Study on Ductility of Ti Aluminides Using Mamdani Fuzzy Inference System

Application of Ti aluminide is limited due to its poor ductility at room temperature. Over the last two decades several studies have been conducted and large amount of data have been generated. These data have been utilized in the present work to obtain optimized set of parameters through Mamdani fuzzy inference system. Ductility database were prepared and three parameters viz, alloy type, grain size and heat treatment cycle were selected for modeling. Additionally, ductility data were generated from literature for training and validation of models on the basis of linearity and considering the primary effect of these three parameters. All the data have been used to frame the fuzzy rules with its membership values. Performance of the models was evaluated, which shows model has better agreement with the data generated from observed data. Possibility of improving ductility more than 5% is observed for multicomponent alloy with grain size of 10-50 mu m using a multistep heat treatment cycle.