Artificial Neural Network Approach for Prediction of Titanium Alloy Stress-Strain Curve

Abstract

In this study, Artificial Neural Network (ANN) approach to predict the stress-strain curve of titanium alloy (Ti-10V-4.5Fe-3Al) was obtained by using layer recurrent neural network that uses Levenberg Marquardt algorithm. In artificial neural network training module volume fraction of α and strain were employed as input and stress as output. ANN system was trained with different number of hidden layers and neurons using the prepared training set. After training process, the test data were used to check system accuracy. As a result the neural network 2-11-1 was found successful for the prediction of stress-strain curve of the titanium alloy.