합성곱 신경망과 복셀화를 활용한 선박 저항 성능 예측
Prediction of Ship Resistance Performance Based on the Convolutional Neural Network With Voxelization
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
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.
Abstract
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.
참고문헌 (15)
- Beşikçi, E. B., "An artificial neural network based decision support system for energy efficient ship operations", Computers & Operations Research, 66, pp.393~401 (2016)
- Choi, M. J., "Artificial neural network for the short-term prediction of Arctic sea ice concentration", Remote Sensing, 11(9), pp.1071~ (2019)
- Feng, D., "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~ (2020)
- Grabowska, K., "Ship resistance prediction with artificial neural networks", 2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) (2015)
- Janßen, C. F., "A fast and rigorously parallel surface voxelization technique for GPUaccelerated CFD simulations", Communications in Computational Physics, 17(5), pp.1246~1270 (2015)
- 김유철, "합성곱 신경망을 이용한 선박의 잉여저항계수 추정", 대한조선학회 논문집, 59(4), pp.243~250 (2022), 대한조선학회[DOI]
- 김현철, "선박의 성능 요소 추정을 위한 신경망의 실용화 연구", 한국해양공학회지, 29(2), pp.111~119 (2015), 한국해양공학회
- 김진혁, "Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning", International Journal of Naval Architecture and Ocean Engineering, 14, pp.1~15 (2022), 대한조선학회[DOI]
- Krizhevsky, A., "Imagenet classification with deep convolutional neural networks", Communications of the ACM, 60(6), pp.84~90 (2017)
- LeCun, Y., "Deep learning", Nature, 521(7553), pp.436~444 (2015)
- Panda, J. P., "Machine Learning for Naval Architecture. Ocean and Marine Engineering", arXiv preprint arXiv:2109. 05574, ~ (2021)
- Paszke, A., "Pytorch: An imperative style, high-performance deep learning library", Advances in neural information processing systems, 32 (2019)
- Wason, R., "Deep learning: Evolution and expansion", Cognitive Systems Research, 52, pp.701~708 (2018)
- Zhao, H., "Embedded deep learning for ship detection and recognition", Future Internet, 11(2), pp.53~ (2019)
- Zhou, Y., "Voxelization modelling based finite element simulation and process parameter optimization for Fused Filament Fabrication", Materials & Design, 187, pp.108409~ (2020)