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

  • 제60권2호
  • /
  • Pages.110-119
  • /
  • 2023
  • /
  • 1225-1143(pISSN)
  • /
  • 2287-7355(eISSN)
대한조선학회 (The Society of Naval Architects of Korea)
권호 표지
DOI QR코드

DOI QR Code

합성곱 신경망과 복셀화를 활용한 선박 저항 성능 예측

Prediction of Ship Resistance Performance Based on the Convolutional Neural Network With Voxelization

  • 박종서 (한국해양대학교 조선해양시스템공학부) ;
  • 최민주 (한국해양대학교 조선해양시스템공학부) ;
  • 송지수 (한국해양대학교 조선해양시스템공학부)
  • Jongseo Park (Department of Naval Architecture and Ocean Systems Engineering, Korea Maritime and Ocean University) ;
  • Minjoo Choi (Department of Naval Architecture and Ocean Systems Engineering, Korea Maritime and Ocean University) ;
  • Gisu Song (Department of Naval Architecture and Ocean Systems Engineering, Korea Maritime and Ocean University)
  • 투고 : 2022.12.21
  • 심사 : 2023.03.15
  • 발행 : 2023.04.20
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

The prediction of ship resistance performance is typically obtained by Computational Fluid Dynamics (CFD) simulations or model tests in towing tank. However, these methods are both costly and time-consuming, so hull-form designers use statistical methods for a quick feed-back during the early design stage. It is well known that results from statistical methods are often less accurate compared to those from CFD simulations or model tests. To overcome this problem, this study suggests a new approach using a Convolution Neural Network (CNN) with voxelized hull-form data. By converting the original Computer Aided Design (CAD) data into three dimensional voxels, the CNN is able to abstract the hull-form data, focusing only on important features. For the verification, suggested method in this study was compared to a parametric method that uses hull parameters such as length overall and block coefficient as inputs. The results showed that the use of voxelized data significantly improves resistance performance prediction accuracy, compared to the parametric approach.

키워드

과제정보

이 논문은 2022년도 정부(교육부)의 재원으로 한국연구재단 기초연구사업의 지원을 받아 수행된 연구임(No.2020R1G1A1014172).

참고문헌

  1. Besikci, E.B., Arslan, O., Turan, O. and Olcer, A.I., 2016. An artificial neural network based decision support system for energy efficient ship operations. Computers & Operations Research, 66, pp.393-401.
  2. Choi, M.J., De Silva, L.W. A. and Yamaguchi, H., 2019. Artificial neural network for the short-term prediction of Arctic sea ice concentration. Remote Sensing, 11(9), pp.1071.
  3. Feng, D., Ye, B., Zhang, Z. and Wang, X., 2020. Numerical simulation of the ship resistance of KCS in different water depths for model-scale and Full-scale. Journal of marine science and engineering, 8, pp.745
  4. Grabowska, K. and Szczuko, P., 2015,. Ship resistance prediction with artificial neural networks. In 2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), Poznan, Poland, 28 December 2015.
  5. Janssen, C.F., Koliha, N. and Rung, T., 2015. A fast and rigorously parallel surface voxelization technique for GPUaccelerated CFD simulations. Communications in Computational Physics, 17(5), pp.1246-1270. https://doi.org/10.4208/cicp.2014.m414
  6. Kim, Y.C., Kim, K.S., Hwang, S.H., and Yeon, S. M., 2022a. Prediction of Residual Resistance Coefficient of Ships using Convolutional Neural Network. Journal of the Society of Naval Architects of Korea, 59(4), pp.243-250. https://doi.org/10.3744/SNAK.2022.59.4.243
  7. Kim, H.C. and Park, H.G., 2015. Practical application of neural networks for prediction of ship's performance factors. Journal of Ocean Engineering and Technology, 29(2), pp.111-119. https://doi.org/10.5574/KSOE.2015.29.2.111
  8. Kim, J.H., Roh, M.I., Kim, K.S., Yeo, I.C., Oh, M.J., Nam, J.W., Lee, S.H. and Jang, Y.H., 2022b. Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning. International Journal of Naval Architecture and Ocean Engineering, 100490.
  9. Krizhevsky, A., Sutskever, I. and Hinton, G. E., 2017. Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6), pp.84-90. https://doi.org/10.1145/3065386
  10. LeCun, Y., Bengio, Y, and Hinton, G., 2015. Deep learning. Nature, 521(7553), pp.436-444. https://doi.org/10.1038/nature14539
  11. Panda, J.P., 2021. Machine Learning for Naval Architecture. Ocean and Marine Engineering. arXiv preprint arXiv:2109.05574.
  12. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J. and Chintala, S., 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32.
  13. Wason, R., 2018. Deep learning: Evolution and expansion. Cognitive Systems Research, 52, pp.701-708. https://doi.org/10.1016/j.cogsys.2018.08.023
  14. Zhao, H., Zhang, W., Sun, H. and Xue, B., 2019. Embedded deep learning for ship detection and recognition. Future Internet, 11(2), pp.53.
  15. Zhou, Y., Lu, H., Wang, G., Wang, J. and Li, W., 2020. Voxelization modelling based finite element simulation and process parameter optimization for Fused Filament Fabrication. Materials & Design, 187, 108409.