Machine learning interatomic potential reveals hydrogen embrittlement origins at general grain boundaries in α-iron

Hydrogen embrittlement accompanied by cracking along general grain boundaries (GBs), which are characterized by a lack of crystallographic symmetry, is a persistent challenge in developing high-strength structural alloys. We develop a highly accurate and transferable machine learning interatomic potential (MLIP) for Fe–H by acquiring comprehensive and efficient learning data via simultaneous learning. Our MLIP accurately describes the density functional theory results for various lattice defects in α-Fe and their interactions with hydrogen, general GBs with hydrogen segregation, and their deformation and fracture behavior. Large-scale molecular dynamics simulations reveal that hydrogen can suppress <111 > /2 full dislocation emissions from general GBs and thereby potentially promote their fracture, supporting experimental suggestions. In contrast, for general GBs, where deformation twins are responsible for plasticity, the influence of hydrogen is minimal. This study contributes to the development of high-strength alloys by providing a robust MLIP construction methodology and new insights into hydrogen embrittlement mechanisms.