Machine learning prediction of thermodynamic and mechanical properties of multicomponent Fe-Cr-based alloys

Mukhamedov, B. O.; Karavaev, K. V.; Abrikosov, Igor A.

doi:10.1103/physrevmaterials.5.104407

Cited by 9 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As can be seen in Supplementary Fig. S18 a–c, the Pugh’s ratio increases with decreasing , in agreement with the ML results by Mukhamedov et al 67 Since Li has the lowest Pauling electronegativity as compared to Cu or Si, the Pugh’s ratio for the topmost AlBeMgTiLi composition is higher than that of AlBeMgTiCu. Similarly, the Pugh’s ratio increases generally with increasing as shown in Supplementary Fig.…”

Section: Discussionsupporting

confidence: 90%

See 1 more Smart Citation

First principles-based design of lightweight high entropy alloys

Sorkin,

Yu,

Chen

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Recently, the design of lightweight high entropy alloys (HEAs) with a mass density lower than 5 g/cm3 has attracted much research interest in structural materials. We applied a first principles-based high-throughput method to design lightweight HEAs in single solid-solution phase. Three lightweight quinary HEA families were studied: AlBeMgTiLi, AlBeMgTiSi and AlBeMgTiCu. By comprehensively exploring their entire compositional spaces, we identified the most promising compositions according to the following design criteria: the highest stability, lowest mass density, largest elastic modulus and specific stiffness, along with highest Pugh’s ratio. We found that HEAs with the topmost compositions exhibit a negative formation energy, a low density and high specific Young’s modulus, but a low Pugh’s ratio. Importantly, we show that the most stable composition, Al0.31Be0.15Mg0.14Ti0.05Si0.35 is energetically more stable than its metallic compounds and it significantly outperforms the current lightweight engineering alloys such as the 7075 Al alloy. These results suggest that the designed lightweight HEAs can be energetically more stable, lighter, and stiffer but slightly less ductile compared to existing Al alloys. Similar conclusions can be also drawn for the AlBeMgTiLi and AlBeMgTiCu. Our design methodology and findings serve as a valuable tool and guidance for the experimental development of lightweight HEAs.

show abstract

Section: Discussionsupporting

confidence: 90%

“…The Pugh’s ratio for the topmost stable composition of AlBeMgTiLi is the highest and that of AlBeMgTiSi is the lowest. ML-based studies 67 , 68 indicate that and are the two most appropriate atomistic descriptors for prediction of the ratio. As can be seen in Supplementary Fig.…”

Section: Discussionmentioning

confidence: 99%

First principles-based design of lightweight high entropy alloys

Sorkin,

Yu,

Chen

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…This approach is adopted in many existing works for learning elastic properties ( e.g. , for alloys 24–27 and polycrystals 28,29 ) and related atomic properties like stress and energy fields. 30 They are, however, limited to derived scalar elastic properties such as bulk modulus and shear modulus, and separate models are built for each derived property.…”

Section: Introductionmentioning

confidence: 99%

“…In a nutshell, state-of-the-art ML models for elastic properties encode compositional information [19][20][21] and/or structural information [20][21][22][23] in a material as feature vectors and then map them to a target using some regression algorithms. This approach is adopted in many existing works for learning elastic properties (e.g., for alloys [24][25][26][27] and polycrystals 28,29 ) and related atomic properties like stress and energy elds. 30 They are, however, limited to derived scalar elastic properties such as bulk modulus and shear modulus, and separate models are built for each derived property.…”

Section: Introductionmentioning

confidence: 99%

An equivariant graph neural network for the elasticity tensors of all seven crystal systems

Wen,

Horton,

Munro

et al. 2024

Digital Discovery

View full text Add to dashboard Cite

show abstract

“…We based our approach on the use of machine learning (ML) techniques, with a focus on probabilistic models and artificial neural networks. Limited by the amount of available composition-property data, conventional ML approaches in alloy design have to predominantly rely on simulation data, often with only limited experimental validation ( 9 , 10 ). As the experimental microstructure database continues to expand, ML obtains higher accuracy in predicting the phase or microstructure of materials ( 11 ).…”

mentioning

confidence: 99%

Machine learning–enabled high-entropy alloy discovery

Rao

Tung

Xie

et al. 2022

Science

220

View full text Add to dashboard Cite

High-entropy alloys are solid solutions of multiple principal elements that are capable of reaching composition and property regimes inaccessible for dilute materials. Discovering those with valuable properties, however, too often relies on serendipity, because thermodynamic alloy design rules alone often fail in high-dimensional composition spaces. We propose an active learning strategy to accelerate the design of high-entropy Invar alloys in a practically infinite compositional space based on very sparse data. Our approach works as a closed-loop, integrating machine learning with density-functional theory, thermodynamic calculations, and experiments. After processing and characterizing 17 new alloys out of millions of possible compositions, we identified two high-entropy Invar alloys with extremely low thermal expansion coefficients around 2 × 10 −6 per degree kelvin at 300 kelvin. We believe this to be a suitable pathway for the fast and automated discovery of high-entropy alloys with optimal thermal, magnetic, and electrical properties.

show abstract

Machine learning prediction of thermodynamic and mechanical properties of multicomponent Fe-Cr-based alloys

Cited by 9 publications

References 34 publications

First principles-based design of lightweight high entropy alloys

First principles-based design of lightweight high entropy alloys

An equivariant graph neural network for the elasticity tensors of all seven crystal systems

Machine learning–enabled high-entropy alloy discovery

Contact Info

Product

Resources

About