In aerodynamic shape optimization, the convergence and computational cost are greatly affected by the representation capacity and compactness of the design space. Previous research has demonstrated that using a deep generative model to parameterize two-dimensional (2D) airfoils achieves high representation capacity/compactness, which significantly benefits shape optimization. In this paper, we propose a deep generative model, Free-Form Deformation Generative Adversarial Networks (FFD-GAN), that provides an efficient parameterization for three-dimensional (3D) aerodynamic/hydrodynamic shapes like aircraft wings, turbine blades, car bodies, and hulls. The learned model maps a compact set of design variables to 3D surface points representing the shape. We ensure the surface smoothness and continuity of generated geometries by incorporating an FFD layer into the generative model. We demonstrate FFD-GAN's performance using a wing shape design example. The results show that FFD-GAN can generate realistic designs and form a reasonable parameterization. We further demonstrate FFD-GAN's high representation compactness and capacity by testing its design space coverage, the feasibility ratio of the design space, and its performance in design optimization. We demonstrate that over 94% feasibility ratio is achieved among wings randomly generated by the FFD-GAN, while FFD and B-spline only achieve less than 31%. We also show that the FFD-GAN leads to an order of magnitude faster convergence in a wing shape optimization problem, compared to the FFD and the B-spline parameterizations.


翻译:在空气动力元件优化中,趋同和计算成本受到设计空间代表能力和紧凑度的极大影响。以前的研究表明,使用深基因模型来参数化二维(2D)表层(Airfolors)的参数,可以实现高代表性能力/方程式,从而大大有利于形成优化。在本文中,我们提出了一个深基因模型,即Fret-Fredform Deform Dismation General Aversarial Networks(FFD-GAN),它为三维(3D)空气动力/水力加速度形状提供了有效的参数化,例如飞机翼、涡轮叶、汽车机身和船体。所学的模型将一组设计变量缩放到代表形状的3D(3D)表面点。我们通过将FFFDD层纳入基因模型,确保生成的地理变化的表面平稳性和连续性。我们用翅膀设计演示FFFDFD-G-G-G-G的性能性能性能,我们用FD-FA-FD-FD-FD-FD-FS-FD-S-FS-S-FS-FS-FS-FS-FS-FS-FS-FS-FS-FS-FS-FS-S-S-FS-FS-FS-FS-S-S-S-FS-FS-FS-S-A-FS-FS-FS-FS-FS-FS-FS-FS-FS-FS-FS-FS-A-FS-FS-FS-FS-A-FS-A-S-A-A-S-FS-A-A-A-A-A-A-A-A-A-A-FA-FA-FA-FA-FA-FA-FA-FA-FA-FA-FA-FS-FS-FS-FS-FS-FA-FA-FA-FS-FS-FS-FS-FS-FA-FA-FA-FA-FA-FA-F

0
下载
关闭预览

相关内容

最新【深度生成模型】Deep Generative Models,104页ppt
专知会员服务
69+阅读 · 2020年10月24日
GAN新书《生成式深度学习》,Generative Deep Learning,379页pdf
专知会员服务
202+阅读 · 2019年9月30日
Hierarchically Structured Meta-learning
CreateAMind
26+阅读 · 2019年5月22日
强化学习的Unsupervised Meta-Learning
CreateAMind
17+阅读 · 2019年1月7日
Unsupervised Learning via Meta-Learning
CreateAMind
42+阅读 · 2019年1月3日
Hierarchical Disentangled Representations
CreateAMind
4+阅读 · 2018年4月15日
条件GAN重大改进!cGANs with Projection Discriminator
CreateAMind
8+阅读 · 2018年2月7日
Auto-Encoding GAN
CreateAMind
7+阅读 · 2017年8月4日
GAN猫的脸
机械鸡
11+阅读 · 2017年7月8日
Arxiv
0+阅读 · 2021年3月8日
Learning Implicit Fields for Generative Shape Modeling
Arxiv
10+阅读 · 2018年12月6日
Arxiv
10+阅读 · 2018年3月23日
VIP会员
相关资讯
Hierarchically Structured Meta-learning
CreateAMind
26+阅读 · 2019年5月22日
强化学习的Unsupervised Meta-Learning
CreateAMind
17+阅读 · 2019年1月7日
Unsupervised Learning via Meta-Learning
CreateAMind
42+阅读 · 2019年1月3日
Hierarchical Disentangled Representations
CreateAMind
4+阅读 · 2018年4月15日
条件GAN重大改进!cGANs with Projection Discriminator
CreateAMind
8+阅读 · 2018年2月7日
Auto-Encoding GAN
CreateAMind
7+阅读 · 2017年8月4日
GAN猫的脸
机械鸡
11+阅读 · 2017年7月8日
Top
微信扫码咨询专知VIP会员