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
Copyright © 2019 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0