Journal of the Society of Naval Architects of Korea (대한조선학회논문집)

The Society of Naval Architects of Korea (대한조선학회)
권호 표지
DOI QR코드

DOI QR Code

Resistance Performance Simulation of Simple Ship Hull Using Graph Neural Network

그래프 신경망을 이용한 단순 선박 선형의 저항성능 시뮬레이션

  • TaeWon, Park (Shipbuilding & Marine Simulation Center, Tongmyong University) ;
  • Inseob, Kim (Smart Safety Research Department, Korea Maritime Transportation Safety Authority) ;
  • Hoon, Lee (Logistics System Institute, Total Soft Bank, Ltd.) ;
  • Dong-Woo, Park (School of Naval Architecture & Ocean Engineering, Tongmyong University)
  • 박태원 (동명대학교 조선해양시뮬레이션센터) ;
  • 김인섭 (한국해양교통안전공단 스마트안전연구실) ;
  • 이훈 ((주)토탈소프트뱅크 물류시스템연구소) ;
  • 박동우 (동명대학교 조선해양공학과)
  • Received : 2022.09.27
  • Accepted : 2022.11.01
  • Published : 2022.12.20
Download PDF
⟨ Previous Next ⟩

Abstract

During the ship hull design process, resistance performance estimation is generally calculated by simulation using computational fluid dynamics. Since such hull resistance performance simulation requires a lot of time and computation resources, the time taken for simulation is reduced by CPU clusters having more than tens of cores in order to complete the hull design within the required deadline of the ship owner. In this paper, we propose a method for estimating resistance performance of ship hull by simulation using a graph neural network. This method converts the 3D geometric information of the hull mesh and the physical quantity of the surface into a mathematical graph, and is implemented as a deep learning model that predicts the future simulation state from the input state. The method proposed in the resistance performance experiment of simple hull showed an average error of about 3.5 % throughout the simulation.

Keywords

Acknowledgement

이 연구는 산업통상자원부의 스마트특성화 기반구축사업 중 실물-가상연계 조선해양 기본설계 기술지원 사업 (P0021213) 과제 및 산업통상자원부와 한국산업기술진흥원의 지역혁신클러스터R&D 사업 (P0015330)의 지원을 받아 수행되었습니다.

References

  1. Ba, J.L., Kiros, J.R. and Hinton, G.E., 2016. Layer Normalization. arXiv preprint arXiv:1607.06450.
  2. He, K., Zhang, X., Ren, S. and Sun, Ji., 2016. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp.770-778.
  3. Hendrycks, D. and Gimpel, K., 2016. Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415.
  4. Kim, B., Azevedo, V.C., Thuerey, N., Kim, T, Gross, M. and Solenthaler, B., 2019. Deep fluids: A generative network for parameterized fluid simulations. Computer Graphics Forum, 38(2), pp.59-70. https://doi.org/10.1111/cgf.13619
  5. Kingma, D.P. and Ba, J., 2015. Adam: A method for stochastic optimization. 3rd International Conference for Learning Representations, San Diego, May 7-9.
  6. Pfaff, T., Fortunato, M., Sanchez-Gonzalez, A. and Battaglia, P.W., 2021. Learning mesh-based simulation with graph networks. 9th International Conference on Learning Representations, Austria, May 3-7.
  7. Thuerey, N., Weissenow, K., Prantl, L. and Hu, X., 2019. Deep learning methods for Reynolds-averaged navier-stokes simulations of airfoil flows. American Institute of Aeronautics and Astronautics Journal, 58(1), pp.25-36.