Data analytics and experimental microscopy power discovery of extremely hard high-entropy alloys—a novel approach that could accelerate search for new materials

By Amy White

A new method of discovering materials using data analytics and electron microscopy has found a new class of extremely hard alloys—materials that could potentially withstand severe impact from projectiles and provide better protection to soldiers in combat.

Lehigh researchers describe the method and findings in a recent article published in Nature Communications.
“We used materials informatics—the application of the methods of data science to materials problems—to predict a class of materials that have superior mechanical properties,” says primary author Jeffrey M. Rickman, a professor of materials science and engineering and physics and a Class of ’61 Professor.
Researchers also used experimental tools, such as electron microscopy, to gain insight into the physical mechanisms that led to the observed behavior in the class of materials known as high-entropy alloys (HEAs). High-entropy alloys contain many different elements that, when combined, may result in systems having beneficial and sometimes unexpected thermal and mechanical properties. For that reason, they are currently the subject of intense research.
“We thought that the techniques that we have developed would be useful in identifying promising HEAs,” Rickman explains. “However, we found alloys that had hardness values that exceeded our initial expectations. Their hardness values are about a factor of 2 better than other, more typical high-entropy alloys and other relatively hard binary alloys.”
All seven authors are from the Rossin College: Rickman; fellow materials science and engineering faculty members Helen M. Chan and Martin P. Harmer; materials science and engineering graduate student Joshua Smeltzer and postdoctoral research associate Christopher Marvel; mechanical engineering and mechanics graduate student Ankit Roy; and Ganesh Balasubramanian, an assistant professor of mechanical engineering and mechanics.

The research was funded by the Office of Naval Research with support from Lehigh’s Nano/Human Interface Initiative (see “The Human Element,” sidebar).

The field of high-entropy, or multi-principal element, alloys has recently seen exponentional growth

Dawn of a paradigm shift

The field of high-entropy, or multi-principal element, alloys has recently seen exponential growth. These systems represent a paradigm shift in alloy development, as some exhibit new structures and superior mechanical properties, as well as enhanced oxidation resistance and magnetic properties, relative to conventional alloys. However, identifying promising HEAs has presented a daunting challenge, given the vast palette of possible elements and combinations that could exist.

Researchers have sought a way to identify the element combinations and compositions that lead to high-strength, high-hardness alloys and other desirable qualities, which are a relatively small subset of the large number of potential HSAs that could be created.

In recent years, materials informatics has emerged as a powerful tool for materials discovery and design. The relatively new field is already having a significant impact on the interpretation of data for a variety of materials systems, including those used in thermoelectrics, ferroelectrics, battery anodes and cathodes, hydrogen storage materials, and polymer dielectrics.

“Creation of large data sets in materials science, in particular, is transforming the way research is done in the field by providing opportunities to identify complex relationships and to extract information that will enable new discoveries and catalyze materials design,” Rickman says. The tools of data science, including multivariate statistics, machine learning, dimensional reduction, and data visualization, have already led to the identification of structure-property-processing relationships, screening of promising alloys, and correlation of microstructure with processing parameters.

Lehigh’s research contributes to the field of materials informatics by demonstrating that this suite of tools is extremely useful for identifying promising materials from among myriad possibilities. “These tools can be used in a variety of contexts to narrow large experimental parameter spaces to accelerate the search for new materials,” Rickman says.

We believe that our approach has the potentiation to change the way researchers discover such systems going forward.
Jeffrey M. Rickman
Compositional maps of a multiple principal element alloy obtained via energy dispersive spectroscopy.

New Method Combines Complementary Tools

Lehigh researchers combined two complementary tools to employ a supervised learning strategy for the efficient screening of high-entropy alloys and to identify promising HEAs: (1) a canonical-correlation analysis and (2) a genetic algorithm with a canonical-correlation analysis-inspired fitness function.

They implemented this procedure using a database for which mechanical property information exists and highlighting new alloys with high hardnesses. The methodology was validated by comparing predicted hardnesses with alloys fabricated in a laboratory using arc-melting, identifying alloys with very high measured hardnesses.
“The methods employed here involved a novel combination of existing methods adapted to the high-entropy alloy problem,” Rickman says. “In addition, these methods may be generalized to discover, for example, alloys having other desirable properties. We believe that our approach, which relies on data science and experimental characterization, has the potential to change the way researchers discover such systems going forward.”

The Human Element

Lehigh's multidisciplinary Nano/Human Interface Presidential Engineering Research Initiative proposes to develop a human-machine interface to improve the ability of scientists to visualize and interpret the vast amounts of data generated by scientific research.

Materials science and engineering professor Martin P. Harmer leads the effort, which got a kick start in 2017 with a $3 million institutional investment. Other senior faculty collaborators include materials science and physics professor Jeffrey M. Rickman, bioengineering professor and chair Anand Jagota, computer science and engineering professor Daniel P. Lopresti, and psychology professor Catherine M. Arrington.

"Several research universities are making major investments in big data," says Rickman. "Our initiative brings in a relatively new aspect: the human element."

The initiative, which is a partnership between Lehigh, Ohio State University, and the Army Research Laboratory, emphasizes the human, says Arrington, because the successful development of new tools for data visualization and manipulation must necessarily include a consideration of the cognitive strengths and limitations of the scientist.

"We are at a new frontier in materials research," says Rickman, "which calls for new approaches and partners to chart the way forward."

I-DISC Launches Data Science Series

The workshop was over. Rows of brown-bag lunches were lined up and ready for the taking. A bus was waiting outside Iacocca Hall.

But still, workshop participants lingered, talking in small groups. It was exactly the scene the conference on applications of machine learning and data science to molecular and materials science and engineering was meant to generate.

“The event brought together a diverse range of fields, which gave people the opportunity to engage with those they wouldn’t ordinarily encounter,” says Srinivas Rangarajan, an assistant professor of chemical and biomolecular engineering (ChBE). “And that was the goal—to bring together top experts from a range of disciplines to share the latest techniques  as well as the challenges in machine learning.”

Rangarajan organized the three-day workshop in May—the first in a series funded by a National Science Foundation TRIPODS+X grant awarded to the Institute for Data, Intelligent Systems, and Computation (I-DISC)—along with ChBE professor Jeetain Mittal; Joshua Agar, an assistant professor of materials science and engineering; and Payel Das of IBM Thomas J. Watson Research Center.

“I-DISC is promoting new knowledge by creating new networks of professionals in these complex domains,” says ChBE chair and R.L. McCann Professor Mayuresh V. Kothare.
In October 2019, the second workshop in the series will focus on emerging directions at the intersection of robotics, deep and reinforcement learning, control systems, and operational research.

“There is a clear need for developing algorithms that are able to learn automatically and have the robot adapt to the environment,” says I-DISC co-director Hector Munoz-Avila, a professor of computer science and engineering. “Anyone who is interested in robotics will get something out of this.”