Prediction of mechanical properties of Mg-rare earth alloys by machine learning

Abstract In this work, the quantitative relationship among composition, processing history and mechanical properties of Magnesium-rare earth alloys was established by machine learning (ML). Based on support vector regression (SVR) algorithm, ML models were with inputs 310 sets data, which can predict ultimate tensile strength (UTS), yield (YS) elongation (EL) well accuracy. order to verify general applicability our model, new data collected from literature, used their respectively. The MAPE UTS, YS EL predicted SVR model are 9%, 12% 36%, reasons for deviation results also analyzed. effects rare elements analyzed models. recommend composition high properties.