Artificial Neural Network Prediction of Silicon and Nickel recovery in Al-Si-Ni alloy Manufactured by Stir Casting
Khalefa, M. (2019). Artificial Neural Network Prediction of Silicon and Nickel recovery in Al-Si-Ni alloy Manufactured by Stir Casting. EKB Journal Management System, 21(1), 1-8. doi: 10.21608/jpme.2019.13519.1003
Moatasem Khalefa. "Artificial Neural Network Prediction of Silicon and Nickel recovery in Al-Si-Ni alloy Manufactured by Stir Casting". EKB Journal Management System, 21, 1, 2019, 1-8. doi: 10.21608/jpme.2019.13519.1003
Khalefa, M. (2019). 'Artificial Neural Network Prediction of Silicon and Nickel recovery in Al-Si-Ni alloy Manufactured by Stir Casting', EKB Journal Management System, 21(1), pp. 1-8. doi: 10.21608/jpme.2019.13519.1003
Khalefa, M. Artificial Neural Network Prediction of Silicon and Nickel recovery in Al-Si-Ni alloy Manufactured by Stir Casting. EKB Journal Management System, 2019; 21(1): 1-8. doi: 10.21608/jpme.2019.13519.1003

Artificial Neural Network Prediction of Silicon and Nickel recovery in Al-Si-Ni alloy Manufactured by Stir Casting

Journal of Petroleum and Mining Engineering
Article 1, Volume 21, Issue 1, December 2019, Page 1-8  XML PDF (302.17 K)
Document Type: Original Article
DOI: 10.21608/jpme.2019.13519.1003
View on SCiNiTO View on SCiNiTO
Author
Moatasem Khalefa email
Mining and petroleum Engineering Department,Faculty of Engineering, Al-Azhar University, Qena- Egypt
Abstract
Artificial neural network (ANN) is a non-linear statistical technique that being used to describe the behaviour of the materials. Al-Si-Ni alloy was prepared by the stir casting method using different optimum parameters as reaction time, temperature, Ni2O3/Al weight ratio, and Na2SiF6/Al wt. ratio. The artificial neural network is used in predicting the silicon and nickel recovery of these prepared alloys. The obtained experimental results are used to train the artificial neural network (ANN) and the temperature, Ni2O3/Al wt. ratio, and Na2SiF6 / Al wt. ratio are used as ANN's inputs. The used ANN consists of three layers; Input layer that includes 4 neurons and the hidden layer include 9 neurons, while the output layer contains 2 neurons. The Levenberg-Marquardt (LM) is used as the training function. Optimal mean square errors (MSE) for the ANN during predicting and estimating silicon and nickel recovery equal 0.0358, 0.0034, respectively, when reaction time is the variable and other parameters are kept constant, MSE equal 1.4007e-04, 1.3478e-04 when temperature is variable and other parameters are kept constant, MSE equal 1.3839e-04, 9.9891e-05 when Ni2O3/Al wt. ratio was the variable and other parameters are kept constant and finally MSE equal 0.0287, 0.0263 when Na2SiF6/Al wt. ratio is variable and other parameters are kept constant.
Keywords
artificial neural network; MSE; stir casting, Levenberg-Marquardt; aluminum matrix
Statistics
Article View: 260
PDF Download: 217