ARTIFICIAL NEURAL NETWORK (ANN) APPROACH TO PREDICTION OF DIFFUSION BONDING BEHAVIOR (SHEAR STRENGTH) OF SiCP  REINFORCED ALUMINUM  METAL MATRIX COMPOSITES

Mustafa Taskin  Uğur Caligulu  Halil DIKBAS

Makale detayları

ARTIFICIAL NEURAL NETWORK (ANN) APPROACH TO PREDICTION OF DIFFUSION BONDING BEHAVIOR (SHEAR STRENGTH) OF SiCP REINFORCED ALUMINUM METAL MATRIX COMPOSITES

Yazarlar:

Mustafa Taskin Uğur Caligulu Halil DIKBAS

Yayıncı:

Yasar University

Dergi:

Journal of Yaşar University 2008 Vol.3 Issue 12, pp.1811-1825

Belge Tipi:

Makale

Yayın Tarihi:

5/2008

Belge Dili:

Türkçe

Document ID (Org No.):

2000692309

Sıklık:

Aylık

pISSN:

1305-970X

Özet:

 

In this study, Artificial Neural Network approach to prediction of diffusion bonding behavior of SiCP reinforced aluminum alloy metal matrix composites, manufactured by powder metallurgy process, were obtained using a back-propagation neural network that uses gradient descent learning algorithm. A powder Al-Mg-Si matrix was employed with particulate SiC at 5-10-20 (wt) % fractions. MMC’s were fabricated by powder mixing and hot pressing at 600ºC below liquation temperature. Diffusion bonding was carried out under protective atmosphere (argon) at 550, 575, 600 and 625ºC process temperatures for 20, 40 and 60 minutes with a load of 0.25 MPa, below those which would cause macrodeformation. Microstructure examination at bond interface were investigated by optical microscopy, SEM. Specimens were tested for shear strength and metallographic evaluations. After the completion of experimental process and relevant test, to prepare the training and test (checking) set of the network, results were recorded in a file on a computer. In neural networks training module, different SiC reinforcement fractions (wt), different temperatures and welding periods were used as input, shear strength of bonded specimens at interface were used as outputs. Then, the neural network was trained using the prepared training set (also known as learning set). At the end of the training process, the test data were used to check the system accuracy. As a result the neural network was found successful in the prediction of diffusion bonding shear strength and behavior.

Makale detayları

ARTIFICIAL NEURAL NETWORK (ANN) APPROACH TO PREDICTION OF DIFFUSION BONDING BEHAVIOR (SHEAR STRENGTH) OF SiCP REINFORCED ALUMINUM METAL MATRIX COMPOSITES

Yazarlar: Mustafa Taskin Uğur Caligulu Halil DIKBAS

Yayıncı: Yasar University

Dergi: Journal of Yaşar University 2008 Vol.3 Issue 12, pp.1811-1825

Belge Tipi: Makale

Yayın Tarihi: 5/2008

Belge Dili: Türkçe

Document ID (Org No.): 2000692309

Sıklık: Aylık

pISSN: 1305-970X

Sayı

Yazarlar:

Mustafa Taskin Uğur Caligulu Halil DIKBAS

Yayıncı:

Yasar University

Dergi:

Journal of Yaşar University 2008 Vol.3 Issue 12, pp.1811-1825

Belge Tipi:

Makale

Yayın Tarihi:

5/2008

Belge Dili:

Türkçe

Document ID (Org No.):

2000692309

Sıklık:

Aylık

pISSN:

1305-970X