Coupling physics in machine learning to investigate the solution behavior of binary Mg alloys
The solution behavior of a second element in the primary phase (α(Mg)) is important in the design of high-performance alloys. In this work, three sets of features have been collected: a) interaction features of solutes and Mg obtained from first-principles calculation, b) intrinsic physical properti...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2022-10-01
|
| Series: | Journal of Magnesium and Alloys |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213956721001584 |
| _version_ | 1797204082972164096 |
|---|---|
| author | Tao Chen Qian Gao Yuan Yuan Tingyu Li Qian Xi Tingting Liu Aitao Tang Andy Watson Fusheng Pan |
| author_facet | Tao Chen Qian Gao Yuan Yuan Tingyu Li Qian Xi Tingting Liu Aitao Tang Andy Watson Fusheng Pan |
| author_sort | Tao Chen |
| collection | DOAJ |
| description | The solution behavior of a second element in the primary phase (α(Mg)) is important in the design of high-performance alloys. In this work, three sets of features have been collected: a) interaction features of solutes and Mg obtained from first-principles calculation, b) intrinsic physical properties of the pure elements and c) structural features. Based on the maximum solid solubility values, the solution behavior of elements in α(Mg) are classified into four types, e.g., miscible, soluble, sparingly-soluble and slightly-soluble. The machine learning approach, including random forest and decision tree algorithm methods, is performed and it has been found that four features, e.g., formation energy, electronegativity, non-bonded atomic radius, and work function, can together determine the classification of the solution behavior of an element in α(Mg). The mathematical correlations, as well as the physical relationships among the selected features have been analyzed. This model can also be applied to other systems following minor modifications of the defined features, if required. |
| first_indexed | 2024-04-11T15:34:06Z |
| format | Article |
| id | doaj.art-e76c674dc4ac4054b910f515e2f90b39 |
| institution | Directory Open Access Journal |
| issn | 2213-9567 |
| language | English |
| last_indexed | 2024-04-24T08:29:35Z |
| publishDate | 2022-10-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Journal of Magnesium and Alloys |
| spelling | doaj.art-e76c674dc4ac4054b910f515e2f90b392024-04-16T20:45:31ZengKeAi Communications Co., Ltd.Journal of Magnesium and Alloys2213-95672022-10-01101028172832Coupling physics in machine learning to investigate the solution behavior of binary Mg alloysTao Chen0Qian Gao1Yuan Yuan2Tingyu Li3Qian Xi4Tingting Liu5Aitao Tang6Andy Watson7Fusheng Pan8State Key Laboratory of Mechanical Transmissions, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR China; National Engineering Research Center for Magnesium Alloys, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR ChinaState Key Laboratory of Mechanical Transmissions, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR China; National Engineering Research Center for Magnesium Alloys, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR ChinaState Key Laboratory of Mechanical Transmissions, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR China; National Engineering Research Center for Magnesium Alloys, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR China; Corresponding author at: National Engineering Research Center for Magnesium Alloys, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR China.National Engineering Research Center for Magnesium Alloys, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR ChinaNational Engineering Research Center for Magnesium Alloys, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR ChinaFaculty of Materials and Energy, Southwest University, Chongqing 400715, PR ChinaState Key Laboratory of Mechanical Transmissions, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR China; National Engineering Research Center for Magnesium Alloys, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR ChinaHampton Thermodynamics, Hampton TW12 1NL, United KingdomState Key Laboratory of Mechanical Transmissions, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR China; National Engineering Research Center for Magnesium Alloys, College of Materials Science and Engineering, Chongqing University, Chongqing 400000, PR ChinaThe solution behavior of a second element in the primary phase (α(Mg)) is important in the design of high-performance alloys. In this work, three sets of features have been collected: a) interaction features of solutes and Mg obtained from first-principles calculation, b) intrinsic physical properties of the pure elements and c) structural features. Based on the maximum solid solubility values, the solution behavior of elements in α(Mg) are classified into four types, e.g., miscible, soluble, sparingly-soluble and slightly-soluble. The machine learning approach, including random forest and decision tree algorithm methods, is performed and it has been found that four features, e.g., formation energy, electronegativity, non-bonded atomic radius, and work function, can together determine the classification of the solution behavior of an element in α(Mg). The mathematical correlations, as well as the physical relationships among the selected features have been analyzed. This model can also be applied to other systems following minor modifications of the defined features, if required.http://www.sciencedirect.com/science/article/pii/S2213956721001584Mg alloysSolid solubilityMachine learningFirst-principles calculationDiagrammatic method |
| spellingShingle | Tao Chen Qian Gao Yuan Yuan Tingyu Li Qian Xi Tingting Liu Aitao Tang Andy Watson Fusheng Pan Coupling physics in machine learning to investigate the solution behavior of binary Mg alloys Journal of Magnesium and Alloys Mg alloys Solid solubility Machine learning First-principles calculation Diagrammatic method |
| title | Coupling physics in machine learning to investigate the solution behavior of binary Mg alloys |
| title_full | Coupling physics in machine learning to investigate the solution behavior of binary Mg alloys |
| title_fullStr | Coupling physics in machine learning to investigate the solution behavior of binary Mg alloys |
| title_full_unstemmed | Coupling physics in machine learning to investigate the solution behavior of binary Mg alloys |
| title_short | Coupling physics in machine learning to investigate the solution behavior of binary Mg alloys |
| title_sort | coupling physics in machine learning to investigate the solution behavior of binary mg alloys |
| topic | Mg alloys Solid solubility Machine learning First-principles calculation Diagrammatic method |
| url | http://www.sciencedirect.com/science/article/pii/S2213956721001584 |
| work_keys_str_mv | AT taochen couplingphysicsinmachinelearningtoinvestigatethesolutionbehaviorofbinarymgalloys AT qiangao couplingphysicsinmachinelearningtoinvestigatethesolutionbehaviorofbinarymgalloys AT yuanyuan couplingphysicsinmachinelearningtoinvestigatethesolutionbehaviorofbinarymgalloys AT tingyuli couplingphysicsinmachinelearningtoinvestigatethesolutionbehaviorofbinarymgalloys AT qianxi couplingphysicsinmachinelearningtoinvestigatethesolutionbehaviorofbinarymgalloys AT tingtingliu couplingphysicsinmachinelearningtoinvestigatethesolutionbehaviorofbinarymgalloys AT aitaotang couplingphysicsinmachinelearningtoinvestigatethesolutionbehaviorofbinarymgalloys AT andywatson couplingphysicsinmachinelearningtoinvestigatethesolutionbehaviorofbinarymgalloys AT fushengpan couplingphysicsinmachinelearningtoinvestigatethesolutionbehaviorofbinarymgalloys |