Researchers at Brigham Young University (BYU) (Provo, Utah) have developed a technique to produce a “dictionary” of the atomic building blocks found in metals, alloys, semiconductors, and other materials.
Their approach analyzes data to provide insight into structures associated with specific mechanisms, processes, and properties.
The goal of the project, which could be a 10- to 20-year process, is to more efficiently develop materials that help create strong, lightweight, and corrosion-free metals and alloys.
“We’re using machine learning, which means algorithms can see trends in data that a human can’t see,” says engineering professor Eric Homer.
Researchers say their project, supported by the U.S. Department of Energy (Washington, DC), is the first attempt to combine the scientific knowledge of factors influencing grain boundaries with the computer algorithms of machine learning. These grain boundaries can influence a metal’s strength, corrosion resistance, and conductivity.
“Siri works by taking sounds and turning them into vowels and consonants and ultimately words by accessing a massive database,” says BYU physicist Gus Hart, referring to the voice-controlled personal assistant on Apple devices. “We’re using the same concept. We have a large database, and our algorithm is taking grain boundaries and comparing them against that database to connect them to certain properties.”
Source: BYU, news.byu.edu.