A finite-element mesh generator based on growing neural networks

A mesh generator for the production of high-quality finite-element meshes is being proposed. The mesh generator uses an artificial neural network, which grows during the training process in order to adapt itself to a prespecified probability distribution. The initial mesh is a constrained Delaunay triangulation of the domain to be triangulated. Two new algorithms to accelerate the location of the best matching unit are introduced. The mesh generator has been found able to produce meshes of high quality in a number of classic cases examined and is highly suited for problems where the mesh density vector can be calculated in advance.

[1]  S. McFee,et al.  Determining an approximate finite element mesh density using neural network techniques , 1992 .

[2]  S. Alfonzetti,et al.  A finite element mesh generator based on an adaptive neural network , 1998 .

[3]  Soo-Young Lee,et al.  Automatic Mesh Generator Based on Self-organizing Finite-element Tessellation for Electromagnetic Field Problems , 1994 .

[4]  Dimitris P. Labridis,et al.  Electromagnetic forces in three-phase rigid busbars with rectangular cross-sections , 1996 .

[5]  D. Lindholm,et al.  Automatic triangular mesh generation on surfaces of polyhedra , 1983 .

[6]  R. Chedid,et al.  Automatic finite-element mesh generation using artificial neural networks-Part I: Prediction of mesh density , 1996 .

[7]  Dimitris P. Labridis,et al.  An automatic mesh generator for handling small features in open boundary power transmission line problems using artificial neural networks , 2000 .

[8]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

[9]  D.A. Lowther,et al.  A Density driven Mesh Generator guided by a Neural Network , 1992, Digest of the Fifth Biennial IEEE Conference on Electromagnetic Field Computation.

[10]  N. Golias,et al.  An approach to refining three‐dimensional tetrahedral meshes based on Delaunay transformations , 1994 .

[11]  Jonathan Richard Shewchuk,et al.  Triangle: Engineering a 2D Quality Mesh Generator and Delaunay Triangulator , 1996, WACG.

[12]  Theodoros D. Tsiboukis,et al.  Adaptive refinement in 2‐D finite element applications , 1991 .

[13]  Soo-Young Lee,et al.  A Self-Organizing Neural Network Approach for Automatic Mesh Generation , 1990 .

[14]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[15]  Kurt Mehlhorn,et al.  Algorithm Design and Software Libraries: Recent Developments in the LEDA Project , 1992, IFIP Congress.

[16]  Z. J. Cendes,et al.  Adaptive mesh refinement in the finite element computation of magnetic fields , 1985 .

[17]  Salvatore Coco,et al.  Automatic mesh generation by the let-it-grow neural network , 1996 .

[18]  Theodoros D. Tsiboukis,et al.  Dual finite-element calculations for static electric and magnetic fields , 1983 .

[19]  Lee Soo-Young,et al.  A self-organizing neural network approach for automatic mesh generation , 1991 .