Calculation and prediction of sliding energy barriers by ffrst-principles combined with machine learning | |
Department | 固体润滑国家重点实验室(LSL) |
Yuan Niu; Yun Wang; Minjuan He; Wenhao He; Zhenghua Zha; Zhibin Lu | |
The second department | 216计算摩擦学课题组 |
2023-05-05 | |
Source Publication | Ceramics International |
Issue | 49Pages:24752–24761 |
Abstract | Recently, many novel two-dimensional materials have been identiffed through data-driven computational methods, whose tribological properties are bound to be further investigated. Here, the ffrst principles calculation and machine learning were combined to predict the maximum sliding potential barrier of elemental twodimensional materials and the importance of different descriptors were discussed. Due to literature reports and high correlation coefffcients, RF and Bagging algorithms are used to present the ffnal prediction results. The prediction results show that R2 is about 0.8, and the root mean square error (RMSE) of ~0.0027 eV and 0.0029 eV, respectively. Importantly, when considering the interfacial charge transfer as the eigenvalue, the R2 of both models increased (R2 can reach 0.89), and the RMSEs decreased to˜0.0020 eV and 0.0024 eV. This indicates that interfacial charge transfer has a signiffcant impact on the prediction of the maximum sliding energy barrier. That is, adjusting the charge transfer at the interface can improve the tribological properties of the interface. In addition, the geometric structure, such as lattice parameter, and mechanical properties of the material are also important factors affecting its maximum sliding energy barrier. Compared with traditional ffrst principles calculation, machine learning based on statistics may be a promising choice for predicting friction performance, and it is expected to ffnd the inffuencing factors directly related to friction behavior. |
Keyword | First-principles calculations Machine learning Maximum sliding energy barrier Elemental 2D materials Friction Interfacial charge transfer |
If | 5.2 |
compositor | 第一作者单位 |
Document Type | 期刊论文 |
Identifier | http://ir.licp.cn/handle/362003/30639 |
Collection | 固体润滑国家重点实验室(LSL) |
Corresponding Author | Wenhao He; Zhibin Lu |
Affiliation | 1.State Key Laboratory of Solid Lubrication, Lanzhou Institute of Chemical Physics, Chinese Academy of Sciences 2.Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences 3.Scientiffc Data Center, Lanzhou Institute of Chemical Physics, Chinese Academy of Sciences 4.School of Information and Control, Xi’an University of Architecture and Technology 5.Petrochina Lanzhou Lube Oil R&D Institute |
Recommended Citation GB/T 7714 | Yuan Niu,Yun Wang,Minjuan He,et al. Calculation and prediction of sliding energy barriers by ffrst-principles combined with machine learning[J]. Ceramics International,2023(49):24752–24761. |
APA | Yuan Niu,Yun Wang,Minjuan He,Wenhao He,Zhenghua Zha,&Zhibin Lu.(2023).Calculation and prediction of sliding energy barriers by ffrst-principles combined with machine learning.Ceramics International(49),24752–24761. |
MLA | Yuan Niu,et al."Calculation and prediction of sliding energy barriers by ffrst-principles combined with machine learning".Ceramics International .49(2023):24752–24761. |
Files in This Item: | ||||||
File Name/Size | DocType | Version | Access | License | ||
luwen_5.pdf(9962KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | View Application Full Text |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment