Wear Resistance Prediction of AlCoCrFeNi-X (Ti, Cu) High-Entropy Alloy Coatings Based on Machine Learning

In order to save the time and cost of friction wear experiments, coating composition (different contents Al, Ti, Cu elements), ratio hardness elastic modulus (H3/E2), vacuum heat treatment (VHT) temperature, form were used as input variables, rates high-entropy alloy (HEA) coatings output variables. The dataset was entirely obtained by experiment. Four machine learning algorithms (classification regression tree (CART), random forest (RF), gradient boosting decision (GBDT), adaptive (AdaBoost)) predict resistance HEA based on a small amount data. results show that except for GBDT model, other three models had good performance. Because data, CART model demonstrated best prediction performance can provide guidance predicting AlCoCrFeNi-X (Ti, Cu) drilling equipment. Furthermore, contribution different factors rate obtained. Al content greatest influence rate, followed H3/E2, form, VHT temperature.