Hardness Prediction of Refractory High Entropy Alloy by Neural Network

Uttam Bandari, Congyan Zhang, Congyuan Zeng, Gbolahan Oyekenu, Nimpha Milbin, Ebrahim Khosravi, Patrick Mensah, Dwayne Jerro, Samuel Ibekwe, Xuhang Gu, Rachel Vincent-Finley, Guoqiang Li, Shengmin Guo, Shizhong Yang

Abstract

The hardness of refractory high entropy alloys (RHEAs) is an essential property but its prediction remains challenging. In this study, we propose a neural network mode (NN) that is capable of predicting the hardness of RHEAs. With this NN model, we predict the hardness of Mo15Nb20Re15Ta30W20 and found a good agreement with the experiment. This study provides an alternative path to calculate hardness before the alloys are synthesized and allows the researcher to design RHEAs until the desired hardness is reached.

Publication

In Proceedings of Louisiana EPSCoR RII CIMM 2020 Symposium