeongsang National University) ;
  • Yong Ho Moon (School of Mechanical and Aerospace Engineering, Gyeongsang National University)
  • 투고 : 2024.03.02
  • 심사 : 2024.04.22
  • 발행 : 2024.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근에 무인항공기의 실용화 및 사업화가 추진됨에 따라 무인항공기의 안전성 확보에 관한 관심이 증가하고 있다. 무인항공기의 사고는 재산 및 인명 피해를 발생시키기 때문에 사고를 예방할 수 있는 기술의 개발은 중요하다. 이러한 이유로 AutoEncoder 모델을 이용한 비정상 비행 상태 탐지 기법이 개발되었다. 그러나 기존 탐지 기법은 성능과 실시간 처리 측면에서 한계를 지닌다. 본 논문에서는 U-Net 기반 비정상 비행 탐지 기법을 제안한다. 제안하는 기법에서는 U-Net 모델에서 얻어지는 재구성 오차에 대한 마할라노비스 거리 증가량에 기반하여 비정상 비행이 탐지된다. 모의실험을 통해 제안 탐지 기법이 기존 탐지 기법에 비해 탐지 성능이 우수하며 온보드 환경에서 실시간으로 구동될 수 있음을 알 수 있다.

Recently, as the practical application and commercialization of unmanned aerial vehicles (UAVs) is pursued, interest in ensuring the safety of the UAV is increasing. Because UAV accidents can result in property damage and loss of life, it is important to develop technology to prevent accidents. For this reason, a technique to detect the abnormal flight state of UAVs has been developed based on the AutoEncoder model. However, the existing detection technique is limited in terms of performance and real-time processing. In this paper, we propose a U-Net based abnormal flight detection technique. In the proposed technique, abnormal flight is detected based on the increasing rate of Mahalanobis distance for the reconstruction error obtained from the U-Net model. Through simulation experiments, it can be shown that the proposed detection technique has superior detection performance compared to the existing detection technique, and can operate in real-time in an on-board environment.

키워드

과제정보

본 논문은 항공우주연구원의 국토교통부 연구개발사업의 연구비 지원(21ACTO-B151664-03)에 의해 수행되었음.

참고문헌

  1. SeungJong Song and Byung-ok Gil, "A Study on the History and Strategic Implications of Military Drones Development," Institute for Military History(MND), No. 97, pp. 263-308, Dec. 2015. 
  2. Junhyeong Sim, Euicheon Hwang, Changgeun Son, Yeonseung Ryu, "Anti-Drone Countermeasures According to Drone Accident Cases and Technology Trend," Journal of the Korea Academia-Industrial cooperation Society, Vol. 24, No. 2, pp. 651-659, Feb. 2023 
  3. Areum Hong, Anseon Park, Minseon Kim, "Policy and Industry Trends in Urban Air Mobility," National Strategic Technology Policy and Industry Trends in the Era of Technological Hegemony Competition, Vol. 38, No. 4, pp. 36-46, Aug. 2023. 
  4. Lishuai Li, Maxime Gariel, R. John Hansman, Rafael Palacios, "Anomaly detection in onboarded-recorded flight data using cluster analysis," IEEE/AIAA 30th Digital Avionics Systems Conference, Dec. 2011 
  5. Murtaja Salah, Tareef Kamil Mustafa, "Anomaly Detection in Flight Data Using the Naive Bayes Classifier," 7th International Conference on Contemporary Information Technology and Mathematics (ICCITM), Jan. 2022 
  6. Nosam Park, "Research Trends on Deep Learning for Anomaly Detection of Aviation Safety." Electronics and Telecommunications Trends, Vol. 36, No. 5, pp. 82-91, Oct. 2021 
  7. Zhiqiang Que, Yanyang Liu, Ce Guo, Xinyu Niu, Yongxin Zhu, Wayne Luk, "Real-Time Anomaly Detection for Flight Testing Using AutoEncoder and LST M," 2019 International Conference on Field-Programmable Technology (ICFPT), Feb. 2020 
  8. Qihan Sun, Ruipeng Ji, "Flight anomaly detection model based on QAR data autoencoder and DBscan algorithm," IEEE 3rd International Conference on Civil Aviation Safety and Information Technology (ICCASIT), Dec. 2021 
  9. Qixin Wang, Kun Qin, Binbin Lu, "Flight Anomaly Detection Based on Deep Hybrid Model" IEEE 2nd International Conference on Civil Aviation Safety and Information Technology (ICCASIT), Mar. 2021 
  10. MinJae Song, EunJu Choi, YongHo Moon, ByoungSoo Kim, "A Study on the Domain Knowledge-Based Data Normalization Method in the Utilization of AI Model for the Detection of Abnormal Flight of Small UAVs," Journal of the Korean Society for Aeronautical and Space Sciences, Vol. 52, No. 1, pp. 57-64, Jan. 2024 
  11. Olaf Ronneberger, Philipp Fischer, Thomas Brox, "UNet: Convolutional Networks for Biomedical Image Segmentation," Computer Vision and Pattern Recognition, May 2015