Artificial neural network to predict the effect of heat treatment, reinforcement size, and volume fraction on AlCuMg alloy matrix composite properties fabricated by stir casting method


ÇANAKÇI A., VAROL T., ÖZŞAHİN Ş.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, cilt.78, ss.305-317, 2015 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 78
  • Basım Tarihi: 2015
  • Doi Numarası: 10.1007/s00170-014-6646-1
  • Dergi Adı: INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.305-317
  • Anahtar Kelimeler: Artificial neural network, Heat treatment, Stir casting, Mechanical properties, MECHANICAL-PROPERTIES, TENSILE PROPERTIES, MICROSTRUCTURE, PARTICLES, BEHAVIOR, SICP, B4C
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

The first goal of this study is to investigate the effect of T6 heat treatment and reinforcement properties on the mechanical properties of AlCuMg alloy matrix composites fabricated by the stir casting technique. The second goal of the study is to develop a prediction model which can predict experimental results with minimum error. For modeling and prediction of hardness, tensile strength, yield strength, and modulus of elasticity, a forward and backward feed propagation multilayer artificial neural network was developed to evaluate and compare the experimental calculated data to predict values. It was found that heat treatment and reinforcement properties have significant effects on the mechanical properties of AlCuMg alloy matrix composites. The prediction model, which has a mean absolute percentage error of approximately 2 % for the predicted values, can effectively predict the effect of the T6 heat treatment and reinforcement properties on the mechanical properties of AlCuMg alloy matrix composites.