A physics-based machine learning study of the behavior of interstitial helium in single crystal W–Mo binary alloys

Abstract

In this work, the behavior of dilute interstitial helium in W–Mo binary alloys was explored through the application of a first principles-informed neural network (NN) in order to study the early stages of helium-induced damage and inform the design of next generation materials for fusion reactors. The neural network (NN) was trained using a database of 120 density functional theory (DFT) calculations on the alloy. The DFT database of computed solution energies showed a linear dependence on the composition of the first nearest neighbor metallic shell. This NN was then employed in a kinetic Monte Carlo simulation, which took into account two pathways for helium migration, the T-T pathway (T: Tetreahedral) and the T-O-T pathway (a second order saddle in both W and Mo) (O: Octahedral). It was determined that the diffusivity of interstitial helium in W–Mo alloys can vary by several orders of magnitude depending on the composition. Moreover, T-O-T pathways were found to dominate the T-T pathways for all alloy compositions for temperatures over about 450 K. Heterogeneous structures were also examined to account for radiation-induced segregation. It was observed that diffusion was fast when W segregated to the grain interior region and Mo to the grain outer region and was slow for the reverse situation. This behavior was explained by studying the energy landscape. Finally, thermodynamic simulations indicated that Mo-rich regions of the alloy were most favorable for binding the interstitial helium and may be the sites for the nucleation of helium bubbles.