arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.04757cs.CEcs.LG
收藏

Airfoil GAN:面向气动外形优化的翼型编码与合成

Airfoil GAN: Encoding and Synthesizing Airfoils for Aerodynamic Shape Optimization

Carnegie Mellon University(卡内基梅隆大学)

Yuyang Wang, Kenji Shimada, Amir Barati Farimani

AI总结:

本文提出基于VAEGAN的数据驱动翼型编码与生成方法,在隐空间学习外形表示并通过遗传算法优化,无需预定义参数即可合成具有目标气动性能的新翼型。

摘要:

当前气动外形(如翼型)的设计依赖计算密集型仿真来探索可能的设计空间。通常,这类设计依赖于设计参数的预先定义,并对合成新颖外形施加了限制。在本工作中,我们提出了一种数据驱动的外形编码与生成方法,该方法自动从现有翼型中学习表示,并利用学习到的表示生成新的翼型。随后,这些表示被用于基于气动性能的合成翼型外形优化。我们的模型构建于VAEGAN之上,VAEGAN是一种将变分自编码器(Variational Autoencoder)与生成对抗网络(Generative Adversarial Network)相结合的神经网络,并通过基于梯度的技术进行训练。我们的模型能够:(1)将现有翼型编码为隐向量,并从该隐向量重建翼型;(2)通过随机采样隐向量并将向量映射到翼型坐标域来生成新颖翼型;(3)通过遗传算法优化学习到的特征,合成具有期望气动特性的翼型。我们的实验表明,学习到的特征在无需预定义设计参数的情况下,能够彻底且全面地编码外形信息。通过对特征向量进行插值/外推或从高斯噪声中采样,模型能够自动合成新颖的翼型外形,其中一些翼型与用于模型训练的翼型相比,具有相当甚至更优的气动性能。通过遗传算法在学习到的隐域上优化外形,合成翼型能够演化至目标气动特性。这展示了一个高效的基于学习的翼型设计框架,该框架在隐域上编码和优化翼型,并为所需气动性能合成有前景的翼型候选。

英文摘要:

The current design of aerodynamic shapes, like airfoils, involves computationally intensive simulations to explore the possible design space. Usually, such design relies on the prior definition of design parameters and places restrictions on synthesizing novel shapes. In this work, we propose a data-driven shape encoding and generating method, which automatically learns representations from existing airfoils and uses the learned representations to generate new airfoils. The representations are then used in the optimization of synthesized airfoil shapes based on their aerodynamic performance. Our model is built upon VAEGAN, a neural network that combines Variational Autoencoder with Generative Adversarial Network and is trained by the gradient-based technique. Our model can (1) encode the existing airfoil into a latent vector and reconstruct the airfoil from that, (2) generate novel airfoils by randomly sampling the latent vectors and mapping the vectors to the airfoil coordinate domain, and (3) synthesize airfoils with desired aerodynamic properties by optimizing learned features via a genetic algorithm. Our experiments show that the learned features encode shape information thoroughly and comprehensively without predefined design parameters. By interpolating/extrapolating feature vectors or sampling from Gaussian noises, the model can automatically synthesize novel airfoil shapes, some of which possess competitive or even better aerodynamic properties comparing to airfoils used for model training purposes. By optimizing shapes on the learned latent domain via a genetic algorithm, synthesized airfoils can evolve to target aerodynamic properties. This demonstrates an efficient learning-based airfoil design framework, which encodes and optimizes the airfoil on the latent domain and synthesizes promising airfoil candidates for required aerodynamic performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑