Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 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

Tailoring Generative Adversarial Networks for Smooth Airfoil Design (2404.11816v1)

Published 18 Apr 2024 in cs.LG

Abstract: In the realm of aerospace design, achieving smooth curves is paramount, particularly when crafting objects such as airfoils. Generative Adversarial Network (GAN), a widely employed generative AI technique, has proven instrumental in synthesizing airfoil designs. However, a common limitation of GAN is the inherent lack of smoothness in the generated airfoil surfaces. To address this issue, we present a GAN model featuring a customized loss function built to produce seamlessly contoured airfoil designs. Additionally, our model demonstrates a substantial increase in design diversity compared to a conventional GAN augmented with a post-processing smoothing filter.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (26)
  1. L. Regenwetter, A. H. Nobari, and F. Ahmed, “Deep generative models in engineering design: A review,” Journal of Mechanical Design, vol. 144, no. 7, p. 071704, 2022.
  2. J. Li, X. Du, and J. R. Martins, “Machine learning in aerodynamic shape optimization,” Progress in Aerospace Sciences, vol. 134, p. 100849, Oct. 2022.
  3. 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.
  4. E. Yilmaz and B. German, “Conditional generative adversarial network framework for airfoil inverse design,” in AIAA aviation 2020 forum, 2020, p. 3185.
  5. A. Heyrani Nobari, W. Chen, and F. Ahmed, “Pcdgan: A continuous conditional diverse generative adversarial network for inverse design,” in Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, 2021, pp. 606–616.
  6. J. Li and M. Zhang, “On deep-learning-based geometric filtering in aerodynamic shape optimization,” Aerospace Science and Technology, vol. 112, p. 106603, May 2021.
  7. Q. Du, T. Liu, L. Yang, L. Li, D. Zhang, and Y. Xie, “Airfoil design and surrogate modeling for performance prediction based on deep learning method,” Physics of Fluids, vol. 34, no. 1, 2022.
  8. G. Achour, W. J. Sung, O. J. Pinon-Fischer, and D. N. Mavris, “Development of a conditional generative adversarial network for airfoil shape optimization,” in AIAA Scitech 2020 Forum, 2020, p. 2261.
  9. X. Tan, D. Manna, J. Chattoraj, L. Yong, X. Xinxing, D. M. Ha, and Y. Feng, “Airfoil inverse design using conditional generative adversarial networks,” in 2022 17th International Conference on Control, Automation, Robotics and Vision (ICARCV).   IEEE, 2022, pp. 143–148.
  10. G. B. Santos, A. V. Pantaleão, and L. O. Salviano, “Using deep generative adversarial network to explore novel airfoil designs for vertical-axis wind turbines,” Energy Conversion and Management, vol. 282, p. 116849, 2023.
  11. K. Wada, K. Suzuki, and K. Yonekura, “Physics-guided training of gan to improve accuracy in airfoil design synthesis,” arXiv preprint arXiv:2308.10038, 2023.
  12. W. Chen and M. Fuge, “B\\\backslash\’eziergan: Automatic generation of smooth curves from interpretable low-dimensional parameters,” arXiv preprint arXiv:1808.08871, 2018.
  13. W. Chen, K. Chiu, and M. Fuge, “Aerodynamic design optimization and shape exploration using generative adversarial networks,” in AIAA Scitech 2019 Forum, 2019, p. 2351.
  14. W. Chen, K. Chiu, and M. D. Fuge, “Airfoil design parameterization and optimization using bézier generative adversarial networks,” AIAA journal, vol. 58, no. 11, pp. 4723–4735, 2020.
  15. K. Yonekura, N. Miyamoto, and K. Suzuki, “Inverse airfoil design method for generating varieties of smooth airfoils using conditional wgan-gp,” Structural and Multidisciplinary Optimization, vol. 65, no. 6, p. 173, 2022.
  16. M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein generative adversarial networks,” in International conference on machine learning.   PMLR, 2017, pp. 214–223.
  17. Y. Wang, K. Shimada, and A. B. Farimani, “Airfoil gan: Encoding and synthesizing airfoils for aerodynamic shape optimization,” Journal of Computational Design and Engineering, p. qwad046, 2023.
  18. A. B. L. Larsen, S. K. Sønderby, H. Larochelle, and O. Winther, “Autoencoding beyond pixels using a learned similarity metric,” in International conference on machine learning.   PMLR, 2016, pp. 1558–1566.
  19. M. S. Selig. (1996) Uiuc airfoil data site. [Online]. Available: https://m-selig.ae.illinois.edu/ads/coord_database.html
  20. J. Li, S. He, and J. R. Martins, “Data-driven constraint approach to ensure low-speed performance in transonic aerodynamic shape optimization,” Aerospace Science and Technology, vol. 92, p. 536–550, Sep. 2019.
  21. J. Li, M. A. Bouhlel, and J. R. Martins, “Data-based approach for fast airfoil analysis and optimization,” AIAA Journal, vol. 57, no. 2, pp. 581–596, 2019.
  22. M. Drela, “Xfoil: An analysis and design system for low reynolds number airfoils,” in Low Reynolds Number Aerodynamics: Proceedings of the Conference Notre Dame, Indiana, USA, 5–7 June 1989.   Springer, 1989, pp. 1–12.
  23. M. Mirza and S. Osindero, “Conditional generative adversarial nets,” arXiv preprint arXiv:1411.1784, 2014.
  24. N. C. Brown and C. T. Mueller, “Quantifying diversity in parametric design: a comparison of possible metrics,” AI EDAM, vol. 33, no. 1, pp. 40–53, 2019.
  25. W. H. Press and S. A. Teukolsky, “Savitzky-golay smoothing filters,” Computers in Physics, vol. 4, no. 6, pp. 669–672, 1990.
  26. D. Yang, S. Hong, Y. Jang, T. Zhao, and H. Lee, “Diversity-sensitive conditional generative adversarial networks,” arXiv preprint arXiv:1901.09024, 2019.
Citations (2)

Summary

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