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 2102.01010physics.flu-dyncs.LG
收藏

机器学习加速计算流体动力学

Machine learning accelerated computational fluid dynamics

Google Research(谷歌研究院);School of Engineering and Applied Sciences, Harvard University(哈佛大学工程与应用科学学院)

Dmitrii Kochkov, Jamie A. Smith, Ayya Alieva, Qing Wang, Michael P. Brenner, Stephan Hoyer

摘要:

流体的数值模拟在模拟天气、气候、空气动力学和等离子体物理等许多物理现象中起着至关重要的作用。纳维-斯托克斯方程很好地描述了流体,但是大规模求解这些方程仍然令人生畏,受限于解决最小时空特征的计算成本。这导致了准确性和易处理性之间的不利权衡。在这里,我们使用端到端深度学习来改进计算流体动力学内部的近似,以模拟二维湍流。对于湍流的直接数值模拟和大涡模拟,我们的结果与基线求解器一样精确,在每个空间维度上具有8- 10倍的精细分辨率,导致40- 80倍的计算加速。我们的方法在长时间的模拟过程中保持稳定,并推广到强制函数和雷诺数以外的流,它是训练,与黑箱机器学习方法。我们的方法阐明了科学计算如何利用机器学习和硬件加速器来改善模拟,而不会牺牲准确性或泛化能力。

英文摘要:

Numerical simulation of fluids plays an essential role in modeling many physical phenomena, such as weather, climate, aerodynamics and plasma physics. Fluids are well described by the Navier-Stokes equations, but solving these equations at scale remains daunting, limited by the computational cost of resolving the smallest spatiotemporal features. This leads to unfavorable trade-offs between accuracy and tractability. Here we use end-to-end deep learning to improve approximations inside computational fluid dynamics for modeling two-dimensional turbulent flows. For both direct numerical simulation of turbulence and large eddy simulation, our results are as accurate as baseline solvers with 8-10x finer resolution in each spatial dimension, resulting in 40-80x fold computational speedups. Our method remains stable during long simulations, and generalizes to forcing functions and Reynolds numbers outside of the flows where it is trained, in contrast to black box machine learning approaches. Our approach exemplifies how scientific computing can leverage machine learning and hardware accelerators to improve simulations without sacrificing accuracy or generalization.

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。

↑