Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Multi-Objective Hull Form Optimization with CAD Engine-based Deep Learning Physics for 3D Flow Prediction (2306.12915v1)

Published 22 Jun 2023 in cs.LG, cs.CV, and physics.flu-dyn

Abstract: In this work, we propose a built-in Deep Learning Physics Optimization (DLPO) framework to set up a shape optimization study of the Duisburg Test Case (DTC) container vessel. We present two different applications: (1) sensitivity analysis to detect the most promising generic basis hull shapes, and (2) multi-objective optimization to quantify the trade-off between optimal hull forms. DLPO framework allows for the evaluation of design iterations automatically in an end-to-end manner. We achieved these results by coupling Extrality's Deep Learning Physics (DLP) model to a CAD engine and an optimizer. Our proposed DLP model is trained on full 3D volume data coming from RANS simulations, and it can provide accurate and high-quality 3D flow predictions in real-time, which makes it a good evaluator to perform optimization of new container vessel designs w.r.t the hydrodynamic efficiency. In particular, it is able to recover the forces acting on the vessel by integration on the hull surface with a mean relative error of 3.84\% \pm 2.179\% on the total resistance. Each iteration takes only 20 seconds, thus leading to a drastic saving of time and engineering efforts, while delivering valuable insight into the performance of the vessel, including RANS-like detailed flow information. We conclude that DLPO framework is a promising tool to accelerate the ship design process and lead to more efficient ships with better hydrodynamic performance.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (21)
  1. “Accelerating marine propeller development in early design stages using machine learning” In 21th Conference on Computer Applications and Information Technology in the Maritime Industries, COMPIT 2022, 2022, pp. 7–15
  2. “Geometric Deep Learning: Going beyond Euclidean data” In IEEE Signal Processing Magazine 34.4, 2017, pp. 18–42 DOI: 10.1109/MSP.2017.2693418
  3. J.F.C. Conn and Cuthbert Coulson Pounder “Encyclopedia Britannica: ship construction”, 2018 URL: https://www.britannica.com/technology/ship-construction
  4. Ould El Moctar, Vladimir Shigunov and Tobias Zorn “Duisburg test case: Post-panamax container ship for benchmarking” In Ship Technology Research 59.3, 2012, pp. 50–64 DOI: 10.1179/str.2012.59.3.004
  5. Alexander I.J. Forrester, Andras Sobester and Andy J. Keane “Engineering Design via Surrogate Modelling - A Practical Guide” Wiley, 2008, pp. I–XVIII\bibrangessep1–210
  6. Systems Friendship “CAESES”, 2018 URL: https://www.friendship-systems.com/products/caeses/
  7. Rober R. Hilleary “The tangent search method of constrained minimization”, 1966
  8. Kurt Hornik, Maxwell Stinchcombe and Halbert White “Multilayer feedforward networks are universal approximators” In Neural Networks 2.5, 1989, pp. 359–366 DOI: https://doi.org/10.1016/0893-6080(89)90020-8
  9. Diederik P. Kingma and Jimmy Ba “Adam: A Method for Stochastic Optimization”, 2014 arXiv:1412.6980 [cs.LG]
  10. Alex Krizhevsky, Ilya Sutskever and Geoffrey E Hinton “ImageNet Classification with Deep Convolutional Neural Networks” In Advances in Neural Information Processing Systems 25 Curran Associates, Inc., 2012 URL: https://proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf
  11. “The Geometry of Ships”, The principles of naval architecture series Society of Naval ArchitectsMarine Engineers, 2009 URL: https://books.google.de/books?id=gEHUMgEACAAJ
  12. “On quasirandom sequences for numerical computations” In USSR Computational Mathematics and Mathematical Physics 28.3, 1988, pp. 88–92 DOI: https://doi.org/10.1016/0041-5553(88)90181-4
  13. “Learning Mesh-Based Simulation with Graph Networks”, 2020, pp. 1–18 arXiv: http://arxiv.org/abs/2010.03409
  14. “Surrogate-based analysis and optimization” In Progress in Aerospace Sciences 41.1, 2005, pp. 1–28 DOI: https://doi.org/10.1016/j.paerosci.2005.02.001
  15. “Wave resistance minimisation in practical ship design” In 7th International Conference on Computational Methods in Marine Engineering, MARINE 2017 2017-May, 2017
  16. Thomas P. Scholcz, Tomasz Gornicz and Christian Veldhuis “Multi-objective hull-form optimization using Kriging on noisy computer experiments”, 2015, pp. 1064–1077 DOI: 10.13140/RG.2.1.4173.5124
  17. Thomas P. Scholcz and Christian H.J. Veldhuis “Multi-objective surrogate based hull-form optimization using high-fidelity rans computations” In 7th International Conference on Computational Methods in Marine Engineering, MARINE 2017 2017-May.May, 2017, pp. 231–242
  18. O.P. Sha, T. Ray and R.P. Gokarn “An artificial neural network model for preliminary ship design” In 8th International Conference on Computer Applications in Shipbuilding, ICCAS 94 2, 1994, pp. 10–15
  19. Software Siemens Digital Industries “Simcenter STAR-CCM+”, 2021 URL: https://www.plm.automation.siemens.com/global/en/products/simcenter/STAR-CCM.html
  20. “Improved hull design with potential-flow-based parametric computer experiments” In 8th International Conference on Computational Methods in Marine Engineering, MARINE 2019 4.4, 2019, pp. 321–333
  21. “Hull Form Optimization with Principal Component Analysis and Deep Neural Network”, 2018 arXiv:1810.11701 [stat.ML]

Summary

We haven't generated a summary for this paper yet.