Machine learning accelerates discovery of high-temperature alloys

The article “Machine Learning Accelerates Discovery of High-Temperature Alloys” describes a new approach by scientists from several institutions, including the University of Science and Technology Beijing, to discover high-temperature refractory high-entropy alloys (RHEAs). The researchers used machine learning, genetic search, cluster analysis, and experimental methods to identify optimal alloy compositions, culminating in a ZrNbMoHfTa alloy with exceptional properties. The study highlights the use of multi-objective optimization to balance strength, ductility, and other properties, marking a significant advancement in materials science. The findings set a new standard for high-temperature alloys, paving the way for future innovation in aerospace, nuclear reactors, and other applications.

Please continue reading the full article under the link below: