Communications of the ACM
Lasers, Levitation, and Machine Learning Make Better Heat-Resistant Materials
Researchers at Argonne National Laboratory came up with a way to use innovative experimental techniques and a new approach to computer simulations to obtain precise data about the structural changes refractory oxides undergo near their melting points.
Credit: Ganesh Sivarama/-Argonne National Laboratory
A process developed by a multidisciplinary research team at the Argonne National Laboratory can predict how refractory oxides are impacted by high temperatures.
The process generates precise data about the structural changes in these ceramic materials near their melting points and can predict other changes that currently are unable to be measured.
Physicists used X-ray beams and aerodynamic levitation to gather data on what happens to hafnium dioxide at its melting point.
This data was fed by computer scientists into machine learning algorithms, one that can make predictions and an active learning algorithm that helps the other algorithm learn with fewer data.
Physicist Chris Benmore said, "We can now go ahead and give you other parameters, such as how well it retains its shape at high temperatures, which we did not measure. We can extrapolate what would happen if we go beyond the temperature we can reach."
From Argonne National Laboratory
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found