Skip to main content
QUICK REVIEW

[论文解读] Turbulence Enrichment using Physics-informed Generative Adversarial Networks

Akshay Subramaniam, Man Long Wong|arXiv (Cornell University)|Mar 4, 2020
Advanced Image Processing Techniques参考文献 27被引用 47
一句话总结

TEGAN 使用物理信息驱动的 GAN(TEResNet 和 TEGAN)对低分辨率的湍流场进行上采样,并通过强制满足支配方程来更好地恢复高频分量和流动统计量。

ABSTRACT

Generative Adversarial Networks (GANs) have been widely used for generating photo-realistic images. A variant of GANs called super-resolution GAN (SRGAN) has already been used successfully for image super-resolution where low resolution images can be upsampled to a $4 imes$ larger image that is perceptually more realistic. However, when such generative models are used for data describing physical processes, there are additional known constraints that models must satisfy including governing equations and boundary conditions. In general, these constraints may not be obeyed by the generated data. In this work, we develop physics-based methods for generative enrichment of turbulence. We incorporate a physics-informed learning approach by a modification to the loss function to minimize the residuals of the governing equations for the generated data. We have analyzed two trained physics-informed models: a supervised model based on convolutional neural networks (CNN) and a generative model based on SRGAN: Turbulence Enrichment GAN (TEGAN), and show that they both outperform simple bicubic interpolation in turbulence enrichment. We have also shown that using the physics-informed learning can also significantly improve the model's ability in generating data that satisfies the physical governing equations. Finally, we compare the enriched data from TEGAN to show that it is able to recover statistical metrics of the flow field including energy metrics and well as inter-scale energy dynamics and flow morphology.

研究动机与目标

  • 在计算资源受限的情况下,推动高保真湍流数据的高效丰富化,以获得接近 DNS 质量的统计量。
  • 开发在上采样过程中强制 Navier–Stokes 方程约束的物理信息深度学习模型。
  • 比较基于有监督 CNN 的上采样器(TEResNet)与基于 SRGAN 的上采样器(TEGAN)。
  • 展示相对于简单插值,在物理一致性和统计保真度方面的提升。

提出的方法

  • 使用基于深度残差网络的生成器,在 GAN 框架内将 16x16x16 的低分辨率湍流场上采样到 64x64x64。
  • 结合来自连续性方程残差和压力泊松方程残差的物理损失,以加强物理可实现性。
  • 将内容损失(MSE 与涡度平方)与物理损失相结合,以引导高频内容的恢复。
  • 先训练 TEResNet,然后用 TEResNet 的生成器初始化并训练 TEGAN(生成器来自 TEResNet,判别器迭代训练)。
  • 可选地考虑未来带梯度惩罚的 WGAN 以及基于物理的判别器扩展。

实验结果

研究问题

  • RQ1与无约束上采样相比,物理信息损失是否能提高生成的湍流场的物理可实现性?
  • RQ2TEResNet 和 TEGAN 在恢复高波数分量与保持湍流统计量方面的表现如何?
  • RQ3增强后的场是否比 bicubic 上采样更接近 DNS 数据在能量谱、两点相关和三阶统计量方面?
  • RQ4在训练稳定性和最终精度方面,包含连续性和压力残差的影响是什么?

主要发现

  • TEGAN 与 TEResNet 在重建小尺度特征方面优于 tricubic 插值。
  • 相较于 TEResNet,TEGAN 将物理残差降低超过 10%。
  • TEGAN 与 TEResNet 产生相似的内容损失,但 TE GAN 在物理保真度方面表现更好。
  • TEGAN 在能量谱和两点相关等方面比 TEResNet 更接近高分辨率 DNS。
  • TEGAN 更好地表示三阶速度相关和 Q–R 图,表明流动形态与能量传递表示更完善。

更好的研究,从现在开始

从论文设计到论文写作,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。