Accession Number:

AD1087034

Title:

Machine Learning for Predicting Properties of Silicon Carbide Grain Boundaries

Descriptive Note:

Technical Report,01 May 2019,30 Sep 2019

Corporate Author:

US Army Combat Capabilities and Development Command, Army Research Laboratory Aberdeen Proving Ground United States

Report Date:

2019-11-01

Pagination or Media Count:

26.0

Abstract:

Statistical techniques are utilized to determine the efficacy of physics-based descriptors to predict the energetic properties of silicon carbide grain boundaries. These descriptors are utilized in kernel ridge regression models with a radial basis function kernel for the prediction of grain boundary energetics. Models derived from this approach have been implemented as a replacement to the insertion, removal, and replacement probability functions in a Monte Carlo based selection scheme for sampling the microscopic degrees of freedom in silicon carbide grain boundaries. Preliminary results show these models increase the overall computational efficiency of finding low-energy minimized states compared to current techniques.

Subject Categories:

  • Inorganic Chemistry
  • Properties of Metals and Alloys
  • Ceramics, Refractories and Glass

Distribution Statement:

APPROVED FOR PUBLIC RELEASE