Artificial neural network model for the prediction of mechanical properties of Ti-10V-2Fe-3Al titanium alloy

An artificial neural network (ANN) model is proposed to predict mechanical properties of Ti-10V-2Fe-3Al titanium alloys. The input parameters of the neural network (NN) model are deformation temperature, degree of reduction, cooling rate, solution temperature and aging temperature. The outputs of the NN model are five most important mechanical properties namely ultimate tensile strength, tensile yield strength, elongation, reduction of area, and fracture toughness. Extensive experiments for correlating forging technology to mechanical properties were conducted in Ti-10V-2Fe-3Al alloy to train the NN. Compared to the traditional regression method, the ANN model has a better compatibility and adaptability. The model can be used for the prediction of properties of Ti-10V-2Fe-3Al alloy as functions of processing parameters and heat treatment cycle. It can also be used for the optimization of the processing and heat treatment parameters.