Microstructure evolution under thermo-mechanical operating of rocksalt- structure TiN via neural network potential

FY Guo and B Chen and QY Zeng and XX Yu and KG Chen and DD Kang and Y Du and JH Wu and JY Dai, JOURNAL OF CHEMICAL PHYSICS, 159, 204702 (2023).

DOI: 10.1063/5.0171528

In the process of high temperature service, the mechanical properties of cutting tools decrease sharply due to the peeling of the protective coating. However, the mechanism of such coating failure remains obscure due to the complicated interaction between atomic structure, temperature, and stress. This dynamic evolution nature demands both large system sizes and accurate description on the atomic scale, raising challenges for existing atomic scale calculation methods. Here, we developed a deep neural network (DNN) potential for Ti-N binary systems based on first-principles study datasets to achieve quantum-accurate large-scale atomic simulation. Compared with empirical interatomic potential based on the embedded-atom-method, the developed DNN-potential can accurately predict lattice constants, phonon properties, and mechanical properties under various thermodynamic conditions. Moreover, for the first time, we present the atomic evolution of the fracture behavior of large-scale rocksalt-structure (B1) TiN systems coupled with temperature and stress conditions. Our study validates that interatomic brittle fractures occur when TiN stretches beyond its tensile yield point. Such simulation of coating fracture and cutting behavior based on large-scale atoms can shed new light on understanding the microstructure and mechanical properties of coating tools under extreme operating conditions.

Return to Publications page