Related Glossary Terms
Substances having metallic properties and being composed of two or more chemical elements of which at least one is a metal.
Developing new materials takes a lot of time, money and effort. A joint research team at Pohang University of Science and Technology recently sought to make that creation easier by applying artificial intelligence to develop high-entropy alloys.
Professor Seungchul Lee, Ph.D. candidate Soo Young Lee, professor Hyungyu Jin, Ph.D. candidate Seokyeong Byeon and professor Hyoung Seop Kim developed a technique for phase prediction of high-entropy alloys using AI.
Metal materials conventionally are made by mixing the principal element for the desired property with two or three auxiliary elements. In contrast, high-entropy alloys are made with equal or similar proportions of five or more elements without a principal element. The types of alloys that can be made like this are theoretically infinite and have exceptional mechanical, thermal, physical and chemical properties. High-strength alloys and alloys resistant to corrosion and extremely low temperatures already have been discovered.
However, until now, designing new high-entropy alloy materials was based on trial and error, thus requiring much time and money. It was even more difficult to determine in advance the phase and the mechanical and thermal properties of the high-entropy alloy being developed.
The team focused on developing prediction models for high-entropy alloys with enhanced phase prediction and explainability using deep learning. Researchers applied deep learning to three perspectives: model optimization, data generation and parameter analysis. In particular, the focus was on building a data-enhancing model based on the conditional generative adversarial network. This allowed AI models to reflect samples of high-entropy alloys that have not yet been discovered, thereby improving phase prediction accuracy compared with conventional methods.
In addition, the team developed a descriptive AI-based high-entropy alloy phase prediction model to provide interpretability to deep learning models while also giving guidance on key design parameters for creating high-entropy alloys with certain phases.
“This research is the result of drastically improving the limitations of existing research by incorporating AI into HEAs that have recently been drawing much attention,” Seungchul Lee said. “It is significant that the joint research team’s multidisciplinary collaboration has produced the results that can accelerate AI-based fabrication of new materials.”
“The results of the study are expected to greatly reduce the time and cost required for the existing new material development process and to be actively used to develop new high-entropy alloys in the future,” Jin said.