Modeling constitutive relationship of Ti17 titanium alloy with lamellar starting microstructure

The isothermal compression tests of Ti17 titanium alloy with lamellar starting microstructure were conducted on a Gleeble-1500 thermo-mechanical simulator at the deformation temperatures ranging from 780 to 860 °C with an interval of 20 °C and the strain rates of 0.001, 0.01, 0.1, 1.0 and 10.0 s−1 with the height reduction of 40 and 60%. The typical flow curves exhibit softening at all the deformation conditions, even at low strain rate (0.001 s−1), which have been considered that the flow softening results from adiabatic shear bands at high strain rates and lamellar globularization at low strain rates. On the basis of the experimental data, the artificial neural network model was proposed to develop the constitutive relationship of Ti17 alloy with lamellar starting microstructure. In the present investigation, the input parameters of ANN model are strain, strain rate and deformation temperature. The output parameter of ANN model is the flow stress. The comparison of experimental flow stresses with predicted value by ANN model and calculated value by regression model was carried out. It is found that the predicted flow stresses obtained from ANN were in a better agreement with the experimental values, indicating that it is available and novel to establish the constitutive relationship of Ti17 alloy using the technique of artificial neural network.