Title :
Neural characterization of wire bundles multiconductor transmission lines
Author :
Cannas, Barbara ; Fanni, Alessandra ; Maradei, Francescaromana
Author_Institution :
Dept. of Electr. & Electron. Eng., Cagliari Univ., Italy
fDate :
3/1/2002 12:00:00 AM
Abstract :
A neural network approach is proposed for the characterization of twisted wire bundles multiconductor transmission lines. The neural network is suitably trained with few cross section configurations to learn the behavior of the per unit length parameters of the nonuniform bundle. The procedure allows a fast characterization of the nonuniform bundles multiconductor transmission lines
Keywords :
multiconductor transmission lines; neural nets; transmission line theory; multiconductor transmission line; neural network model; nonuniform twisted wire bundle; per unit length parameters; Cable insulation; Dielectrics and electrical insulation; Electromagnetic analysis; Electromagnetic compatibility; Electromagnetic modeling; Finite element methods; Multiconductor transmission lines; Neural networks; Predictive models; Wire;
Journal_Title :
Magnetics, IEEE Transactions on
