Loading...

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

Shafyei, A ; Sharif University of Technology | 2006

441 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.msea.2006.05.150
  3. Publisher: 2006
  4. Abstract:
  5. 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. © 2006 Elsevier B.V. All rights reserved
  6. Keywords:
  7. Alloying elements ; Composition ; Forecasting ; Mathematical models ; Metal castings ; Neural networks ; Porosity ; Sensitivity analysis ; Casting alloy ; Cooling rate ; Grain refiner ; Modifier ; Aluminum alloys ; Sensitivity analysis
  8. Source: Materials Science and Engineering A ; Volume 431, Issue 1-2 , 2006 , Pages 206-210 ; 09215093 (ISSN)
  9. URL: https://www.sciencedirect.com/science/article/abs/pii/S0921509306010100