arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.06264physics.flu-dyncs.LG
收藏

利用自编码器和生成对抗网络对强迫各向同性湍流的参数化

Parameterization of Forced Isotropic Turbulent Flow using Autoencoders and Generative Adversarial Networks

Delhi Technological University(德里理工大学)

Kanishk, Tanishk Nandal, Prince Tyagi, Raj Kumar Singh

摘要:

自动编码器和生成神经网络模型最近在流体力学中得到了普及,因为它们的自发性和低处理时间,而不是高保真CFD模拟。在流体力学的应用中,通过使用编码器压缩输入的高维数据以将输入空间映射到较低维的潜在空间,自动编码器被用作模型阶次降低工具。然而,生成模型,如变分自动编码器(VAE)和生成对抗网络(GANs)被证明是有效的,在生成具有高“随机性”的混沌模型,如湍流的解决方案。在这项研究中,强制各向同性湍流流产生的参数化成一些基本的统计特性。模型根据对这些特征的依赖性对预模拟数据进行训练,然后通过改变这些参数来影响流量生成。沿着生成器模型(如解码器和生成器)推送的隐向量包含独立的条目,这些条目可用于创建具有相似属性的不同输出。使用基于神经网络的体系结构消除了对经典的基于网格的Navier-Stoke方程估计的依赖,这在许多CFD软件中是突出的。

英文摘要:

Autoencoders and generative neural network models have recently gained popularity in fluid mechanics due to their spontaneity and low processing time instead of high fidelity CFD simulations. Auto encoders are used as model order reduction tools in applications of fluid mechanics by compressing input high-dimensional data using an encoder to map the input space into a lower-dimensional latent space. Whereas, generative models such as Variational Auto-encoders (VAEs) and Generative Adversarial Networks (GANs) are proving to be effective in generating solutions to chaotic models with high 'randomness' such as turbulent flows. In this study, forced isotropic turbulence flow is generated by parameterizing into some basic statistical characteristics. The models trained on pre-simulated data from dependencies on these characteristics and the flow generation is then affected by varying these parameters. The latent vectors pushed along the generator models like the decoders and generators contain independent entries which can be used to create different outputs with similar properties. The use of neural network-based architecture removes the need for dependency on the classical mesh-based Navier-Stoke equation estimation which is prominent in many CFD softwares.

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。

↑