The construction of a neural network proxy model for ship hull design based on multi-fidelity datasets and the parameter freezing strategy

References

• Alfonsi G. 2009. Reynolds-averaged Navier–Stokes equations for turbulence modeling. Appl Mech Rev. 62(4):040802. doi:10.1115/1.3124648.
   Web of Science ®Google Scholar
• Anderson JD, Wendt J. 1995. Computational fluid dynamics. Vol. 206. Springer.
   Google Scholar
• Ao Y., Duan H., Li S. 2024. An integrated-hull design assisted by artificial intelligence-aided design method. Computers & Structures. 297:107320. doi:10.1016/j.compstruc.2024.107320.
   Web of Science ®Google Scholar
• Ao Y, Li Y, Gong J, Li S. 2021. An artificial intelligence-aided design (AIAD) of ship hull structures. J Ocean Eng Sci. 8(1):15–32.
   Web of Science ®Google Scholar
• Ao Y, Li Y, Gong J, Li S. 2022. Artificial intelligence design for ship structures: a variant multiple-input neural network based ship resistance prediction. J Mech Des. 144(9):091707.
   Web of Science ®Google Scholar
• Bakhtiari M, Ghassemi H. 2020. CFD data based neural network functions for predicting hydrodynamic performance of a low-pitch marine cycloidal propeller. Appl Ocean Res. 94:101981. doi: 10.1016/j.apor.2019.101981.
   Web of Science ®Google Scholar
• Buhmann MD. 2000. Radial basis functions. Acta Numer. 9:1–38. doi: 10.1017/S0962492900000015.
   Google Scholar
• Chorin AJ. 1997. A numerical method for solving incompressible viscous flow problems. J Comput Phys. 135:118–125. doi: 10.1006/jcph.1997.5716.
   Web of Science ®Google Scholar
• Claveria O, Monte E, Torra S. 2015. Research Institute of Applied Economics. 2015:1–28.
   Google Scholar
• D'Agostino D, Serani A, Stern F, Diez M. 2021. Recurrent-type neural networks for real-time short-term prediction of ship motions in high sea state. arXiv preprint arXiv:2105.13102.
   Google Scholar
• Dawson C. 1977. A practical computer method for solving ship-wave problems. In: Proceedings of second international conference on numerical ship hydrodynamics. p. 30–38.
   Google Scholar
• Dick S. 2019. Artificial Intelligence. Harvard Data Science Review. 1(1). https://doi.org/10.1162/99608f92.92fe150c.
   Google Scholar
• Eymard R, Gallouët T, Herbin R. 2000. Finite volume methods. Handb Numer Anal. 7:713–1018.
   Google Scholar
• Forti D, Rozza G. 2014. Efficient geometrical parametrisation techniques of interfaces for reduced-order modelling: application to fluid–structure interaction coupling problems. Int J Comut Fluid Dyn. 28:158–169. doi: 10.1080/10618562.2014.932352.
   Web of Science ®Google Scholar
• He K, Zhang X, Ren S, Sun J. 2015. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision. p. 1026–1034.
   Google Scholar
• Hess JL, Smith A. 1967. Calculation of potential flow about arbitrary bodies. Prog Aerosp Sci. 8:1–138. doi: 10.1016/0376-0421(67)90003-6.
   Google Scholar
• Hirt CW, Nichols BD. 1981. Volume of fluid (VOF) method for the dynamics of free boundaries. J Comput Phys. 39:201–225. doi: 10.1016/0021-9991(81)90145-5.
   Web of Science ®Google Scholar
• Huang CJ, Kuo PH. 2019. Multiple-input deep convolutional neural network model for short-term photovoltaic power forecasting. IEEE Access. 7:74822–74834. doi: 10.1109/Access.6287639.
   Web of Science ®Google Scholar
• Kazemi H, Doustdar MM, Najafi A, Nowruzi H, Ameri MJ. 2021. Hydrodynamic performance prediction of stepped planing craft using CFD and ANNs. J Mar Sci Appl. 20:67–84. doi: 10.1007/s11804-020-00182-y.
   Web of Science ®Google Scholar
• Li Y, Gong J, Ma Q, Yan S. 2018. Effects of the terms associated with ϕzz in free surface condition on the attitudes and resistance of different ships. Eng Anal Bound Elem. 95:266–285. doi: 10.1016/j.enganabound.2018.08.006.
   Web of Science ®Google Scholar
• Mittendorf M, Nielsen UD, Bingham HB. 2022. Data-driven prediction of added-wave resistance on ships in oblique waves comparison between tree-based ensemble methods and artificial neural networks. Appl Ocean Res. 118:102964. doi: 10.1016/j.apor.2021.102964.
   Web of Science ®Google Scholar
• Nagelkerke NJ. 1991. A note on a general definition of the coefficient of determination. biometrika. 78:691–692. doi: 10.1093/biomet/78.3.691.
   Web of Science ®Google Scholar
• Panda JP, Warrior H. 2022. Data-driven prediction of complex flow field over an axisymmetric body of revolution using machine learning. J Offsh Mech Arct Eng. 144:060903. doi: 10.1115/1.4055280.
   Web of Science ®Google Scholar
• Peng H, Ni S, Qiu W. 2014. Wave pattern and resistance prediction for ships of full form. Ocean Eng. 87:162–173. doi: 10.1016/j.oceaneng.2014.06.004.
   Web of Science ®Google Scholar
• Prpić-Oršić J, Valčić M, Čarija Z. 2020. A hybrid wind load estimation method for container ship based on computational fluid dynamics and neural networks. J Mar Sci Eng. 8:539. doi: 10.3390/jmse8070539.
   Web of Science ®Google Scholar
• Siemens Digital Industries Software. 2021. Simcenter STAR-CCM+ User Guide, version 2021.1. 
   Google Scholar
• Silva KM, Maki KJ. 2022. Data-driven system identification of 6-DoF ship motion in waves with neural networks. Appl Ocean Res. 125:103222. doi: 10.1016/j.apor.2022.103222.
   Web of Science ®Google Scholar
• Sun Z, Sun Ly, Xu Lx, Hu Yl, Zhang Gy, Zong Z. 2023. A CFD-based data-driven reduced order modeling method for damaged ship motion in waves. J Mar Sci Eng. 11:686. doi: 10.3390/jmse11040686.
   Web of Science ®Google Scholar
• Willmott CJ, Matsuura K. 2005. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim Res. 30:79–82. doi: 10.3354/cr030079.
   Web of Science ®Google Scholar
• Zhang RZ. 2010. Verification and validation for RANS simulation of KCS container ship without/with propeller. J Hydrodyn. 22:889–896. doi: 10.1016/S1001-6058(10)60055-8.
   Web of Science ®Google Scholar