Accurate Ti–Al–Nb ternary interatomic potential development using deep neural networks for TiAl PST single crystals

A deep learning-driven Ti-Al-Nb ternary interatomic potential is developed continuously through DP-GEN framework, combining first-principles accuracy with molecular dynamics scalability. The neural network potential demonstrates exceptional transferability in predicting critical properties of Nb-doped<i>γ</i>-TiAl and<i>α</i>₂-Ti₃Al phases. Nb influence on shear deformation in<i>α</i>₂-Ti₃Al is investigated. Meanwhile, Nb-doped<i>α</i>₂/<i>γ</i>interface tensile perpendicular to the interface and shear simulations along 1/2[11¯0] and 1/2[112¯] are performed in order to simulate the local configurations in Ti-Al PST single crystals. This model provides a computational framework for interfacial engineering in lamellar TiAl alloys.