%0 Journal Article 
%A Pedreño Molina, Juan Luis
%A Monzó Cabrera, Juan
%A Pinzolas Prado, Miguel
%A Requena Pérez, María Eugenia
%T A New Predictive Neural Architecture for Modelling Electric Field Patterns Within Dielectric Materials in Industrial Microwave-Heating Processes
%D 2007
%U http://hdl.handle.net/10317/1475
%X In this work, a learning architecture based on neural networks has
been employed for modelling the electric field pattern along an axis of a
multimode microwave-heating cavity that contains dielectric materials. The
multilevel configuration of this architecture, based on Radial Basis
Functions (RBF) and polynomial structures, allows the fitting of the
electric field as a function of the dielectric parameters (i.e. "    "0 ÿ j"00)
along one axis (x) of the cavity as well as inside the sample. In the learning
stage, different samples have trained the neural architecture, by means of
the mapping between ("0; "00) and the absolute value of the electric field
pattern, generated with a 2D simulation platform based on the Finite
Elements Method (FEM). The results obtained with conventional samples,
such as polyester, epoxy, silicon crystal or beef steak, show that the
proposed neural model is able to accurately predict the electric field spatial
distribution under appropriate training processes.
%K Teoría de la Señal y las Comunicaciones
%K Electric field estimation
%K Learning-based predictive system
%K Microwave-assisted applications
%K Microwave-heating oven
%K Neural network modelling
%K Estimación de campo eléctrico
%K Sistema predictivo basado en el aprendizaje
%K Aplicaciones asistidas por microondas
%K Calentamiento por horno de microondas
%K Modelos de redes neuronales
%~ GOEDOC, SUB GOETTINGEN