Guwahati, February 4: Researchers at the Indian Institute of Technology (IIT) Guwahati, in collaboration with colleagues from London South Bank University, the University of Manchester, and the University of Leeds, have developed a machine learning (ML)-based method to design advanced metal alloys free of critical raw materials (CRM).
This innovation is expected to provide a practical means to identify high-performance, sustainable materials that are not dependent on fragile global supply chains.
In recent years, a new class of materials, high-entropy alloys (HEAs), have attracted the attention of researchers and industry around the world.
Unlike traditional alloys, which contain a primary metal with small amounts of secondary metals, HEAs contain approximately equal amounts of multiple metals. These fall into the category of multi-principal element alloys (MPEA).
HEAs are attractive because they are more combinable than traditional alloys and often exhibit superior strength and stability at high temperatures.
Many high-performance HEAs used in areas such as aerospace engines, gas turbines, and nuclear power plants employ CRMs such as tantalum, niobium, tungsten, and hafnium. These elements are expensive, difficult to mine, and available in limited amounts.
High dependence on such materials increases import dependence, strains supply chains, and adds to environmental pressures from mining. Reducing its use is therefore essential for sustainability and long-term industrial safety.
To address this challenge, a research team led by IIT Guwahati developed a machine learning-assisted alloy design framework focused on identifying MPEAs that avoid the most critical raw materials.
The researchers first grouped CRMs into three levels based on supply risk, economic importance, and global availability. They created a database of 3,608 alloy compositions, focusing primarily on simple alloy systems built from less rare elements.
The Extra Trees Regressor model was combined with various optimization techniques inspired by natural processes to explore alloy compositions that achieve high hardness without CRM.
A CRM-free alloy, Ti-Ni-Fe-Cu, was identified. The research team developed the newly proposed Ti-Ni-Fe-Cu alloy at laboratory scale at IIT Kanpur and found that its measured hardness closely matched the predicted value, confirming that the AI-based method actually works.
The research results were published in the Nature Publishing Group’s journal Scientific Reports in a paper co-authored by Professor Joshi and his research team members Dr. Swati Singh of Guwahati University of Technology, Professor Saurav Goel of London South Bank University, Dr. Mingwen Bai of the University of Leeds, and Professor Alan Matthews of the University of Manchester.
