Predicting Elastic Constants of Refractory Complex Concentrated Alloys Using Machine Learning Approach
Abstract
Refractory complex concentrated alloys (RCCAs) have drawn increasing attention recently owing to their balanced mechanical properties, including excellent creep resistance, ductility, and oxidation resistance. The mechanical and thermal properties of RCCAs are directly linked with the elastic constants. However, it is time consuming and expensive to obtain the elastic constants of RCCAs with conventional trial-and-error experiments. The elastic constants of RCCAs are predicted using a combination of density functional theory simulation data and machine learning (ML) algorithms in this study. The elastic constants of several RCCAs are predicted using the random forest regressor, gradient boosting regressor (GBR), and XGBoost regression models. Based on performance metrics R-squared, mean average error and root mean square error, the GBR model was found to be most promising in predicting the elastic constant of RCCAs among the three ML models. Additionally, GBR model accuracy was verified using the other four RHEAs dataset which was never seen by the GBR model, and reasonable agreements between ML prediction and available results were found. The present findings show that the GBR model can be used to predict the elastic constant of new RHEAs more accurately without performing any expensive computational and experimental work.
- Authors:
- Publication Date:
- Research Org.:
- Southern Univ. and A & M College, Baton Rouge, LA (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA); National Science Foundation (NSF)
- OSTI Identifier:
- 1876509
- Alternate Identifier(s):
- OSTI ID: 1878155
- Grant/Contract Number:
- NA0003979
- Resource Type:
- Published Article
- Journal Name:
- Materials
- Additional Journal Information:
- Journal Name: Materials Journal Volume: 15 Journal Issue: 14; Journal ID: ISSN 1996-1944
- Publisher:
- MDPI AG
- Country of Publication:
- Switzerland
- Language:
- English
- Subject:
- 36 MATERIALS SCIENCE; complex concentrated alloys; elastic constants; random forest regressor; gradient boosting regressor; XGBoost regression
Citation Formats
Bhandari, Uttam, Ghadimi, Hamed, Zhang, Congyan, Yang, Shizhong, and Guo, Shengmin. Predicting Elastic Constants of Refractory Complex Concentrated Alloys Using Machine Learning Approach. Switzerland: N. p., 2022.
Web. doi:10.3390/ma15144997.
Bhandari, Uttam, Ghadimi, Hamed, Zhang, Congyan, Yang, Shizhong, & Guo, Shengmin. Predicting Elastic Constants of Refractory Complex Concentrated Alloys Using Machine Learning Approach. Switzerland. https://doi.org/10.3390/ma15144997
Bhandari, Uttam, Ghadimi, Hamed, Zhang, Congyan, Yang, Shizhong, and Guo, Shengmin. Mon .
"Predicting Elastic Constants of Refractory Complex Concentrated Alloys Using Machine Learning Approach". Switzerland. https://doi.org/10.3390/ma15144997.
@article{osti_1876509,
title = {Predicting Elastic Constants of Refractory Complex Concentrated Alloys Using Machine Learning Approach},
author = {Bhandari, Uttam and Ghadimi, Hamed and Zhang, Congyan and Yang, Shizhong and Guo, Shengmin},
abstractNote = {Refractory complex concentrated alloys (RCCAs) have drawn increasing attention recently owing to their balanced mechanical properties, including excellent creep resistance, ductility, and oxidation resistance. The mechanical and thermal properties of RCCAs are directly linked with the elastic constants. However, it is time consuming and expensive to obtain the elastic constants of RCCAs with conventional trial-and-error experiments. The elastic constants of RCCAs are predicted using a combination of density functional theory simulation data and machine learning (ML) algorithms in this study. The elastic constants of several RCCAs are predicted using the random forest regressor, gradient boosting regressor (GBR), and XGBoost regression models. Based on performance metrics R-squared, mean average error and root mean square error, the GBR model was found to be most promising in predicting the elastic constant of RCCAs among the three ML models. Additionally, GBR model accuracy was verified using the other four RHEAs dataset which was never seen by the GBR model, and reasonable agreements between ML prediction and available results were found. The present findings show that the GBR model can be used to predict the elastic constant of new RHEAs more accurately without performing any expensive computational and experimental work.},
doi = {10.3390/ma15144997},
journal = {Materials},
number = 14,
volume = 15,
place = {Switzerland},
year = {Mon Jul 18 00:00:00 EDT 2022},
month = {Mon Jul 18 00:00:00 EDT 2022}
}
https://doi.org/10.3390/ma15144997
Figures / Tables:
Figures / Tables found in this record: