Better way found to determine the integrity of metals

July 30, 2018

Researchers at the University of Waterloo have found a better way to identify atomic structures, an essential step in improving materials selection in the aviation, construction and automotive industries.

The findings of the study could result in greater confidence when determining the integrity of metals.

Devinder Kumar, a PhD candidate in systems design engineering at Waterloo, collaborated with the Fritz Haber Institute (FHI) in Berlin, to develop a powerful AI model that can accurately detect different atomic structures in metallic materials. The system can find imperfections in the metal that were previously undetectable.

"Anywhere you have metals you want to know the consistency, and that can't be done in current practical scenarios because current methods fail to identify the symmetry in imperfect conditions," said Kumar, who is a member of the Vision and Image Processing Research Group under the supervision of Alexander Wong, a professor at Waterloo and Canada Research Chair in the area of artificial intelligence.

"So, this new method of evaluating metallic material will lead to better material design overall and has the potential to affect all the industries where you need material designing properties."

FHI came up with a new scenario that can artificially create data which relates to the real world. Kumar along with his collaborators was able to use this to generate about 80,000 images of the different kind of defects and displacements to produce a very effective AI model to identify various types of crystal structures in practical scenarios. This data has been released to the public so people can actually learn their own algorithms.

"In theory, all metallic materials have perfect symmetry, and all the items are in the correct place, but in practice because of various reasons such as cheap manufacturing there are defects," Kumar said. "All these current methods fail when they try to match actual ideal structures, most of them fail when there is even one per cent defect."

"We have made an AI-based algorithm or model that can classify these kinds of symmetries even up to 40 per cent of defect."

The study, Insightful classification of crystal structures using deep learning, was published recently in the journal Nature Communications.

University of Waterloo

Related Crystal Structures Articles from Brightsurf:

Getting single-crystal diamond ready for electronics
Researchers from Osaka University and collaborating partners polished single-crystal diamond to near-atomic smoothness without damaging it.

Magnetic nature of complex vortex-like structures in a Kagome crystal Fe3Sn2
Three-dimensional magnetic bubbles were demonstrated from the view of integral magnetizations for the first time, which clarify the physics behind complex multi-ring and arc-shaped vortices obtained from two-dimensional transmission electron microscopy magnetic imaging.

X-rays indicate that water can behave like a liquid crystal
Scientists at Stockholm University have discovered that water can exhibit a similar behavior like a liquid crystal when illuminated with laser light.

Photonic crystal light converter
Spectroscopy is the use of light to analyze physical objects and biological samples.

Higher-order topology found in 2D crystal
The research team took a new approach by using the Josephson junctions to spatially resolve the supercurrent flow and to show that WTe2 does indeed appear to have hinge states and be a higher-order topological insulator.

Hammer-on technique for atomic vibrations in a crystal
Vibrations of atoms in a crystal of the semiconductor gallium arsenide (GaAs) are impulsively shifted to a higher frequency by an optically excited electric current.

Crystal wars
Scientists at The University of Tokyo and Fudan University researched the process of crystallization in which competing structural forms coexist.

Melting a crystal topologically
Physicists at EPFL have successfully melted a very thin crystal of magnetic quasi-particles controllably, as turning ice into water.

The makings of a crystal flipper
Hokkaido University scientists have fabricated a crystal that autonomously flips back and forth while changing its flipping patterns in response to lighting conditions.

Crystal power
Scientists at the US Department of Energy's Argonne National Laboratory have created and tested a single-crystal electrode that promises to yield pivotal discoveries for advanced batteries under development worldwide.

Read More: Crystal Structures News and Crystal Structures Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to