항공우주시스템공학회지 (Journal of Aerospace System Engineering)

  • 제16권4호
  • /
  • Pages.45-52
  • /
  • 2022
  • /
  • 1976-6300(pISSN)
  • /
  • 2508-7150(eISSN)
항공우주시스템공학회 (The Society for Aerospace System Engineering)
권호 표지
DOI QR코드

DOI QR Code

CNN-LSTM 혼합모델을 이용한 비행상태 예측 기법

Flight State Prediction Techniques Using a Hybrid CNN-LSTM Model

  • 박진상 (경상국립대학교 일반대학원 기계항공공학부) ;
  • 송민재 (경상국립대학교 일반대학원 기계항공공학부) ;
  • 최은주 (한국항공우주연구원 항공연구소) ;
  • 김병수 (경상국립대학교 일반대학원 기계항공공학부) ;
  • 문용호 (경상국립대학교 일반대학원 기계항공공학부)
  • Park, Jinsang (School of Mechanical and Aerospace Engineering, Gyeongsang National University) ;
  • Song, Min jae (School of Mechanical and Aerospace Engineering, Gyeongsang National University) ;
  • Choi, Eun ju (Korea Aerospace Research Institute) ;
  • Kim, Byoung soo (School of Mechanical and Aerospace Engineering, Gyeongsang National University) ;
  • Moon, Young ho (School of Mechanical and Aerospace Engineering, Gyeongsang National University)
  • 투고 : 2022.04.20
  • 심사 : 2022.07.19
  • 발행 : 2022.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 차세대 운송시스템으로 주목받고 있는 UAM 분야에서 무인항공기 활용을 위한 기술 개발이 활발히 진행되고 있다. 이러한 기술이 적용된 무인항공기는 주로 도심에서 운용되기 때문에 추락사고를 예방하는 것이 중요하다. 그러나 충돌이 발생되는 무인항공기는 비선형성이 강하기 때문에 비정상 비행상태를 예측하는 것은 쉽지 않은 일이다. 본 논문에서는 CNN-LSTM 혼합모델을 이용하여 무인항공기의 비행상태를 예측하는 방법을 제안한다. 제안 모델은 비행 데이터간의 시간적, 공간적 특징을 추출하는 CNN 모델과 추출된 특징의 장단기 시간 의존성을 추출하는 LSTM 모델을 결합하여 미래의 특정 시점에서 비행 상태변수를 예측한다. 모의 실험은 제안하는 방법이 기존 인공신경망 모델에 기반한 예측 방법보다 우수한 성능을 보인다.

In the field of UAM, which is attracting attention as a next-generation transportation system, technology developments for using UAVs have been actively conducted in recent years. Since UAVs adopted with these technologies are mainly operated in urban areas, it is imperative that accidents are prevented. However, it is not easy to predict the abnormal flight state of an UAV causing a crash, because of its strong non-linearity. In this paper, we propose a method for predicting a flight state of an UAV, based on a CNN-LSTM hybrid model. To predict flight state variables at a specific point in the future, the proposed model combines the CNN model extracting temporal and spatial features between flight data, with the LSTM model extracting a short and long-term temporal dependence of the extracted features. Simulation results show that the proposed method has better performance than the prediction methods, which are based on the existing artificial neural network model.

키워드

과제정보

본 연구는 국토교통부 연구개발사업의 연구비 지원(22ACTO-B151661-04)에 의해 수행되었습니다.

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. Choong Hyun Choi, "[KISTEP Technology trend brief] Personal Air Vehicle(PAV)," Korea Institute of Science & Technology Evaluation and Planning, no. 5, Apr 2015.
  3. Jeong-ho Yang, "Personal Aircraft (PAV) Technology Market Trends and Industrial Environment Analysis Report," Korea Aerospace Research Institute, May 2019.
  4. On Park, "Aircraft Upset Detection Algorithm using Neural Networks," Master's thesis. Chungnam National University. Chungnam. Korea, 2016.
  5. Junjie He, Junliang Wang, Lu Dai, Jie Zhang, Jingsong Bao, "An Adaptive Interval Forecast CNN Model for Fault Detection Method," 2019 IEEE 15th Internation Conference on Automation Science and Enginnering (CASE), Sep. 2019.
  6. Yunfei Ma, Xisheng Jia, Huajun Bai, Guozeng Liu, Guanglong Wang, Chiming Guo, Shuangchuan Wang, "A new fault diagnosis method based on convolutional neural network and compressive sensing," Journal of Mechanical Science and Technology, vol. 33, no. 11, pp. 5177-5188, Nov 2019. https://doi.org/10.1007/s12206-019-1007-5
  7. Kang Wang, Kenli Li, Liqian Zhou, Yikun Hu, Zhongyao Cheng, Jing Liu, Cen Chen, "Multiple convolutional neural networks for multivariate time series prediction," Neurocomputing, vol. 360, no. 30, pp. 107-119, Sep. 2019. https://doi.org/10.1016/j.neucom.2019.05.023
  8. Aslam Muhammad, Jae Myoung Lee, Sug Won Hong, Seung Jae Lee, Eui Hyang Lee, "Deep Learning Application in Power System with a Case Study on Solar Irradiation Forecasting," 2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pp. 275-279, 2019.
  9. Benjamin Lindemann, Benjamin Maschler, Nada Sahlab, Michael Weyrich, "A survey on anomaly detection for technical systems using LSTM networks," Computers in Industry, vol. 131, 2021.
  10. Jun Yang, Jingbin Qu, Qiang Mi, Qing Li, "A CNN-LSTM Model for Tailings Dam Risk Prediction," IEEE Access, vol. 8, pp. 206491-206502, Nov. 2020. https://doi.org/10.1109/ACCESS.2020.3037935
  11. Musaed Alhussein, Khursheed Aurangzeb, Syed Irtaza Haider, "Hybrid CNN-LSTM Model for Short-Term Individual Household Load Forecasting". IEEE Access, vol. 8, pp. 2169-3536, Oct. 2020.
  12. Haifeng Zheng, Feng Lin, Xinxin Feng, YouJia Chen, "A Hybrid Deep Learning Model With Attention-Based Conv-LSTM Networks for Short-Term Traffic Flow Prediction", IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 11, pp. 6910-6920, Nov. 2021. https://doi.org/10.1109/TITS.2020.2997352