Browse > Article
http://dx.doi.org/10.3744/SNAK.2022.59.6.393

Resistance Performance Simulation of Simple Ship Hull Using Graph Neural Network  

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)
Publication Information
Journal of the Society of Naval Architects of Korea / v.59, no.6, 2022 , pp. 393-399 More about this Journal
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
Mesh based simulation; Graph neural network; Resistance performance; Computational fluid dynamics;
Citations & Related Records
연도 인용수 순위
  • Reference
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.   DOI
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.