Modelling tensile properties of gamma-based titanium aluminides using artificial neural network

A model was developed for the prediction of the correlation between alloy composition and microstructure and its tensile properties in gamma-based titanium aluminide alloys through the use of artificial neural network (ANN). The inputs of the neural network were alloy composition, microstructure type and work (test) temperature. The outputs of the model were four important tensile properties: ultimate strength, elongation, reduction of area, and elastic modulus. The model was based on feed-forward neural networks, trained with data collected from various sources of literature. A good performance of the network was achieved, and some explanation of the predicted outputs from a metallurgical point of view was offered. The model can be used for prediction of tensile properties of gamma-based titanium aluminides at various working temperatures. It can also be used to optimise processing parameters to obtain desirable tensile properties. A graphical user interface (GUI) was developed for easy use of the model.