BPANN modified constitutive descriptions for flow behavior and softening mechanism in the α+β phase region of Ti-55511 alloy with equiaxed microstructure

Abstract

The deformation behavior of Ti-55511 alloy was investigated by hot compression tests conducted at deformation temperatures of 993∼1113 K and strain rates of 0.001–1 s−1. To eliminate the effects of friction and adiabatic temperature rise on the flow stresses, the flow curves were corrected. Subsequently, a strain compensated Arrhenius (SCA) model was developed and further modified using the back propagation artificial neural network (BPANN) method. The modified model exhibits significant improvements compared to the SCA model. The average absolute relative error (AARE) decreases from 4.895 % to 0.756 %, while the relative error (δ) range decreases from −14.75 %–17.99 % to −4.78 %–8.01 %. Moreover, cross-validation also confirms the modified model has higher generalization ability and prediction accuracy than the SCA model. Microstructural characterization reveals dynamic recrystallization (DRX) of the α phase and dynamic recovery (DRV) of the β phase are the main mechanisms responsible for softening, and their volume fractions increase with decreasing strain rate and increasing deformation temperature. The equiaxed α phase undergoes elongation first, followed by gradual migration and transformation of grain boundaries. Finally, the β phase wedges into the α phase until the α phase separates. The continuous dynamic recrystallization (CDRX) of β phase accompanies its DRV, which is mainly characterised by progressive sub-grain rotation. The α grains aggregated by dislocations promote CDRX of the β phase.

Keywords

• Ti-55511 alloy
• Constitutive model
• Dynamic recovery
• Dynamic recrystallization
• Back propagation artificial neural network