A collinear-spin machine learned interatomic potential for Fe${}_7$Cr${}_2$Ni alloy

Abstract

We have developed a new machine learned interatomic potential for the prototypical austenitic steel Fe${}_7$Cr${}_2$Ni, using the Gaussian approximation potential (GAP) framework. This new GAP can model the alloy's properties with close to density functional theory (DFT) accuracy, while at the same time allowing us to access larger length and time scales than expensive first-principles methods. We also extended the GAP input descriptors to approximate the effects of collinear spins (Spin GAP), and demonstrate how this extended model successfully predicts structural distortions due to antiferromagnetic and paramagnetic spin states. We demonstrate the application of the Spin GAP model for bulk properties and vacancies and validate against DFT. These results are a step towards modelling the atomistic origins of ageing in austenitic steels with higher accuracy.

References in corpus (6)

• Machine-learning based interatomic potential for amorphous carbon
• Tensor-reduced atomic density representations
• Short-range order and compositional phase stability in refractory high-entropy alloys via first principles theory and atomistic modelling: NbMoTa, NbMoTaW and VNbMoTaW
• Interplay between magnetism and short-range order in medium- and high-entropy alloys: CrCoNi, CrFeCoNi, and CrMnFeCoNi
• Development of a Plasticity-oriented Interatomic Potential for CrFeMnNi High Entropy Alloys
• Compositional phase stability in medium-entropy and high-entropy Cantor-Wu alloys from an ab initio all-electron, Landau-type theory and atomistic modelling

Cited by in corpus (6)

• Structure, short-range order, and phase stability of the Al${}_x$CrFeCoNi high-entropy alloy: Insights from a perturbative, DFT-based analysis
• Competition between phase ordering and phase segregation in the Ti${}_x$NbMoTaW and Ti${}_x$VNbMoTaW refractory high-entropy alloys
• BraWl: Simulating the thermodynamics and phase stability of multicomponent alloys using conventional and enhanced sampling techniques
• Radiation damage and phase stability of Al${}_x$CrCuFeNi${}_y$ alloys using a machine-learned interatomic potential
• Active learning potentials for first-principles phase diagrams using replica-exchange nested sampling
• Lattice vacancy migration barriers in Fe-Ni alloys, and why Ni atoms diffuse slowly: An ab initio study