Combining two or three metals together produce an alloy that usually looks and acts like a metal, with its atoms arranged in rigid geometric patterns. Sometimes, however, under the right conditions, something entirely new results: a futuristic alloy called metallic glass. This amorphous material’s atoms are arranged in a non-crystalline, disordered structure, much like the atoms of the glass in a window, and its glassy nature makes it stronger and lighter than today's best steel, and able to better withstand corrosion and wear.
Although metallic glass shows promise as a protective coating and alternative to steel, only a few thousand of the millions of possible component combinations have been evaluated over the past 50 years, and only a handful have been developed to the point that they may become useful. Now a group led by scientists at the U.S. Department of Energy’s SLAC National Accelerator Laboratory (Menlo Park, California, USA), the National Institute of Standards and Technology (NIST) (Gaithersburg, Maryland, USA), and Northwestern University (Evanston, Illinois, USA) has reported a shortcut for discovering and improving metallic glass and other elusive materials at a fraction of the time and cost.
The research group utilized a system at SLAC’s Stanford Synchrotron Radiation Lightsource (SSRL) that combines machine learning—a form of artificial intelligence (AI) where computer algorithms glean knowledge from enormous amounts of data—with experiments that quickly make and screen hundreds of sample materials at a time. This allowed the team to discover three new blends of materials that form metallic glass, and do it 200 times faster than could be done previously.
“It typically takes a decade or two to get a material from discovery to commercial use,” says Chris Wolverton, the Jerome B. Cohen Professor of Materials Science and Engineering in Northwestern's McCormick School of Engineering, who is an early pioneer in using computation and AI to predict new materials. “This is a big step in trying to squeeze that time down. You could start out with nothing more than a list of properties you want in a material and, using AI, quickly narrow the huge field of potential materials to a few good candidates.”
Over the past half century, scientists have investigated about 6,000 combinations of ingredients that form metallic glass. "We were able to make and screen 20,000 in a single year," notes Apurva Mehta, a staff scientist at SSRL. Ultimately the goal is to get to the point where a scientist can scan hundreds of sample materials, get almost immediate feedback from machine learning models, and have another set of samples ready to test the next day or even within the hour, adds Wolverton, who led the group’s machine learning work.
“One of the more exciting aspects of this is that we can make predictions so quickly and turn experiments around so rapidly that we can afford to investigate materials that don't follow our normal rules of thumb about whether a material will form a glass or not,” comments Jason Hattrick-Simpers, a materials research engineer at NIST. “AI is going to shift the landscape of how materials science is done, and this is the first step.”
In the metallic glass study, the research team investigated thousands of alloys that contain three inexpensive, nontoxic metals each. They started with a trove of materials data dating back more than 50 years, including the results of 6,000 experiments that searched for metallic glass. The team combed through the data with advanced machine learning algorithms developed by Wolverton and Logan Ward, a graduate student in Wolverton’s laboratory.
Based on what the algorithms learned in the first round, the scientists crafted two sets of sample alloys using two different methods, allowing them to test how manufacturing methods affect whether an alloy will morph into a glass. An SSRL x-ray beam scanned both sets of alloys, then researchers fed the results into a database to generate new machine learning results, which were used to prepare additional samples that underwent another round of scanning and machine learning.
By the experiment's third and final round, Mehta says, the group's success rate for finding metallic glass had increased from one out of 300 or 400 samples tested to one out of two or three samples tested. The metallic glass samples they identified represented three different combinations of materials, two of which had not been previously used to make metallic glass.
Source: Northwestern University, www.northwestern.edu.