Modelling of the hot deformation behaviour of a titanium alloy using constitutive equations and artificial neural network

Hot deformation characteristics of a Ti600 titanium alloy were investigated by a Gleeble 1500D thermo-mechanical test simulator over the temperature range from 760 to 920 °C and strain rate range from 0.01 to 10 s−1. The flow behaviour and microstructural evolution were studied. Dynamic recrystallisation (DRX) grains exhibit different shapes at different deformation temperatures, and more severe distortion around the DRX grains exists in the matrix deformed at low temperature compared with that at relatively high temperature. Phenomenological and empirical constitutive equations were established based on the hyperbolic sine Arrhenius-type model and the multiple-linear regression, respectively. An artificial neural network (ANN) model was developed to predict the flow stress. A comparative study was made on the capability of the developed models to represent the hot deformation behaviour of this alloy. The results indicate that the flow stress of Ti600 alloy is sensitively dependent on the strain rate and deformation temperature. The multiple-linear model shows a higher accuracy in tracking the flow behaviour of Ti600 alloy than the Arrhenius-type model. The ANN model is much more efficient and has higher accuracy in predicting the hot deformation flow behaviour of Ti600 alloy than both the Arrhenius-type and multiple-linear models.