Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning
2
조회
0
다운로드
7
인용
0
참고문헌
키워드
초록
When designing a ship's hull form, a designer creates various candidate hull forms and performs a Computational Fluid Dynamics (CFD) analysis to evaluate the performance of each candidate. Designers consider quantitative indicators, such as the total resistance and wake coefficient, and qualitative indicators, such as the wave height and pressure distributions, when evaluating the performance of a hull form. During the design process, quantitative and qualitative indicators are often used to determine the superiority of two hull forms. However, in the case of quantitative indicators, the difference between the two hull forms is often minimal; thus, superiority cannot be readily determined. Furthermore, because qualitative indicators are in the form of images, it is challenging to determine the superiority in many cases, even for experienced designers. To solve this problem, we propose a convolutional neural networkbased model for predicting the superiority of hull form performance from a qualitative indicator of the image form derived from CFD analysis. The proposed prediction model received various types of hull form performance images. From these results, the hull form performance characteristics were well fused for prediction with high accuracy. CFD analysis images and quantitative indicators for 1600 hull forms were used to determine the superiority of the prediction model. The learned model was verified using 240 hulls. The result confirmed that the proposed model accurately predicted superiority with an accuracy of approximately 94%.
Abstract
When designing a ship's hull form, a designer creates various candidate hull forms and performs a Computational Fluid Dynamics (CFD) analysis to evaluate the performance of each candidate. Designers consider quantitative indicators, such as the total resistance and wake coefficient, and qualitative indicators, such as the wave height and pressure distributions, when evaluating the performance of a hull form. During the design process, quantitative and qualitative indicators are often used to determine the superiority of two hull forms. However, in the case of quantitative indicators, the difference between the two hull forms is often minimal; thus, superiority cannot be readily determined. Furthermore, because qualitative indicators are in the form of images, it is challenging to determine the superiority in many cases, even for experienced designers. To solve this problem, we propose a convolutional neural networkbased model for predicting the superiority of hull form performance from a qualitative indicator of the image form derived from CFD analysis. The proposed prediction model received various types of hull form performance images. From these results, the hull form performance characteristics were well fused for prediction with high accuracy. CFD analysis images and quantitative indicators for 1600 hull forms were used to determine the superiority of the prediction model. The learned model was verified using 240 hulls. The result confirmed that the proposed model accurately predicted superiority with an accuracy of approximately 94%.
참고문헌 (38)
- Agarap, A. F., "Deep Learning Using Rectified Linear Units (ReLU)", ~ (2018)
- Atienza, R., "Advanced Deep Learning with Keras" (2018), Packt Publishing
- Baird, Z., "A CNN-LSTM network for augmenting target detection in real maritime wide area surveillance radar data", IEEE Access, 8, pp.179281~179294 (2020)[DOI]
- Bodla, N., "Deep heterogeneous feature fusion for template-based face recognition", Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017, pp.586~595 (2017), IEEE
- Cheng, G., "Cross-scale feature fusion for object detection in optical remote sensing images", Geosci. Rem. Sens. Lett. IEEE, 18, pp.431~435 (2020)[DOI]
- Choi, J. E., "Computational predictions of ship-speed performance", J. Mar. Sci. Technol, 14, pp.322~333 (2009)[DOI]
- Duarte, D., "Satellite image classification of building damages using airborne and satellite image samples in a deep learning approach", ISPRS Annal. Photogram., Remo. Sens. Spatial Inform. Sci, 4, pp.89~96 (2018)[DOI]
- Feichtenhofer, C., "Convolutional two-stream network fusion for video action recognition", Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.1933~1941 (2016)
- He, K., "Deep residual learning for image recognition", Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.770~778 (2016)
- Hochreiter, S., "Long short-term memory", Neural Comput, 9, pp.1735~1780 (1997)
- Howard, A. G., "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications", ~ (2017)
- Ian, G., "Deep Learning, Nature" (2016), MIT Press
- ITTC, "ITTC e Recommended Procedures and Guidelines - Testing and Extrapolation Methods High Speed Marine Vehicles - Resistance Test. 7.5-02-05-01 (Revision 02)", ~ (2008)
- 지바한, "딥러닝 기술을 이용한 캐비테이션 자동인식에 대한 연구", 대한조선학회 논문집, 58(2), pp.105~111 (2021), 대한조선학회[DOI]
- Jiang, Y. G., "Modeling multimodal clues in a hybrid deep learning framework for video classification", IEEE Transactions on Multimedia, pp.3137~3147 (2018)[DOI]
- Kim, B. S., "Study on hull optimization process considering operational efficiency in waves", Processes, 9, pp.898~ (2021)[DOI]
- Kim, H., "Object detection algorithm for unmanned surface vehicle using faster R-CNN", World Maritime Technology Conference, pp.1~12 (2018)
- Kim, K. S., "Prediction of ocean weather based on denoising autoencoder and convolutional LSTM", J. Mar. Sci. Eng, 8, pp.1~24 (2020)[DOI]
- Kingma, D. P., "Adam: a method for stochastic optimization. 3rd international conference on learning representations", ICLR 2015 - Conference Track Proceedings (2015)
- Kong, M. C., "Object detection method for ship safety plans using deep learning", Ocean Eng, 246, pp.110587~ (2022)[DOI]
- Larsson, L., "CFD in Ship Hydrodynamics - Results of the Gothenburg 2010 Workshop", Computational Methods in Applied Sciences (2013), Springer[DOI]
- 이준범, "Prediction of ship power based on variation in deep feed-forward neural network", International Journal of Naval Architecture and Ocean Engineering, 13, pp.641~649 (2021), 대한조선학회[DOI]
- 이재빈, "In-plane and out-of-plane bending moments and local stresses in mooring chain links using machine learning technique", International Journal of Naval Architecture and Ocean Engineering, 13, pp.848~857 (2021), 대한조선학회[DOI]
- Sung-Jun Lee, "Image-based ship detection using deep learning", Ocean Systems Engineering, 10(4), pp.415~434 (2020), 테크노프레스[DOI]
- Lee, S. J., "Image-based object detection and tracking method for ship navigation", RINA, Royal Institution of Naval Architects - 19th International Conference on Computer Applications in Shipbuilding (2019)
- Lee Won-Jae, "Detection and tracking for the awareness of surroundings of a ship based on deep learning", Journal of Computational Design and Engineering, 8(5), pp.1407~1430 (2021), 한국CDE학회[DOI]
- Lin, T. Y., "Focal loss for dense object detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, pp.318~327 (2020)[DOI]
- O'Halloran, S., "Lecture 9: Logit", Probit, 2013
- Redmon, J., "YOLOv3: an Incremental Improvement", ~ (2018)
- Ren, S., "Faster R-CNN: towards real-time object detection with region proposal networks", IEEE Trans. Pattern Anal. Mach. Intell, 39, pp.1137~1149 (2017)[DOI]
- Roh, M. I., "An initial hull structural modeling system for computeraided process planning in shipbuilding", Adv. Eng. Software, 37(7), pp.457~476 (2006)[DOI]
- Roh, M. I., "Computational Ship Design" (2018), Springer
- Song Euijeong, "SRPS–deep-learning-based photometric stereo using superresolution images", Journal of Computational Design and Engineering, 8(4), pp.995~1012 (2021), 한국CDE학회[DOI]
- Tobias C. Spruegel, "Approach and application to transfer heterogeneous simulation data from finite element analysis to neural networks", Journal of Computational Design and Engineering, 8(1), pp.298~315 (2021), 한국CDE학회[DOI]
- Szegedy, C., "Rethinking the inception architecture for computer vision", Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.2818~2826 (2016)
- Weng, W., "INet: convolutional networks for biomedical image segmentation", IEEE Access, pp.16591~16603 (2021), Springer[DOI]
- Wu, Z., "Modeling spatial-temporal clues in a hybrid deep learning framework for video classification", Proceedings of the 23rd ACM International Conference on Multimedia, pp.461~470 (2015)
- Yao, Y., "On early stopping in gradient descent learning", Constr. Approx, 26, pp.289~315 (2007)[DOI]