Application of multilayer perceptron neural networks for predicting the permeability tensor components of thin ferrite films

¹ Laboratoire des matériaux diélectriques, Université Amar Telidji-Laghouat, Algeria
² DIOM, Université de Lyon, 42023 Saint-Étienne, France
³ Laboratoire d’Instrumentation Scientifique (LIS), Département d’Électronique, Faculté des Sciences de l’Ingénieur, Université Ferhat ABBAS, 1900 Sétif, Algeria

^a e-mail: f.djerfaf@mail.lagh-univ.dz
^b e-mail: vincentd@univ-st-etienne.fr

Received: 6 December 2010
Revised: 6 April 2011
Accepted: 7 July 2011
Published online: 14 November 2011

Abstract

A novel characterization method using artificial neural networks is presented. This method allows one to determine the intrinsic permeability tensor of ferrite thin-films from S-parameters measurements. Neural networks, efficient to solve inverse problems, are used to compute the permeability tensor components μ and k. This optimization technique is used to find extremely complex functions between inputs and outputs and can be successfully applied on our magnetic thin-film characterization problem. Results of our networks are compared to a theoretical model. A great number of both simulated and measured tests have been performed on many magnetic thin-films. Neural network processing leads to a rapid and robust method for predicting the magnetic characterization of thin-films in microwave range.