Journal of Engineering and Computer Innovations
Subscribe to JECI
Full Name*
Email Address*

Article Number - 301407E8279


Vol.1(1), pp. 10-17 , September 2010

ISSN: 2141-6508



Full Length Research Paper

Simulating of microstructure and magnetic properties of nanostructured Fe and Fe50Co50 powders by neural networks


Ali Heidari1*, Mehdi Delshad Chermahiniand Mohammad Heidari3




 

1Department of Civil Engineering, Shahrekord University, Shahrekord, Iran.

2Department of Material Science and Engineering, Kerman University, Kerman, Iran.

3Islamic Azad University, Aligodarz Branch, Aligodarz, Iran


Email: heidari@eng.sku.ac.ir






 Published: 30 September 2010

Copyright © 2010 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0


 

In this study, a series of experiments were performed in order to determine the effects of changing milling time on the microstructure and magnetic properties of nanostructured Fe and Fe50Co50 alloys by back propagation neural networks (BPN). The microstructure and magnetic properties of Fe and Fe50Co50 alloys were estimated using the data acquired from the experiments performed, performance values obtained were used for training a BPN whose structure was designed for this operation. The network, which has two layers as hidden layer, and output layer, has two input and five output neurons. The BPN is used for simulating the microstructure and magnetic properties of nanostructured Fe and Fe50Co50 alloys. The BPN method is found to be the most accurate and quick, the best results were obtained by the BPN by quasi-newton algorithms training with 12 neurons in the hidden layer. The quasi-newton algorithms procedure is more accurate and requires significantly less computation time than the other methods. Training was continued until the mean square error is less than 1e-3, desired error value was achieved in the BPN was tested with both data used and not used for training the network. Resultant of the test indicates the usability of the BPN in this area.

 

Key words: Nanostructured materials, mchanical alloying, microstructure, magnetic measurements, computer simulation


APA (2010). Simulating of microstructure and magnetic properties of nanostructured Fe and Fe50Co50 powders by neural networks. Journal of Engineering and Computer Innovations, 1(1), 10-17.
Chicago Ali Heidari, Mehdi Delshad Chermahini and Mohammad Heidari. "Simulating of microstructure and magnetic properties of nanostructured Fe and Fe50Co50 powders by neural networks." Journal of Engineering and Computer Innovations 1, no. 1 (2010): 10-17.
MLA Ali Heidari, Mehdi Delshad Chermahini and Mohammad Heidari. "Simulating of microstructure and magnetic properties of nanostructured Fe and Fe50Co50 powders by neural networks." Journal of Engineering and Computer Innovations 1.1 (2010): 10-17.
   
DOI
URL http://academicjournals.org/journal/JECI/article-abstract/301407E8279

Subscription Form