Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Enhancing Vehicle Aerodynamics with Deep Reinforcement Learning in Voxelised Models (2405.11492v1)

Published 19 May 2024 in cs.RO and cs.CV

Abstract: Aerodynamic design optimisation plays a crucial role in improving the performance and efficiency of automotive vehicles. This paper presents a novel approach for aerodynamic optimisation in car design using deep reinforcement learning (DRL). Traditional optimisation methods often face challenges in handling the complexity of the design space and capturing non-linear relationships between design parameters and aerodynamic performance metrics. This study addresses these challenges by employing DRL to learn optimal aerodynamic design strategies in a voxelised model representation. The proposed approach utilises voxelised models to discretise the vehicle geometry into a grid of voxels, allowing for a detailed representation of the aerodynamic flow field. The Proximal Policy Optimisation (PPO) algorithm is then employed to train a DRL agent to optimise the design parameters of the vehicle with respect to drag force, kinetic energy, and voxel collision count. Experimental results demonstrate the effectiveness and efficiency of the proposed approach in achieving significant results in aerodynamic performance. The findings highlight the potential of DRL techniques for addressing complex aerodynamic design optimisation problems in automotive engineering, with implications for improving vehicle performance, fuel efficiency, and environmental sustainability.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. H. Wang, X. Zhu, and Z. Du, “Aerodynamic optimization for low pressure turbine exhaust hood using kriging surrogate model,” International communications in heat and mass transfer, vol. 37, no. 8, pp. 998–1003, 2010.
  2. M. Urquhart, E. Ljungskog, and S. Sebben, “Surrogate-based optimisation using adaptively scaled radial basis functions,” Applied Soft Computing, vol. 88, p. 106050, 2020.
  3. G. Sun and S. Wang, “A review of the artificial neural network surrogate modeling in aerodynamic design,” Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, vol. 233, no. 16, pp. 5863–5872, 2019.
  4. H. Chen, L. He, W. Qian, and S. Wang, “Multiple aerodynamic coefficient prediction of airfoils using a convolutional neural network,” Symmetry, vol. 12, no. 4, p. 544, 2020.
  5. Z. Cao, J. Xu, W. Xiao, Y. Gao, and H. Wu, “A novel method for detection of wind turbine blade imbalance based on multi-variable spectrum imaging and convolutional neural network,” in 2019 Chinese Control Conference (CCC).   IEEE, 2019, pp. 4925–4930.
  6. X. Du, P. He, and J. R. Martins, “A b-spline-based generative adversarial network model for fast interactive airfoil aerodynamic optimization,” in AIAA Scitech 2020 Forum, 2020, p. 2128.
  7. K. Li, T. Zhang, and R. Wang, “Deep reinforcement learning for multiobjective optimization,” IEEE transactions on cybernetics, vol. 51, no. 6, pp. 3103–3114, 2020.
  8. T. Yang, H. Tang, C. Bai, J. Liu, J. Hao, Z. Meng, P. Liu, and Z. Wang, “Exploration in deep reinforcement learning: a comprehensive survey,” arXiv preprint arXiv:2109.06668, 2021.
  9. N. Vithayathil Varghese and Q. H. Mahmoud, “A survey of multi-task deep reinforcement learning,” Electronics, vol. 9, no. 9, p. 1363, 2020.
  10. M. Aleksandrov, S. Zlatanova, and D. J. Heslop, “Voxelisation algorithms and data structures: A review,” Sensors, vol. 21, no. 24, p. 8241, 2021.
  11. P. Nourian, R. Gonçalves, S. Zlatanova, K. A. Ohori, and A. V. Vo, “Voxelization algorithms for geospatial applications: Computational methods for voxelating spatial datasets of 3d city models containing 3d surface, curve and point data models,” MethodsX, vol. 3, pp. 69–86, 2016.
  12. X. Yang, H. Li, H. Zhai, Y. Ming, Y. Liu, and G. Zhang, “Vox-fusion: Dense tracking and mapping with voxel-based neural implicit representation,” in 2022 IEEE International Symposium on Mixed and Augmented Reality (ISMAR).   IEEE, 2022, pp. 499–507.
  13. A. Telea and A. Jalba, “Voxel-based assessment of printability of 3d shapes,” in Mathematical Morphology and Its Applications to Image and Signal Processing: 10th International Symposium, ISMM 2011, Verbania-Intra, Italy, July 6-8, 2011. Proceedings 10.   Springer, 2011, pp. 393–404.
  14. D. Lindlbauer and A. D. Wilson, “Remixed reality: Manipulating space and time in augmented reality,” in Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, 2018, pp. 1–13.
  15. V. Kniaz, F. Remondino, and V. Knyaz, “Generative adversarial networks for single photo 3d reconstruction,” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 42, pp. 403–408, 2019.
  16. P. Hübner, M. Weinmann, S. Wursthorn, and S. Hinz, “Automatic voxel-based 3d indoor reconstruction and room partitioning from triangle meshes,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 181, pp. 254–278, 2021.
  17. W. Cai, D. Liu, X. Ning, C. Wang, and G. Xie, “Voxel-based three-view hybrid parallel network for 3d object classification,” Displays, vol. 69, p. 102076, 2021.
  18. F. Poux and R. Billen, “Voxel-based 3d point cloud semantic segmentation: Unsupervised geometric and relationship featuring vs deep learning methods,” ISPRS International Journal of Geo-Information, vol. 8, no. 5, p. 213, 2019.
  19. A. Saleem and M.-H. Kim, “Aerodynamic performance optimization of an airfoil-based airborne wind turbine using genetic algorithm,” Energy, vol. 203, p. 117841, 2020.
  20. Y. Li, K. Wei, W. Yang, and Q. Wang, “Improving wind turbine blade based on multi-objective particle swarm optimization,” Renewable Energy, vol. 161, pp. 525–542, 2020.
  21. Z. Lyu, Z. Xu, and J. Martins, “Benchmarking optimization algorithms for wing aerodynamic design optimization,” in Proceedings of the 8th International Conference on Computational Fluid Dynamics, Chengdu, Sichuan, China, vol. 11.   Citeseer, 2014, p. 585.
  22. S. N. Skinner and H. Zare-Behtash, “State-of-the-art in aerodynamic shape optimisation methods,” Applied Soft Computing, vol. 62, pp. 933–962, 2018.
  23. J. Li, Z. Gao, J. Huang, and K. Zhao, “Aerodynamic design optimization of nacelle/pylon position on an aircraft,” Chinese Journal of Aeronautics, vol. 26, no. 4, pp. 850–857, 2013.
  24. J. Li, J. Cai, and K. Qu, “Surrogate-based aerodynamic shape optimization with the active subspace method,” Structural and Multidisciplinary Optimization, vol. 59, pp. 403–419, 2019.
  25. J. Li, M. Zhang, J. R. Martins, and C. Shu, “Efficient aerodynamic shape optimization with deep-learning-based geometric filtering,” AIAA journal, vol. 58, no. 10, pp. 4243–4259, 2020.
  26. J. Li, X. Du, and J. R. Martins, “Machine learning in aerodynamic shape optimization,” Progress in Aerospace Sciences, vol. 134, p. 100849, 2022.
  27. R. Li, Y. Zhang, and H. Chen, “Learning the aerodynamic design of supercritical airfoils through deep reinforcement learning,” AIAA Journal, vol. 59, no. 10, pp. 3988–4001, 2021.
  28. K. Arulkumaran, M. P. Deisenroth, M. Brundage, and A. A. Bharath, “A brief survey of deep reinforcement learning,” arXiv preprint arXiv:1708.05866, 2017.
  29. X. Yan, J. Zhu, M. Kuang, and X. Wang, “Aerodynamic shape optimization using a novel optimizer based on machine learning techniques,” Aerospace Science and Technology, vol. 86, pp. 826–835, 2019.
  30. J. Viquerat, J. Rabault, A. Kuhnle, H. Ghraieb, A. Larcher, and E. Hachem, “Direct shape optimization through deep reinforcement learning,” Journal of Computational Physics, vol. 428, p. 110080, 2021.
  31. P. Garnier, J. Viquerat, J. Rabault, A. Larcher, A. Kuhnle, and E. Hachem, “A review on deep reinforcement learning for fluid mechanics,” Computers & Fluids, vol. 225, p. 104973, 2021.

Summary

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now