Title :
Determining an approximate finite element mesh density using neural network techniques
Author :
Dyck, D.N. ; Lowther, D.A. ; McFee, S.
Author_Institution :
Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
fDate :
3/1/1992 12:00:00 AM
Abstract :
A system is presented which uses a neural network to predetermine the mesh density for modeling a magnetic device with finite elements. The system `learns´ how to mesh from examples of ideal meshes. Once trained, the system computes the mesh density given the geometric and material descriptions of a device. A mesh based on this density information can be used as the initial mesh for an adaptive solver
Keywords :
finite element analysis; magnetic devices; neural nets; adaptive solver; density information; finite element mesh density; ideal meshes; magnetic device; material descriptions; neural network techniques; Computer networks; Feature extraction; Finite element methods; Humans; Iron; Magnetic analysis; Magnetic devices; Magnetic materials; Neural networks; Packaging;
Journal_Title :
Magnetics, IEEE Transactions on
