Machine learning assisted prediction of the Young’s modulus of compositionally complex alloys

Khakurel, Hrishabh; Taufique, M. F. N.; Roy, Abhinaba; Balasubramanian, Ganesh; Cui, Jun; Johnson, Duane D.; Devanathan, Ram

doi:10.1038/s41598-021-96507-0

Cited by 53 publications

(28 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…VEC and MT hold the top two positions in predicting the elastic constants. From the previous findings, it is interesting to note the role of the VEC descriptor, which has the top position in descriptor importance in determining the crystal structure [ 20 , 21 , 22 , 23 , 24 , 25 ], Young’s modulus [ 27 , 60 , 61 ], and hardness [ 62 ] of HEAs. The previous study has shown that VEC is the essential feature in determining Young’s modulus of complex concentrated alloys in their ML models [ 27 ].…”

Section: Resultsmentioning

confidence: 99%

“…From the previous findings, it is interesting to note the role of the VEC descriptor, which has the top position in descriptor importance in determining the crystal structure [ 20 , 21 , 22 , 23 , 24 , 25 ], Young’s modulus [ 27 , 60 , 61 ], and hardness [ 62 ] of HEAs. The previous study has shown that VEC is the essential feature in determining Young’s modulus of complex concentrated alloys in their ML models [ 27 ]. Moreover, Roy et al [ 63 ] also found that MT is an essential parameter in predicting Young’s modulus of HEAs using the gradient boosting method.…”

Section: Resultsmentioning

confidence: 99%

“…For example, the Islam group [ 20 ] used 118 instances of data set with five descriptors, i.e., VEC , Δ S mix , Δ H mix , δ, and χ , to determine the phase in multi-principle element alloys. Khakurel et al [ 27 ] used some ML models to estimate Young’s modulus of CCAs. They found that VEC , geometrical parameter, δ, and melting temperature play essential roles in determining the modulus of CCAs.…”

Section: Data Generation and ML Modelsmentioning

confidence: 99%

“…Machine learning (ML) is a reasonably easy and cost-effective tool for quickly identifying hidden patterns in a dataset. The recent trend of applying ML models in designing HEAs is promising in determining the phase formation [ 19 , 20 , 21 , 22 , 23 , 24 , 25 ] and predicting mechanical properties [ 26 , 27 , 28 ]. ML is also applied in the biomedical field to design metallic implants [ 29 , 30 , 31 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Predicting Elastic Constants of Refractory Complex Concentrated Alloys Using Machine Learning Approach

et al. 2022

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Data Generation and ML Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting Elastic Constants of Refractory Complex Concentrated Alloys Using Machine Learning Approach

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Young's modulus is a measurement of a material's ability to endure tensile or compressive loads. The Valence Electron Concentration (VEC) is defined as the number of valence electrons per formula unit [14]. And the Average Melting Temperature is the average of melting temperatures of all the participating elements.…”

Section: Introductionmentioning

confidence: 99%

Mathematical modelling for prediction of Young’s modulus in compositionally complex alloys

Nikaran¹,

Sathiskumar²,

Dharani³

et al. 2022

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

A generic mathematical model-based bottom-up approach for high throughput materials development of compositionally complex alloys is established in this study. A general bottom-up technique, in contrast to a top-down approach, entails property selection, element screening, structure identification, and fabrication. The application is used to guide the property selection. The alloy design depends on the screening of contributing elements depending on the necessary property. The usage of mathematical models could help with element screening to meet the property requirement. The properties of the resulting compound alloys may be determined by the attributes of compositionally complex alloys. As a result, developing a model that links the needed attribute to the most important aspects of compositionally complex alloys is critical. The Young’s modulus, which is the considered attribute, is predicted using a predictive mathematical modelling approach based on its relationship with the features: valence electron concentration and average melting temperature. Monte Carlo Simulation is also used to discover the optimum feasible composition in order to improve Young’s modulus.

show abstract

Strength of Disordered and Ordered Al‐Containing Refractory High‐Entropy Alloys

Laube,

Winkens,

Kauffmann

et al. 2024

Adv Eng Mater

View full text Add to dashboard Cite

Body‐centered cubic refractory high entropy alloys (RHEA) are promising for high‐temperature structural application due to their exceptional properties, particularly in terms of yield strength at elevated temperatures. For certain alloy systems, such as Mo‐Ti‐Cr‐Al, both disordered (A2) and ordered (B2) crystal structures are possible. In this particular system, a solid‐state transformation from A2 to B2 during cooling occurs. For Al concentrations above approximately 10 at.%, B2 order is obtained from the transformation temperature down to room temperature, while A2 is stable above room temperature below the critical Al content. In this study, two alloys from the Mo‐Ti‐Cr‐Al system close to the transition between A2 and B2 were investigated. Nanoindentation tests revealed that the magnitude of strain rate sensitivity for both alloys is small compared to classical alloys, however, significantly temperature dependent up to the strength plateau temperatures. The yield strength plateau, which is insensitive to the strain rate, was observed at temperatures exceeding 573 K. Modelling of solid solution strengthening reproduces the experimental data in the Al‐lean A2 alloys. However, the observed discontinuous increase of strength in the Al‐rich B2 alloys can only be rationalized by the appearance of B2 order and to no significant other obvious strengthening mechanisms.This article is protected by copyright. All rights reserved.

show abstract

Machine learning assisted prediction of the Young’s modulus of compositionally complex alloys

Cited by 53 publications

References 54 publications

Predicting Elastic Constants of Refractory Complex Concentrated Alloys Using Machine Learning Approach

Predicting Elastic Constants of Refractory Complex Concentrated Alloys Using Machine Learning Approach

Mathematical modelling for prediction of Young’s modulus in compositionally complex alloys

Strength of Disordered and Ordered Al‐Containing Refractory High‐Entropy Alloys

Contact Info

Product

Resources

About