DOI QR코드

DOI QR Code

심층신경망을 이용한 어선의 운동응답 추정

Motion Response Estimation of Fishing Boats Using Deep Neural Networks

  • 박태원 (동명대학교 조선해양시뮬레이션센터) ;
  • 박동우 (동명대학교 해양모빌리티학과) ;
  • 서장훈 (동명대학교 조선해양시뮬레이션센터)
  • TaeWon Park (Shipbuilding & Marine Simulation Center, Tongmyong University) ;
  • Dong-Woo Park (Department of Marine Mobility, Tongmyong University) ;
  • JangHoon Seo (Shipbuilding & Marine Simulation Center, Tongmyong University)
  • 투고 : 2023.10.16
  • 심사 : 2023.12.29
  • 발행 : 2023.12.31

초록

최근에 선박을 안전하게 설계 및 운항하기 위해 인공지능으로 운동성능을 예측하는 연구가 늘고 있다. 하지만 일반적인 선박에 비해 소형 어선에 대한 연구는 부족한 실정이다. 본 논문에서는 소형 어선의 운동성능 계산에 필수적인 운동응답을 심층신경망으로 추정하는 모델을 제안한다. 15척의 소형 어선에 대하여 유체동역학 해석을 수행하였으며 이를 통해 데이터베이스를 구축하였다. 환경 조건과 주요 제원을 입력 데이터로, 단위 파고에 대한 운동응답(Response Amplitude Operator)을 출력 데이터로 설정하였다. 훈련된 심층신경망 모델을 통해 예측된 운동응답은 유체동역학 해석 결과와 유사한 경향을 보이며 고주파 성분을 가진 운동응답 함수를 낮은 오차로 근사하는 결과를 보여준다. 본 연구의 결과를 바탕으로 어선의 선형 특성 고려한 심층신경망 모델로 확장하여 연구 결과의 활용도를 넓히고자 한다.

Lately, there has been increasing research on the prediction of motion performance using artificial intelligence for the safe design and operation of ships. However, compared to conventional ships, research on small fishing boats is insufficient. In this paper, we propose a model that estimates the motion response essential for calculating the motion performance of small fishing boats using a deep neural network. Hydrodynamic analysis was conducted on 15 small fishing boats, and a database was established. Environmental conditions and main particulars were applied as input data, and the response amplitude operators were utilized as the output data. The motion response predicted by the trained deep neural network model showed similar trends to the hydrodynamic analysis results. The results showed that the high-frequency motion responses were predicted well with a low error. Based on this study, we plan to extend existing research by incorporating the hull shape characteristics of fishing boats into a deep neural network model.

키워드

과제정보

본 연구는 한국해양교통안전공단의 자체연구개발과제인 "D.N.A. 기반 어선의 횡동요 및 안정성능 예측 프로그램 개발" 과제의 지원을 받아 수행되었습니다.

참고문헌

  1. Girshick, R.(2015), Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1440-1448
  2. Hwang, J. H. and K. P. Rhee(1980), On a Computer Program to Calculate the Responses of a Ship in Lateral Regular Waves, Journal of the Society of Naval Architects of Korea, 17.4, pp. 39-45.
  3. Im, N. K. and S. M. Lee(2021), A Study on Motion Response of Small Fishing Vessels According to Various Tonnage in Regular Waves, Journal of the Korean Society of Marine Environment & Safety, 27(6), pp. 832-838. https://doi.org/10.7837/kosomes.2021.27.6.832
  4. Kang, I. K., H. S. Kim, M. S. Kim, Y. W. Lee, J. C. Kim, H. J. Jo, and C. K. Lee(2007), Characterstics on the rolling response of a small fishing boat according to the waves and the ship's speed, J. Kor. Soc. Fish. Tech, 43(1), pp. 62-70. https://doi.org/10.3796/KSFT.2007.43.1.062
  5. Kim, Y. R., J. B. Park, and S. B. Moon(2018), Prediction of Ship Roll Motion using Machine Learning-based Surrogate Model. J. Navig. Port Res, 42(6), pp. 395-405.
  6. Kingma, D. P. and J. Ba(2015), Adam: A Method for Stochastic Optimization. In Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA, pp. 24-28.
  7. Korea Maritime Safety Tribunal(2021), Maritime accidents statistical yearbook.
  8. Park, R. S., S. G. Kim, and J. B. Lee(2011), Study on Motion Response Characteristics for Large Inclined State of Small Fishing Vessel in Beam Sea Condition, Journal of Ocean Engineering and Technology, 25(6), pp. 17-22. https://doi.org/10.5574/KSOE.2011.25.6.017
  9. Xu, W., K. J. Maki, and K. M. Silva(2021), A data-driven model for nonlinear marine dynamics. Ocean Engineering, 236, 109469.
  10. Zhang, D., X. Zhou, Z. H. Wang, Y. Peng, and S. R. Xie (2023), A data driven method for multi-step prediction of ship roll motion in high sea states. Ocean Engineering, 276, 114230.