Revealing high-fidelity phase selection rules for high entropy alloys: A combined CALPHAD and machine learning study

Abstract We reveal high-fidelity new phase selection rules for high entropy alloys (HEAs) by combining CALPHAD calculations and the machine learning (ML) method. Employing Thermo-Calc and TCHEA3 database, we first generate more than 300,000 equilibrium phase data from 20 quinary families formed by the 8 elements of Al Co, Cr, Cu, Fe, Mn, Ni, and Ti, and choose initially 15 materials/physical descriptors. The eXtreme Gradient Boosting (XGBoost) method is then used to identify 5 most important descriptors that best delineate the single and mixed phases in the complex temperature-composition space of HEAs. The ML model trained by the 5 features is validated by 155 annealing experimental data points from 15 publications and then used to predict 213 new single-phase alloys with BCC and FCC structures of the alloy families of AlCrNiFeMn and AlCrCoNiFeTi. We also highlight the importance of equilibrium temperature and offer in-depth insights into the paradigm of composition-feature-phase of HEAs. On the basis of the 5 important features, we establish new phase selection rules for single FCC and BCC phases with a success rate above 90%, significantly outperforming all existing phase selection rules and providing a powerful tool for mapping single-phase in the complex temperature-composition space of HEAs.