Hot deformation characterization of Ti-Nb alloy based on GA-LSSVM and 3D processing map

Abstract The thermal compression tests of Ti–Nb alloy under T = 790–940 °C and e ˙  = 0.001–10s−1 were carried out on the thermal simulation testing machine of Gleeble-3500. The flow stress curves were obtained, and the high-temperature rheological properties of the alloy were analyzed. The 3D activation energy maps were calculated and constructed. The LSSVM model of constitutive relation was established, and the penalty coefficient γ and kernel parameter δ of the LSSVM model were optimized by the genetic algorithm (GA). The constitutive model of the alloy based on the GA-LSSVM algorithm was constructed. The predicted value of the model was also compared with the experimental data. The polar reciprocity model (PRM) and dynamic material model (DMM) were used to establish the 3D processing map of the alloy and appropriate thermal processing parameters. The results indicated that T and e ˙ have a great influence on the flow stress of Ti–Nb alloy. Ti–Nb alloy is a negative temperature-sensitive and a positive strain rate-sensitive material. The correlation coefficient (R) of the GA-LSSVM algorithm constitutive model is 0.9958. The model has high prediction accuracy and strong generalization ability, which provide a new method for establishing a high-temperature constitutive model of materials. The PRM processing map is more accurate in optimizing the processing parameters of Ti–Nb alloy than that of the DMM processing map through analyzing the 3D processing map and observing the microstructure. The instability modes in the instability region of the alloy mainly include local flow. The stability region's predominant deformation mechanism is DRX. The 870–940 °C and 0.001–0.01s−1 are the best parameters during the processing of Ti–Nb alloy.