Prediction of the mechanical properties of forged Ti–10V–2Fe–3Al titanium alloy using FNN

In this paper, a fuzzy neural network (FNN) prediction model has been employed to establish the relationship between processing parameters and mechanical properties of Ti–10V–2Fe–3Al titanium alloy. In establishing these relationships, deformation temperature, degree of deformation, solution temperature and aging temperature are entered as input variables while the ultimate tensile strength, yield strength, elongation and area reduction are used as outputs, respectively. After the training process of the network, the accuracy of fuzzy model was tested by the test samples and compared with regression method. The obtained results with fuzzy neural network show that the predicted results are much better agreement with the experimental results than regression method and the maximum relative error is less than 7%. And the optimum matching processing parameters can be quickly selected to achieve the desired mechanical property based on the fuzzy model. It proved that the model has a good precision and excellent ability of predicting.

Research highlights
► A novel method was developed to predict mechanical property.
► Solution temperature has a significant influence on the mechanical property.
► σb and σ0.2 exhibit a decline trend with the increasing of aging temperature.
► Predicted results are much better agreement with the experimental results.