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.
Dmsh: A Multi-Agent Reinforcement Learning Framework for All-Quad Mesh Generation
Department of Mechanical Engineering, Indian Institute of Technology Madras(印度理工学院马德拉斯分校机械工程系);Institute of Continuum Mechanics, Leibniz Universität Hannover(莱比锡大学汉诺威连续力学研究所);Institute of Structural Mechanics, Bauhaus-Universität Weimar(魏玛包豪斯大学结构力学研究所);Department of Civil and Systems Engineering, Johns Hopkins University(约翰霍普金斯大学土木与系统工程系)
Stochastic domain decomposition for time dependent adaptive mesh generation
Department of Mathematics and Statistics, Memorial University of Newfoundland(纽芬兰纪念大学数学与统计系);Department of Mathematics, University of British Columbia(不列颠哥伦比亚大学数学系);Department of Engineering Design and Mathematics, University of Western England(西英格兰大学工程设计与数学系)
Automatic feature-preserving size field for 3D mesh generation
本文提出了一种方法,旨在大大减轻高质量的网格生成复杂的三维域。我们表明,整个网格生成过程可以控制,只有五个参数,以生成在一个中风的质量网格的任意几何形状。其主要思想是建立一个网格字段$h(x)$考虑局部特征的几何形状,如曲率,考虑。然后将网格信息从表面传播到体积中,确保始终控制$\vert \nabla h \vert$的大小,以便获得平滑分级的网格。由于网格尺寸字段存储在独立的八叉树数据结构中,因此可以单独计算函数h,然后将其插入任何能够遵守规定网格尺寸字段的网格生成器中。整个过程是自动的,在这个意义上,需要与用户的最小交互。应用实例的基础上采取的模型从非常大的ABC数据集,然后提出,所有处理相同的脱殊集的参数值,以证明该技术的效率和通用性。
Maximal Poisson-disk Sampling for Variable Resolution Conforming Delaunay Mesh Generation: Applications for Three-Dimensional Discrete Fracture Networks and the Surrounding Volume
An arbitrarily high order unfitted finite element method for elliptic interface problems with automatic mesh generation, Part II. Piecewise-smooth interfaces
An efficient and stable diffusion generated method for quadrilateral mesh generation in general domains
The Hong Kong Polytechnic University(香港理工大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Shenzhen Research Institute of Big Data(深圳大数据研究院)