Title: Employment of the artificial neural networks for prediction of magnetic properties of the metallic amorphous alloys

Authors: Jaroslaw Konieczny, Leszek A. Dobrzanski, Blazej Tomiczek

Addresses: Institute of Engineering Materials and Biomaterials, Silesian University of Technology, Konarskiego 18A Street, Gliwice, Poland. ' Institute of Engineering Materials and Biomaterials, Silesian University of Technology, Konarskiego 18A Street, Gliwice, Poland. ' Institute of Engineering Materials and Biomaterials, Silesian University of Technology, Konarskiego 18A Street, Gliwice, Poland

Abstract: The aim of this work is to employ the artificial neural networks for modelling the magnetic properties of the amorphous alloys with the iron and cobalt matrix. The artificial neural networks implemented in StatSoft Statistica Neural Network PL 4.0F were used to determine the relationship between the chemical compositions of amorphous alloys, heat treatment parameters and magnetic properties. The attempt to use the artificial neural networks for predicting the effect of the chemical composition and heat treatment parameters on the magnetic flux density BS succeeded, as the level of the obtained results was acceptable, as the level of the obtained results was acceptable. For different magnetic properties of soft magnetic materials, further calculations are planned. The results of calculation makes it possible to design new advantageous combinations of concentrations of the particular elements to develop grades of the soft magnetic alloys. This paper employs the artificial neural networks for modelling chemical composition and heat treatment parameters of amorphous soft magnetic alloys to obtain the best magnetic properties. [Received 15 August 2007; Accepted 20 October 2007]

Keywords: artificial neural networks; ANNs; amorphous alloys; nanocrystalline materials; magnetic properties; prediction; modelling; iron; cobalt; heat treatment; chemical composition; soft magnetic alloys.

DOI: 10.1504/IJCMSSE.2007.017922

International Journal of Computational Materials Science and Surface Engineering, 2007 Vol.1 No.6, pp.650 - 662

Published online: 23 Apr 2008 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article