arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.11298cs.LG
收藏

探索用于高分辨率流场恢复的物理潜在空间

Exploring Physical Latent Spaces for High-Resolution Flow Restoration

LTCI, Télécom Paris, Institut Polytechnique de Paris(巴黎理工学院巴黎电信学院LTCI);Technical University of Munich(慕尼黑工业大学)

Chloe Paliard, Nils Thuerey, Kiwon Um

AI总结:

本文提出将PDE物理模拟自由度作为神经网络可自主修改的约简潜在空间,用于高分辨率流场恢复,并在多种流体场景中验证其性能提升。

摘要:

我们探索将深度神经网络模型与通过偏微分方程(PDE)进行的物理模拟相结合进行训练,使用模拟自由度作为神经网络的潜在空间。与以往工作不同,本文将模拟空间的自由度纯粹视为神经网络可使用的工具。我们针对学习约简表示展示了这一概念,因为使用传统约简表示在长时间跨度内忠实保留正确解极具挑战性,尤其是对于包含大量小尺度特征的解。本工作专注于将这种物理的、约简的潜在空间用于精细模拟的恢复,方法是训练模型,使其能够根据需要尽可能修改约简物理状态的内容,以最佳满足学习目标。这种自主性使神经网络能够发现替代动力学,从而显著提升给定任务中的性能。我们针对从不同湍流场景到上升烟羽的多种流体流动展示了这一概念。

英文摘要:

We explore training deep neural network models in conjunction with physics simulations via partial differential equations (PDEs), using the simulated degrees of freedom as latent space for a neural network. In contrast to previous work, this paper treats the degrees of freedom of the simulated space purely as tools to be used by the neural network. We demonstrate this concept for learning reduced representations, as it is extremely challenging to faithfully preserve correct solutions over long time-spans with traditional reduced representations, particularly for solutions with large amounts of small scale features. This work focuses on the use of such physical, reduced latent space for the restoration of fine simulations, by training models that can modify the content of the reduced physical states as much as needed to best satisfy the learning objective. This autonomy allows the neural networks to discover alternate dynamics that significantly improve the performance in the given tasks. We demonstrate this concept for various fluid flows ranging from different turbulence scenarios to rising smoke plumes.

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。

↑