R. Chedid et N. Najjar, AUTOMATIC FINITE-ELEMENT MESH GENERATION USING ARTIFICIAL NEURAL NETWORKS .1. PREDICTION OF MESH DENSITY, IEEE transactions on magnetics, 32(5), 1996, pp. 5173-5178
One of the inconveniences associated with the existing finite-element
packages is the need for an educated user to develop a correct mesh at
the preprocessing level. Procedures which start with a coarse mesh an
d attempt serious refinements, as is the case in most adaptive finite-
element packages, are time consuming and costly, Hence, it is very imp
ortant to develop a tool that can provide a mesh that either leads imm
ediately to an acceptable solution, or would require fewer correcting
steps to achieve better results, In this paper, we present a technique
for automatic mesh generation based on artificial neural networks (AN
N). The essence of this technique is to predict the mesh density distr
ibution of a given model, and then supply this information to a Kohone
n neural network ,which provides the final mesh. Prediction of mesh de
nsity is accomplished by a simple feedforward neural network which has
the ability to learn the relationship between mesh density and model
geometric features, It will be shown that ANN are able to recognize de
licate areas where a sharp variation of the magnetic field is expected
, Examples of 2-D models are provided to illustrate the usefulness of
the proposed technique.