Prediction of elastic properties of face-centered cubic high-entropy alloys by machine learning

The machine learning (ML) models were proposed for predicting elastic properties of face-centered-cubic (FCC) high-entropy alloys (HEAs). The data set was from the first-principles calculation, which contained 186 samples. The goodness-of-fit (R2) values of predicted bulk modulus (B) and shear modulus (G) in the test set were 0.81 and 0.84, respectively. According to the results of ML, CoNiCuMoW HEAs have the largest B, G, elastic modulus (Y) and good ductility (G/B <= 0.57) among the FCC HEAs with equal components. The first-principles calculation results show that the elastic anisotropy of (CoNiCuMo)1-xWx HEAs increases and ductility decreases with increasing W content. According to the analysis of charge density difference, there is obvious charge accumulation at W-W and W-Mo bonds, indicating the directional covalent bonds formed between W atoms and their neighboring atoms.

Automated summary

Machine learning models were used to predict the elastic properties of face-centered-cubic high-entropy alloys. The data set consisted of 186 samples from first-principles calculations. The goodness-of-fit values (R2) for predicted bulk modulus and shear modulus in the test set were 0.81 and 0.84, respectively. According to the results, among the face-centered-cubic high-entropy alloys with equal components, CoNiCuMoW HEAs have the largest bulk modulus, shear modulus, elastic modulus, and good ductility (G/B <= 0.57). The first-principles calculation results show that the elastic anisotropy of (CoNiCuMo)1-xWx HEAs increases and ductility decreases with increasing W content. The analysis of charge density difference reveals obvious charge accumulation at W-W and W-Mo bonds, indicating the formation of directional covalent bonds between W atoms and their neighboring atoms.