arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1707.03351math.NAcs.NA
收藏

用人工神经网络求解参数偏微分方程问题

Solving parametric PDE problems with artificial neural networks

Stanford University(斯坦福大学);Duke University(杜克大学)

Yuehaw Khoo, Jianfeng Lu, Lexing Ying

AI总结:

本文提出利用神经网络对偏微分方程中的物理量进行参数化建模,以解决高维不确定性下的计算难题,通过工程和物理中的实例验证了该方法的简洁性和准确性。

摘要:

维度灾难在数值偏微分方程(PDE)中经常出现,尤其是在需要将不确定性作为随机系数纳入方程时。然而,往往可以通过系数场空间上的几个特征来捕捉由PDE导出的物理量的变异性。基于这一观察,我们提出使用基于神经网络(NN)的方法,将感兴趣的物理量参数化为输入系数的函数。通过将神经网络视为执行时间演化以求解PDE,可以证明使用神经网络表示此类量的可行性。我们进一步通过工程和物理中的显著例子展示了该方法的简单性和准确性。

英文摘要:

The curse of dimensionality is commonly encountered in numerical partial differential equations (PDE), especially when uncertainties have to be modeled into the equations as random coefficients. However, very often the variability of physical quantities derived from a PDE can be captured by a few features on the space of the coefficient fields. Based on such an observation, we propose using a neural-network (NN) based method to parameterize the physical quantity of interest as a function of input coefficients. The representability of such quantity using a neural-network can be justified by viewing the neural-network as performing time evolution to find the solutions to the PDE. We further demonstrate the simplicity and accuracy of the approach through notable examples of PDEs in engineering and physics.

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。

↑