Hull form optimization of fully parameterized small ships using characteristic curves and deep neural networks
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Designing a hull form typically involves beginning with a reference hull form based on ship owner requirements, editing the hull form to satisfy the requirements, and determining the most efficient hull form. Numerical analyses using Computational Fluid Dynamics (CFD) were employed to assess the performance of the hull form. However, these analyses require extensive computational resources, making it challenging to perform thorough analyses within the design timeframe. To address this issue, this paper proposes an approach that involves defining a range of hull forms with characteristic curves, predicting their performance using Deep Neural Networks (DNNs), and subsequently determining the optimal hull form based on these predictions. Initially, the hull form of a small ship was defined using four characteristic curves and parameterized using 29 variables. Fairness optimization was performed using these characteristic curves to define the hull form surface. By varying 29 parameters, 896 different hull forms were generated, with CFD analysis conducted for each variant. These data were then used to build a DNN model capable of predicting the performance based on hull form parameters. The accuracy of the DNN model was evaluated, resulting in a Mean Absolute Error (MAE) of 2.835%. Subsequently, the DNN model is combined with a genetic algorithm to identify the optimal set of parameters for the hull form, resulting in an optimal hull form. This optimization process revealed that the optimal hull form reduced the total hydrodynamic resistance by approximately 7% compared to the initial reference design. Consequently, this study demonstrates the effectiveness of the proposed method for deriving the optimal hull form for small ships.
Abstract
Designing a hull form typically involves beginning with a reference hull form based on ship owner requirements, editing the hull form to satisfy the requirements, and determining the most efficient hull form. Numerical analyses using Computational Fluid Dynamics (CFD) were employed to assess the performance of the hull form. However, these analyses require extensive computational resources, making it challenging to perform thorough analyses within the design timeframe. To address this issue, this paper proposes an approach that involves defining a range of hull forms with characteristic curves, predicting their performance using Deep Neural Networks (DNNs), and subsequently determining the optimal hull form based on these predictions. Initially, the hull form of a small ship was defined using four characteristic curves and parameterized using 29 variables. Fairness optimization was performed using these characteristic curves to define the hull form surface. By varying 29 parameters, 896 different hull forms were generated, with CFD analysis conducted for each variant. These data were then used to build a DNN model capable of predicting the performance based on hull form parameters. The accuracy of the DNN model was evaluated, resulting in a Mean Absolute Error (MAE) of 2.835%. Subsequently, the DNN model is combined with a genetic algorithm to identify the optimal set of parameters for the hull form, resulting in an optimal hull form. This optimization process revealed that the optimal hull form reduced the total hydrodynamic resistance by approximately 7% compared to the initial reference design. Consequently, this study demonstrates the effectiveness of the proposed method for deriving the optimal hull form for small ships.
참고문헌 (31)
- Boser, B. E., "A training algorithm for optimal margin classifiers", Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pp.144~152 (1992)
- Breiman, L., "Random forests", Mach. Learn, 45, pp.5~32 (2001)
- Chi, Y., "An overview of simulation-based hydrodynamic design of ship hull forms", J. Hydrodyn., Ser. B, 28, pp.947~960 (2016)
- Chun, D. H., "Optimum arrangement design of mastic ropes for membrane-type LNG tanks considering the flatness of thermal insulation panel and production cost", J. Mar. Sci. Eng, 8, pp.353~ (2020)[DOI]
- Deb, K., "A fast and elitist multiobjective genetic algorithm : NSGA-II", IEEE Trans. Evol. Comput, 6, pp.182~197 (2002)[DOI]
- Feng, Y., "Multidisciplinary optimization of an offshore aquaculture vessel hull form based on the support vector regression surrogate model", Ocean Eng, 166, pp.145~158 (2018)[DOI]
- Funahashi, K. I., "On the approximate realization of continuous mappings by neural networks", Neural Network, 2(3), pp.183~192 (1989)[DOI]
- Greiner, G., "Variational design and fairing of spline surfaces", Computer Graphics Forum, pp.143~154 (1994), Wiley Online Library
- Guan, G., "Hull form optimization design of SWATH with combination evaluations of resistance and seakeeping performance", Ocean Eng, 264, pp.112513~ (2022)[DOI]
- Kim, J. H., "Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning", Int. J. Nav. Archit. Ocean Eng, 14, pp.100490~ (2023)[DOI]
- Kim, S. Y., "A Study about Hull Form Generation of High-Speed Coastal Fishing Vessel Using Irrational Function and Hull Form Characteristic Curves", J. Soc. Nav. Archit. Korea, 34, pp.96~103 (1997)
- Kocis, L., "Computational investigations of low-discrepancy sequences", ACM Trans. Math Software, 23, pp.266~294 (1997)[DOI]
- LeCun, Y., "Deep learning", Nature, 521, pp.436~444 (2015)[DOI]
- Lee, K. Y., "Optimal compartment layout design for a naval ship using an improved genetic algorithm", Marine Technology and SNAME News, 39, pp.159~169 (2002)[DOI]
- Lee, K. Y., "An improved genetic algorithm for facility layout problems having inner structure walls and passages", Comput. Oper. Res, 30, pp.117~138 (2003)[DOI]
- Lee, K. Y., "An improved genetic algorithm for multi-floor facility layout problems having inner structure walls and passages", Comput. Oper. Res, 32, pp.879~899 (2005)[DOI]
- Lee, S. M., "Method for a simultaneous determination of the path and the speed for ship route planning problems", Ocean Eng, 157, pp.301~312 (2018)[DOI]
- Lin, Y., "Hull form design optimization of twin-skeg fishing vessel for minimum resistance based on surrogate model", Adv. Eng. Software, 123, pp.38~50 (2018)[DOI]
- Liu, X., "Multi-fidelity model and reduced-order method for comprehensive hydrodynamic performance optimization and prediction of JBC ship", Ocean Eng, 267, pp.113321~ (2023)[DOI]
- Liu, X., "A cross-entropy algorithm based on Quasi-Monte Carlo estimation and its application in hull form optimization", Int. J. Nav. Archit. Ocean Eng, 13, pp.115~125 (2021)[DOI]
- Liu, X., "Multi-fidelity Co-Kriging surrogate model for ship hull form optimization", Ocean Eng, 243, pp.110239~ (2022)[DOI]
- Mittendorf, M., "Hydrodynamic hull form optimization of fast catamarans using surrogate models", Ship Technol. Res, 68, pp.14~26 (2021)[DOI]
- Ouyang, X., "Application of an improved maximum entropy sampling method in hull form optimization", Ocean Eng, 270, pp.112702~ (2023)[DOI]
- Piegl, L., "The NURBS Book" (1996), Springer Science & Business Media
- Roh, M. I., "Computational Ship Design" (2018), Springer
- Sari¨oz, E., "An optimization approach for fairing of ship hull forms", Ocean Eng, 33, pp.2105~2118 (2006)[DOI]
- Snoek, J., "Practical bayesian optimization of machine learning algorithms", Adv. Neural Inf. Process. Syst, pp.25~ (2012)
- Son, E. Y., "Entrance and run angle variations of hull form preserving the prismatic coefficient", Int. J. Nav. Archit. Ocean Eng, 15, pp.100519~ (2023)[DOI]
- Williams, C., "Gaussian processes for regression", Adv. Neural Inf. Process. Syst, pp.8~ (1995)
- Yeo, I. C., "Optimal arrangement design of pipeline support by considering safety and production cost", Int. J. Nav. Archit. Ocean Eng, 15, pp.100531~ (2023)[DOI]
- Zhang, S., "Research on the hull form optimization using the surrogate models", Eng. Appl. Comput. Fluid Mech, 15, pp.747~761 (2021)[DOI]