Artificial neural network modeling to effect of reinforcement properties on the physical and mechanical properties of Al2024-B4C composites produced by powder metallurgy

VAROL T., ÇANAKÇI A., ÖZŞAHİN Ş.

COMPOSITES PART B-ENGINEERING, cilt.54, ss.224-233, 2013 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 54
  • Basım Tarihi: 2013
  • Doi Numarası: 10.1016/j.compositesb.2013.05.015
  • Dergi Adı: COMPOSITES PART B-ENGINEERING
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.224-233
  • Anahtar Kelimeler: Metal matrix composites (MMCs), Mechanical properties, Computational modelling, MATRIX COMPOSITES, MILLING TIME, PREDICTION, BEHAVIOR, WEAR, MICROSTRUCTURE, TEMPERATURE, HARDNESS, TENSILE
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

In the present study artificial neural network (ANN) approach was used for the prediction of effect of physical and mechanical properties of Al2024-B4C composites produced by powder metallurgy. Effects of reinforcement size and content (wt.%) on the physical and mechanical properties of composites were determined by measuring the density, hardness and tensile strength values. Density, hardness and tensile values strength of the composites were the outputs obtained from the proposed ANN. It was found that the effect of reinforcement size and content on the homogeneous distribution of B4C particles is as important as the effect of milling time. By comparing the predicted values with the experimental data, it was demonstrated that the well-trained feed forward back propagation ANN model is a powerful tool for prediction of effect of physical and mechanical properties of composites. Crown Copyright (c) 2013 Published by Elsevier Ltd. All rights reserved.