arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.10119math.NAcs.NA
收藏

Biot系统内罚间断Galerkin法中内罚系数的机器学习选择

Choice of Interior Penalty Coefficient for Interior Penalty Discontinuous Galerkin Method for Biot's System by Employing Machine Learning

Sanghyun Lee, Teeratorn Kadeethum, Hamidreza M. Nick

摘要:

本文利用神经网络和机器学习方法研究了椭圆型问题和Biot方程组的间断Galerkin有限元法的内罚参数的最优选择问题。选择最优的内罚参数对数值离散解的稳定性、鲁棒性和效率至关重要。线性回归和非线性人工神经网络方法,并使用几个数值实验来说明我们提出的计算框架的能力进行比较。该框架是一个开发自动化数值模拟平台的组成部分,因为它可以自动识别最佳的内部罚参数。还可以实施实时反馈以实时更新和提高模型准确性。

英文摘要:

In this paper, the optimal choice of the interior penalty parameter of the discontinuous Galerkin finite element methods for both the elliptic problems and the Biot's systems are studied by utilizing the neural network and machine learning. It is crucial to choose the optimal interior penalty parameter, which is not too small or not too large for the stability, robustness, and efficiency of the numerical discretized solutions. Both linear regression and nonlinear artificial neural network methods are employed and compared using several numerical experiments to illustrate the capability of our proposed computational framework. This framework is an integral part of a developing automated numerical simulation platform because it can automatically identify the optimal interior penalty parameter. Real-time feedback could also be implemented to update and improve model accuracy on the fly.

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。

↑