Researchers from POSTECH have created an AI model to predict the yield strength of metals, combining physical theory with machine learning. This model uses “grain boundary sliding” mechanisms and machine learning algorithms to enhance prediction accuracy while reducing time and costs. Tested on various iron-based alloys, it demonstrated high accuracy with an average absolute error of 7.79 MPa. This advancement aims to optimize the development of high-performance materials and improve structural stability.
For further details, visit Phys.org: