DOI QR코드

DOI QR Code

순환 신경망 모델을 이용한 소형어선의 운동응답 예측 연구

Study on the Prediction of Motion Response of Fishing Vessels using Recurrent Neural Networks

  • 서장훈 (동명대학교 조선해양시뮬레이션센터) ;
  • 박동우 (동명대학교 해양모빌리티학과 ) ;
  • 남동 (한국해양교통안전공단 )
  • Janghoon Seo (Shipbuilding & Marine Simulation Center, Tongmyong University) ;
  • Dong-Woo Park (Department of Marine Mobility, Tongmyong University) ;
  • Dong Nam (Department of Marine Mobility, Korea Maritime Transportation Safety Authority)
  • 투고 : 2023.07.20
  • 심사 : 2023.08.29
  • 발행 : 2023.08.31

초록

본 논문에서는 소형어선의 운동 응답을 예측하기 위해 딥러닝 모델을 구축하였다. 크기가 다른 두 소형어선을 대상으로 유체동역학 성능을 평가하여 데이터세트를 확보하였다. 딥러닝 모델은 순환 신경망 기법의 하나인 장단기 메모리 기법(LSTM, Long Short-Term Memory)을 사용하였다. 딥러닝 모델의 입력 데이터는 6 자유도 운동 및 파고의 시계열 데이터를 사용하였으며, 출력 라벨로는 6 자유도 운동의 시계열 데이터로 선정하였다. 최적 LSTM 모델 구축을 위해 hyperparameter 및 입력창 길이의 영향을 평가하였다. 구축된 LSTM 모델을 통해 입사파 방향에 따른 시계열 운동 응답을 예측하였다. 예측된 시계열 운동 응답은 해석 결과와 전반적으로 잘 일치함을 확인할 수 있었다. 시계열의 길이가 길어짐에 따라서 예측값과 해석 결과의 차이가 발생하는데, 이는 장기 데이터에 따른 훈련 영향도가 감소 됨에 따라 나타난 것으로 확인할 수 있다. 전체 예측 데이터의 오차는 약 85% 이상의 데이터가 10% 이내의 오차를 보였으며, 소형어선의 시계열 운동 응답을 잘 예측함을 확인하였다. 구축된 LSTM 모델은 소형어선의 모니터링 및 경보 시스템에 활용될 수 있을 것으로 기대한다.

In the present study, a deep learning model was established to predict the motion response of small fishing vessels. Hydrodynamic performances were evaluated for two small fishing vessels for the dataset of deep learning model. The deep learning model of the Long Short-Term Memory (LSTM) which is one of the recurrent neural network was utilized. The input data of LSTM model consisted of time series of six(6) degrees of freedom motions and wave height and the output label was selected as the time series data of six(6) degrees of freedom motions. The hyperparameter and input window length studies were performed to optimize LSTM model. The time series motion response according to different wave direction was predicted by establised LSTM. The predicted time series motion response showed good overall agreement with the analysis results. As the length of the time series increased, differences between the predicted values and analysis results were increased, which is due to the reduced influence of long-term data in the training process. The overall error of the predicted data indicated that more than 85% of the data showed an error within 10%. The established LSTM model is expected to be utilized in monitoring and alarm systems for small fishing vessels.

키워드

과제정보

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

참고문헌

  1. Abankwa, N. O., S. J. Johnston, M. Scott, and S. J. Cox (2015), Ship motion measurement using an inertial measurement unit. In 2015 IEEE 2nd World Forum on Internet of Things (WF-IoT), pp. 375-380. 
  2. Choi, C. W., Y. Noh, D. S. Shin, H. M. Kim, and H. C. Park(2021), Identifying Risk Factors of Marine Accidents in Coastal Area by Marine Accident Types, Korean Society of Transportation, 39(4), pp. 540-554.  https://doi.org/10.7470/jkst.2021.39.4.540
  3. del Aguila Ferrandis, J., M. S. Triantafyllou, C. Chryssostomidis, and G. E. Karniadakis(2021), Learning functionals via LSTM neural networks for predicting vessel dynamics in extreme sea states. Proceedings of the Royal Society A, 477(2245), 20190897. 
  4. Guo, X., X. Zhang, X. Tian, X. Li, and W. Lu(2021), Predicting heave and surge motions of a semi-submersible with neural networks. Applied Ocean Research, 112, 102708. 
  5. 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. 
  6. 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
  7. Korea Maritime Safety Tribunal(2021), Maritime accidents statistical yearbook. 
  8. Kang, I. K., H. S. Kim, M. S. Kim, Y. W. Lee, J. C. Kim, H. J. Jo, and C. K. Lee(2007), Characteristics 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
  9. 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. 
  10. 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
  11. Son, G. B., H. J. Choi, J. H. Lee, Y. B. Ro, and P. S. Kang (2020), Significant Wave Height Regression from a Raw Ocean Image with Convolutional LSTM and 3D Convolutional Networks. Journal of The Korean Operations Research and Management Science Society, 45(1), 11-24.  https://doi.org/10.7737/JKORMS.2020.45.1.011
  12. Xu, W., K. J. Maki, and K. M. Silva(2021), A data-driven model for nonlinear marine dynamics. Ocean Engineering, 236, 109469. 
  13. Yang, Y. J. and S. Y. Kwon(2017), Rolling Motion Simulation in the Time Domain and Ship Motion Experiment for Algorithm Verification for Fishing Vessel Capsizing Alarm Systems. Journal of the Korean Society of Marine Environment & Safety, 23(7), pp. 956-964.  https://doi.org/10.7837/kosomes.2017.23.7.956
  14. 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.