Unsupervised Learning of Dislocation Motion

Published

October 14, 2019

Author(s)

Darren Pagan, Thien Q. Phan, Jordan Weaver, Austin Benson, Armand Beaudoin

Abstract

The unsupervised learning technique, locally linear embedding (LLE), is applied to the analysis of X-ray diffraction data measured in-situ during uniaxial plastic deformation of an additively manufactured nickel-based superalloy. With the aid of a physics-based material model, we find that the lower-dimensional coordinates determined using LLE appear to be physically significant and reflect the evolution of the defect densities that dictate strength and plastic ow behavior in the alloy. The implications of the findings for future constitutive model development are discussed, with a focus on wider applicability of the approach to microstructure evolution and phase transformation studies during in-situ materials processing.

Citation

Acta Materialia

Volume

181

Pub Type

Journals

Download Paper

https://doi.org/10.1016/j.actamat.2019.10.011

Local Download

Keywords

Additive Manufacturing, Synchrotron X-Ray Diffraction, Unsupervised Machine Learning

Citation

Pagan, D. , Phan, T. , Weaver, J. , Benson, A. and Beaudoin, A. (2019), Unsupervised Learning of Dislocation Motion, Acta Materialia, [online], https://doi.org/10.1016/j.actamat.2019.10.011 , https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=928192 (Accessed October 18, 2025)