Prediction of porosity percent in Al–Si casting alloys using ANN

Abstract In this investigation a theoretical model based on artificial neural network (ANN) has been developed to predict porosity percent and correlate the chemical composition and cooling rate to the amount of porosity in Al–Si casting alloys. In addition, the sensivity analysis was performed to investigate the importance of the effects of different alloying elements, composition, grain refiner, modifier and cooling rate on porosity formation behavior of Al–Si casting alloys. By comparing the predicted values with the experimental data, it is demonstrated that the well-trained feed forward back propagation ANN model with eight nodes in hidden layer is a powerful tool for prediction of porosity percent in Al–Si casting alloys.

[1]  F. H. Samuel,et al.  Porosity formation in AI-9 Wt Pct Si-3 Wt Pct Cu alloy systems: Metallographic observations , 1996 .

[2]  Zhongya Zhang,et al.  Artificial neural networks applied to polymer composites: a review , 2003 .

[3]  Q. Z. Zhang,et al.  Heat treatment optimization for 7175 aluminum alloy by genetic algorithm , 2001 .

[4]  H. M. Hosseini,et al.  EFFECTIVE PARAMETERS MODELING IN COMPRESSION OF AN AUSTENITIC STAINLESS STEEL USING ARTIFICIAL NEURAL NETWORK , 2005 .

[5]  H. K. D. H. Bhadeshia,et al.  Neural Networks in Materials Science , 1999 .

[6]  J. A. Taylor.  Metal-related castability effects in aluminium foundry alloys , 1996 .

[7]  M. Makhlouf,et al.  Effect of key alloying elements on the feeding characteristics of aluminum–silicon casting alloys , 2001 .

[8]  A. Muc,et al.  Genetic algorithms and finite element analysis in optimization of composite structures , 2001 .

[9]  A. Bahrami,et al.  A new method in prediction of TCP phases formation in superalloys , 2005 .

[10]  A. Samuel,et al.  Influence of casting and heat treatment parameters in controlling the properties of an Al-10 wt% Si-0.6 wt% Mg/SiC/20p composite , 1994, Journal of Materials Science.

[11]  H. K. D. H. Bhadeshia,et al.  Estimation of the amount of retained austenite in austempered ductile irons using neural networks , 2001 .

[12]  Ren-Guo Song,et al.  The application of artificial neural networks to the investigation of aging dynamics in 7175 aluminium alloys , 1995 .

[13]  A. Samuel,et al.  Various aspects involved in the production of low-hydrogen aluminium castings , 1992 .

[14]  A. Bahrami,et al.  Prediction of mechanical properties of DP steels using neural network model , 2005 .

[15]  G. B. Schaffer,et al.  The role of iron in the formation of porosity in Al-Si-Cu-based casting alloys: Part I. Initial experimental observations , 1999 .