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 2004.07016math.NAcs.GRcs.LGcs.NA
收藏

MeshingNet:一种基于深度学习的网格生成新方法

MeshingNet: A New Mesh Generation Method based on Deep Learning

University of Leeds(利兹大学)

Zheyan Zhang, Yongxing Wang, Peter K. Jimack, He Wang

摘要:

我们介绍了一种新的方法来自动非结构化网格生成使用机器学习预测一个最佳的有限元网格以前看不见的问题。我们开发的框架是基于训练人工神经网络(ANN)来指导标准网格生成软件,基于对整个域所需的局部网格密度的预测。我们描述的训练制度,建议,使用\emph{a posteriori}误差估计的基础上,并讨论我们所考虑的人工神经网络的拓扑结构。然后,我们说明性能使用两个标准的测试问题,一个单一的椭圆偏微分方程(PDE)和一个系统的偏微分方程与线性弹性。我们证明了高质量的网格的任意多边形的几何形状和一系列的材料参数,使用各种用户选择的误差规范的有效生成。

英文摘要:

We introduce a novel approach to automatic unstructured mesh generation using machine learning to predict an optimal finite element mesh for a previously unseen problem. The framework that we have developed is based around training an artificial neural network (ANN) to guide standard mesh generation software, based upon a prediction of the required local mesh density throughout the domain. We describe the training regime that is proposed, based upon the use of \emph{a posteriori} error estimation, and discuss the topologies of the ANNs that we have considered. We then illustrate performance using two standard test problems, a single elliptic partial differential equation (PDE) and a system of PDEs associated with linear elasticity. We demonstrate the effective generation of high quality meshes for arbitrary polygonal geometries and a range of material parameters, using a variety of user-selected error norms.

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。

↑