arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.13162math.NAcs.AIcs.LGcs.NA
收藏

一种用于自适应分区的深度学习方法

A deep learning approach for adaptive zoning

Oak Ridge National Laboratory(橡树岭国家实验室);ETH Zurich(苏黎世联邦理工学院)

Massimiliano Lupo Pasini, Luka Malenica, Kwitae Chong, Stuart Slattery

摘要:

我们提出了一种有监督的深度学习(DL)方法,用于对不定常的偏微分方程进行自适应分区,该方程对可压缩介质中一维冲击波的传播进行建模。我们训练一个神经网络的数据集组成的不同的静态冲击剖面与相应的自适应网格计算与标准的自适应分区技术。我们表明,训练后的DL模型学习如何捕捉域中存在的冲击,并在每个时间步生成一个自适应的非均匀网格,重新定位网格节点,以提高Lax-Wendroff和五阶加权本质不振荡(WENO 5)空间离散格式的精度。我们还表明,代理DL模型减少了计算时间,以执行自适应分区的至少2倍的因素,相对于标准技术,而不影响的准确性重建的物理量的兴趣。

英文摘要:

We propose a supervised deep learning (DL) approach to perform adaptive zoning on time dependent partial differential equations that model the propagation of 1D shock waves in a compressible medium. We train a neural network on a dataset composed of different static shock profiles associated with the corresponding adapted meshes computed with standard adaptive zoning techniques. We show that the trained DL model learns how to capture the presence of shocks in the domain and generates at each time step an adapted non-uniform mesh that relocates the grid nodes to improve the accuracy of Lax-Wendroff and fifth order weighted essentially non-oscillatory (WENO5) space discretization schemes. We also show that the surrogate DL model reduces the computational time to perform adaptive zoning by at least a 2x factor with respect to standard techniques without compromising the accuracy of the reconstruction of the physical quantities of interest.

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。

↑