Development of neural network potential for Al-based alloys containing vacancy
Potential energy of an alloy is an essential indicator for evaluating the stability of the structure in predicting new materials. Therefore, how to calculate the potential energy in material design has become an inevitable problem. While first-principles calculations can provide chemical accuracy fo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Japan Society of Mechanical Engineers
2023-07-01
|
| Series: | Mechanical Engineering Journal |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/mej/10/4/10_23-00066/_pdf/-char/en |
| _version_ | 1797742232586944512 |
|---|---|
| author | Jia ZHAO Yutaro MAEDA Kenjiro SUGIO Gen SASAKI |
| author_facet | Jia ZHAO Yutaro MAEDA Kenjiro SUGIO Gen SASAKI |
| author_sort | Jia ZHAO |
| collection | DOAJ |
| description | Potential energy of an alloy is an essential indicator for evaluating the stability of the structure in predicting new materials. Therefore, how to calculate the potential energy in material design has become an inevitable problem. While first-principles calculations can provide chemical accuracy for arbitrary atomic arrangements, they are prohibitive in terms of computational effort and time. To enable atomistic-level simulations of both the processing and performance of Aluminum alloys, neural network potential was proposed to predict the binding energy of vacancy-containing aluminum alloys in a highly accurate state. This method combined first-principles calculations and machine learning techniques to explore the intrinsic link between solid solution structure and binding energies. In this study, four binary alloys (aluminum-silicon, aluminum- zirconium, aluminum-magnesium and aluminum-titanium alloys) were investigated. The mean squared errors were used to quantify the quality of the neural network potential models and it was found that the trained model is more stable and exhibits high accuracy for energy prediction. The Monte Carlo simulation results show that using this neural network potential successfully simulated aging process of aluminum alloys, and the neural network potential can be much faster than first-principles calculations, even with high accuracy. |
| first_indexed | 2024-03-12T14:38:01Z |
| format | Article |
| id | doaj.art-390a3c56698d471b86e877616038bffd |
| institution | Directory Open Access Journal |
| issn | 2187-9745 |
| language | English |
| last_indexed | 2024-03-12T14:38:01Z |
| publishDate | 2023-07-01 |
| publisher | The Japan Society of Mechanical Engineers |
| record_format | Article |
| series | Mechanical Engineering Journal |
| spelling | doaj.art-390a3c56698d471b86e877616038bffd2023-08-17T02:40:07ZengThe Japan Society of Mechanical EngineersMechanical Engineering Journal2187-97452023-07-0110423-0006623-0006610.1299/mej.23-00066mejDevelopment of neural network potential for Al-based alloys containing vacancyJia ZHAO0Yutaro MAEDA1Kenjiro SUGIO2Gen SASAKI3Graduate School of Advanced Science and Engineering, Hiroshima UniversityGraduate School of Advanced Science and Engineering, Hiroshima UniversityGraduate School of Advanced Science and Engineering, Hiroshima UniversityGraduate School of Advanced Science and Engineering, Hiroshima UniversityPotential energy of an alloy is an essential indicator for evaluating the stability of the structure in predicting new materials. Therefore, how to calculate the potential energy in material design has become an inevitable problem. While first-principles calculations can provide chemical accuracy for arbitrary atomic arrangements, they are prohibitive in terms of computational effort and time. To enable atomistic-level simulations of both the processing and performance of Aluminum alloys, neural network potential was proposed to predict the binding energy of vacancy-containing aluminum alloys in a highly accurate state. This method combined first-principles calculations and machine learning techniques to explore the intrinsic link between solid solution structure and binding energies. In this study, four binary alloys (aluminum-silicon, aluminum- zirconium, aluminum-magnesium and aluminum-titanium alloys) were investigated. The mean squared errors were used to quantify the quality of the neural network potential models and it was found that the trained model is more stable and exhibits high accuracy for energy prediction. The Monte Carlo simulation results show that using this neural network potential successfully simulated aging process of aluminum alloys, and the neural network potential can be much faster than first-principles calculations, even with high accuracy.https://www.jstage.jst.go.jp/article/mej/10/4/10_23-00066/_pdf/-char/enmachine learningmonte carlo methodfirst-principles calculationbinding energyaluminum alloysvacancy |
| spellingShingle | Jia ZHAO Yutaro MAEDA Kenjiro SUGIO Gen SASAKI Development of neural network potential for Al-based alloys containing vacancy Mechanical Engineering Journal machine learning monte carlo method first-principles calculation binding energy aluminum alloys vacancy |
| title | Development of neural network potential for Al-based alloys containing vacancy |
| title_full | Development of neural network potential for Al-based alloys containing vacancy |
| title_fullStr | Development of neural network potential for Al-based alloys containing vacancy |
| title_full_unstemmed | Development of neural network potential for Al-based alloys containing vacancy |
| title_short | Development of neural network potential for Al-based alloys containing vacancy |
| title_sort | development of neural network potential for al based alloys containing vacancy |
| topic | machine learning monte carlo method first-principles calculation binding energy aluminum alloys vacancy |
| url | https://www.jstage.jst.go.jp/article/mej/10/4/10_23-00066/_pdf/-char/en |
| work_keys_str_mv | AT jiazhao developmentofneuralnetworkpotentialforalbasedalloyscontainingvacancy AT yutaromaeda developmentofneuralnetworkpotentialforalbasedalloyscontainingvacancy AT kenjirosugio developmentofneuralnetworkpotentialforalbasedalloyscontainingvacancy AT gensasaki developmentofneuralnetworkpotentialforalbasedalloyscontainingvacancy |