A Pliant Method for Anisotropic Mesh Generation
A Pliant Method for Anisotropic Mesh Generation
复制标题
DOI：
--
复制
发表时间：
1996
期刊：
影响因子：
--
通讯作者：
F. Bossen;Paul S. Heckbert
中科院分区：
文献类型：
--
作者：
F. Bossen;Paul S. Heckbert
.提出了一种新的生成二维各向异性非结构三角形网格的算法。该算法的输入是边界几何形状和一个度量，该度量将所需的元素大小和形状指定为位置的函数。该算法是我们所说的受范网格生成的一个例子。它首先构造域的约束Delaunay三角剖分，然后迭代地平滑，内斯和重新三角化。在每次迭代中，随机选择一个节点，根据与邻居的吸引/排斥重新定位它，重新划分邻居，并根据需要插入或删除节点。所有操作都是相对于度量张量进行的。这种简单的方法生成高质量的网格，其元素符合要求的形状度量。该方法似乎特别适合于表面网格和粘性湍流模拟，拉伸三角形是可取的，并随时间变化的重新网格化问题。
. A new algorithm for the generation of anisotropic, unstructured triangular meshes in two dimensions is described. Inputs to the algorithm are the boundary geometry and a metric that specifies the desired element size and shape as a function of position. The algorithm is an example of what we call pliant mesh generation . It first con-structs the constrained Delaunay triangulation of the domain, then iteratively smooths, refines, and retriangulates. On each iteration, a node is selected at random, it is repositioned according to attraction/repulsion with its neighbors, the neighborhood is retriangulated, and nodes are inserted or deleted as necessary. All operations are done relative to the metric tensor. This simple method generates high quality meshes whose elements conform well to the requested shape metric. The method appears particularly well suited to surface meshing and viscous flow simulations, where stretched triangles are desirable, and to time-dependent remeshing problems.