Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys
Al-Li alloys are widely used in aerospace applications due to their high strength, high fracture toughness, and strong resistance to stress corrosion. However, the lack of interatomic potentials has hindered systematic investigations of the relationship between structures and properties. To address...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4701/15/1/48 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587916767920128 |
|---|---|
| author | Fei Chen Han Wang Yanan Jiang Lihua Zhan Youliang Yang |
| author_facet | Fei Chen Han Wang Yanan Jiang Lihua Zhan Youliang Yang |
| author_sort | Fei Chen |
| collection | DOAJ |
| description | Al-Li alloys are widely used in aerospace applications due to their high strength, high fracture toughness, and strong resistance to stress corrosion. However, the lack of interatomic potentials has hindered systematic investigations of the relationship between structures and properties. To address this issue, we apply a neural network-based neuroevolutionary machine learning potential (NEP) and use evolutionary strategies to train it for large-scale molecular dynamics (MD) simulations. The results obtained from this potential function are compared with those from Density Functional Theory (DFT) calculations, with training errors of 2.1 meV/atom for energy, 47.4 meV/Å for force, and 14.8 meV/atom for virial, demonstrating high training accuracy. Using this potential, we simulate cluster formation and the high-temperature stability of the T1 phase, with results consistent with previous experimental findings, confirming the accurate predictive capability of this potential. This approach provides a simple and efficient method for predicting atomic motion, offering a promising tool for the thermal treatment of Al-Li alloys. |
| format | Article |
| id | doaj-art-4da769b61e4e440392e84df350354d0b |
| institution | Kabale University |
| issn | 2075-4701 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metals |
| spelling | doaj-art-4da769b61e4e440392e84df350354d0b2025-01-24T13:41:31ZengMDPI AGMetals2075-47012025-01-011514810.3390/met15010048Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li AlloysFei Chen0Han Wang1Yanan Jiang2Lihua Zhan3Youliang Yang4School of Mechanical Engineering and Automation, College of Science and Technology, Ningbo University, Ningbo 315000, ChinaSchool of Mechanical Engineering and Automation, College of Science and Technology, Ningbo University, Ningbo 315000, ChinaSchool of Mechanical Engineering and Automation, College of Science and Technology, Ningbo University, Ningbo 315000, ChinaLight Alloy Research Institute of Central South University, Central South University, Changsha 410083, ChinaLight Alloy Research Institute of Central South University, Central South University, Changsha 410083, ChinaAl-Li alloys are widely used in aerospace applications due to their high strength, high fracture toughness, and strong resistance to stress corrosion. However, the lack of interatomic potentials has hindered systematic investigations of the relationship between structures and properties. To address this issue, we apply a neural network-based neuroevolutionary machine learning potential (NEP) and use evolutionary strategies to train it for large-scale molecular dynamics (MD) simulations. The results obtained from this potential function are compared with those from Density Functional Theory (DFT) calculations, with training errors of 2.1 meV/atom for energy, 47.4 meV/Å for force, and 14.8 meV/atom for virial, demonstrating high training accuracy. Using this potential, we simulate cluster formation and the high-temperature stability of the T1 phase, with results consistent with previous experimental findings, confirming the accurate predictive capability of this potential. This approach provides a simple and efficient method for predicting atomic motion, offering a promising tool for the thermal treatment of Al-Li alloys.https://www.mdpi.com/2075-4701/15/1/48Al-Cu-Li alloyneuroevolution machine learning potentialmolecular dynamics simulationprecipitationaging forming |
| spellingShingle | Fei Chen Han Wang Yanan Jiang Lihua Zhan Youliang Yang Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys Metals Al-Cu-Li alloy neuroevolution machine learning potential molecular dynamics simulation precipitation aging forming |
| title | Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys |
| title_full | Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys |
| title_fullStr | Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys |
| title_full_unstemmed | Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys |
| title_short | Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys |
| title_sort | development of a neuroevolution machine learning potential of al cu li alloys |
| topic | Al-Cu-Li alloy neuroevolution machine learning potential molecular dynamics simulation precipitation aging forming |
| url | https://www.mdpi.com/2075-4701/15/1/48 |
| work_keys_str_mv | AT feichen developmentofaneuroevolutionmachinelearningpotentialofalculialloys AT hanwang developmentofaneuroevolutionmachinelearningpotentialofalculialloys AT yananjiang developmentofaneuroevolutionmachinelearningpotentialofalculialloys AT lihuazhan developmentofaneuroevolutionmachinelearningpotentialofalculialloys AT youliangyang developmentofaneuroevolutionmachinelearningpotentialofalculialloys |