arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.07559physics.flu-dynnlin.CDphysics.comp-ph
收藏

用可微规划学习Turbulence的稳定Galerkin模型

Learning Stable Galerkin Models of Turbulence with Differentiable Programming

Arvind T. Mohan, Kaushik Nagarajan, Daniel Livescu

摘要:

湍流流动控制具有许多应用,并且建立流动的降阶模型(ROM)和相关联的闭环控制定律是极其具有挑战性的。尽管为湍流构建数据驱动的ROM很复杂,但深度神经网络的卓越表现能力已经证明在学习ROM方面取得了相当大的成功。然而,这些战略通常缺乏物质基础,往往缺乏可解释性。相反,基于正交分解(POD)的伽辽金投影(GP)方法由于其理论上的一致性和可解释的物理基础而在许多问题中受到欢迎。然而,一个关键的限制是,从GP ROM产生的常微分方程(ODE)是非常容易受到不稳定性,由于截断POD模式,并导致恶化的时间预测。在这项工作中,我们提出了一个\textit{differentiable programming}的方法,融合了这两种策略的优势,通过嵌入神经网络显式到GP ODE结构,称为神经Galerkin投影。本文在中等马赫数下可压缩空腔绕流的等熵纳维-斯托克斯方程上证明了这种方法。当提供投影方程的结构,我们表明,神经伽辽金方法隐式学习稳定的ODE系数POD系数,并表现出显着更长的时间和准确的时间范围预测相比,经典的POD-GP辅助校准。我们观察到,与纯粹的数据驱动神经网络相比,这种基于可区分编程的方法的主要好处包括增加基于物理的学习的灵活性,非常低的计算成本以及可解释性的显着增加。

英文摘要:

Turbulent flow control has numerous applications and building reduced-order models (ROMs) of the flow and the associated feedback control laws is extremely challenging. Despite the complexity of building data-driven ROMs for turbulence, the superior representational capacity of deep neural networks has demonstrated considerable success in learning ROMs. Nevertheless, these strategies are typically devoid of physical foundations and often lack interpretability. Conversely, the Proper Orthogonal Decomposition (POD) based Galerkin projection (GP) approach for ROM has been popular in many problems owing to its theoretically consistent and explainable physical foundations. However, a key limitation is that the ordinary differential equations (ODEs) arising from GP ROMs are highly susceptible to instabilities due to truncation of POD modes and lead to deterioration in temporal predictions. In this work, we propose a \textit{differentiable programming} approach that blends the strengths of both these strategies, by embedding neural networks explicitly into the GP ODE structure, termed Neural Galerkin projection. We demonstrate this approach on the isentropic Navier-Stokes equations for compressible flow over a cavity at a moderate Mach number. When provided the structure of the projected equations, we show that the Neural Galerkin approach implicitly learns stable ODE coefficients from POD coefficients and demonstrates significantly longer and accurate time horizon predictions, when compared to the classical POD-GP assisted by calibration. We observe that the key benefits of this differentiable programming-based approach include increased flexibility in physics-based learning, very low computational costs, and a significant increase in interpretability, when compared to purely data-driven neural networks.

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。

↑