Learning grain boundary segregation energy spectra in polycrystals

Abstract

The segregation of solute atoms at grain boundaries (GBs) can profoundly impact the structural properties of metallic alloys, and induce effects that range from strengthening to embrittlement. And, though known to be anisotropic, there is a limited understanding of the variation of solute segregation tendencies across the full, multidimensional GB space, which is critically important in polycrystals where much of that space is represented. Here we develop a machine learning framework that can accurately predict the segregation tendency—quantified by the segregation enthalpy spectrum—of solute atoms at GB sites in polycrystals, based solely on the undecorated (pre-segregation) local atomic environment of such sites. We proceed to use the learning framework to scan across the alloy space, and build an extensive database of segregation energy spectra for more than 250 metal-based binary alloys. The resulting machine learning models and segregation database are key to unlocking the full potential of GB segregation as an alloy design tool, and enable the design of microstructures that maximize the useful impacts of segregation.

Atomistic and machine learning studies of solute segregation in metastable grain boundaries

“…While many experimental and computational studies explored GB solute segregation in a wide range of metallic alloys, the role of GB metastable structures in solute segregation remains poorly understood. Recently, researchers have employed ML techniques to examine GB properties 63 – 65 . Huber et al 63 performed a high-throughput computational study of the segregation of six elemental species to various GB types.…”

“…A linear model was developed relating the GB segregation energy to the excess volume and change in coordination number. The study by Wagih et al 65 extracted structural features from atomistic simulations of GB segregation in a polycrystalline ensemble of a wide range of alloys by fitting radial basis functions and spherical harmonics to particle densities. The data was then used to construct a linear regression model of the GB segregation energy.…”

Atomistic Assessment of Solute-Solute Interactions during Grain Boundary Segregation

“…Assuming a McLean-type contribution from each site type with dilute limit segregation energy , and accounting for the mixture rule of Equation (5), Wagih and Schuh’s spectral isotherm is given as an integral over segregation energies [ 43 ]: where is the density of sites of type , and was shown by Wagih and Schuh to follow a roughly skew-normal distribution for general polycrystals: where , , and are the fitted shape, location, and breadth of the dilute limit segregation energy distribution, respectively. The values of these parameters for several hundred binary alloys have been presented in reference [ 53 ].…”

Machine‐learning‐based interatomic potentials for advanced manufacturing

“…71 The ML framework is applied to predict the segregation energy of more than 250 metal-based binary alloys. 72 Deep potential generators (DP-GENs) can produce potential energy surface (PES) models in Mg, Al, and Mg-Al alloys. 73 The potential generated by the NN-ML approach of the Pd-Si system can describe both liquid and crystal structures.…”

“…It has been reported that linearized pairwise and angular‐dependent MLIPs are robustness for 31 elemental metals, and angular‐dependent descriptors are important for transition metals 71 . The ML framework is applied to predict the segregation energy of more than 250 metal‐based binary alloys 72 …”