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 and attempt serious refinements, as is the case in most adaptive finite-element packages, are time consuming and costly. Hence, it is very important to develop a tool that can provide a mesh that either leads immediately 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 (ANN). The essence of this technique is to predict the mesh density distribution of a given model, and then supply this information to a Kohonen neural network, which provides the final mesh. Prediction of mesh density 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 delicate 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.
[1]
L. Nackman,et al.
Automatic mesh generation using the symmetric axis transformation of polygonal domains
,
1992,
Proc. IEEE.
[2]
Dominique Pelletier,et al.
Adaptative remeshing for viscous incompressible flows
,
1992
.
[3]
Soo-Young Lee,et al.
A Self-Organizing Neural Network Approach for Automatic Mesh Generation
,
1990
.
[4]
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.
[5]
Lee Soo-Young,et al.
A self-organizing neural network approach for automatic mesh generation
,
1991
.
[6]
S. McFee,et al.
Determining an approximate finite element mesh density using neural network techniques
,
1992
.