Modeling of Correlation between Heat Treatment and Mechanical Properties of Ti–6Al–4V Alloy Using Feed Forward Back Propagation Neural Network

Abstract

A model for predicting mechanical properties of Ti–6Al–4V alloy has been developed and the Feed Forward Back Propagation (FFBP) as one type of algorithm of the Artificial Neural Network has been applied as the prediction system. Hardness, ultimate tensile strength (UTS), yield strength (YS) and elongation that are basic mechanical properties of Ti–6AL–4V alloy are predicted as a function of heat treatment process. Other tensile testing parameter, i.e. strain rate, is also considered in the model because increase of strain rate will increase UTS and YS, but will decrease elongation. Since the FFBP is a supervised system, it requires a lot of input and output data pairs for training process. The data are acquired from literatures and preprocessed before training. Performance of the model are evaluated by the Normalized Root Mean Square Error (NRMSE) and the Coefficient Correlation (R). The NRMSE and the R values of both training and validation parts show almost excellent values. Therefore, the model using the FFBP is appropriate to predict the mechanical properties of Ti–6Al–4V alloy.