Predicting the energetics and kinetics of Cr atoms in Fe-Ni-Cr alloys via physics-based machine learning
Predicting the energetics and kinetics of Cr atoms in Fe-Ni-Cr alloys via physics-based machine learning
复制标题
DOI：
10.1016/j.scriptamat.2021.114177
复制
发表时间：
2021-12
影响因子：
6
通讯作者：
Yuchu Wang;B. Ghaffari;C. Taylor;S. Lekakh;Mei Li;Yue Fan
中科院分区：
文献类型：
--
作者：
Yuchu Wang;B. Ghaffari;C. Taylor;S. Lekakh;Mei Li;Yue Fan
奥氏体合金中铬原子的能量和活化势垒分布通过多种化学（例如固溶体与偏析态）和微观结构（例如块体与晶界）环境中的多个建模样本进行研究。借助基于物理的机器学习算法，发现可以根据局域电负性 (χ) 和局域原子堆积自由体积 (V v) 可靠地预测 Cr 原子的热力学和动力学行为。建立了 χ− V v 参数空间中相应的预测图，该预测图与现有实验一致，并通过不同原子间力场的并行建模进行了验证。还讨论了本研究对于指导具有所需性能的奥氏体合金设计的潜力的影响。
The energy and activation barrier distributions of Cr atoms in austenitic alloys are investigated over a multiplicity of modeling samples across a wide range of chemical (eg solid solutions vs. segregated states) and microstructural (eg bulk vs. grain boundaries) environments. Assisted with a physics-based machine learning algorithm, it is found that the thermodynamic and kinetic behaviors of Cr atoms can be reliably predicted according to the local electronegativity (χ) and free volume of local atomic packing (V v). The corresponding predictive maps in the χ− V v parameter space are established, which are in line with existing experiments and validated by a parallel modeling with a different interatomic force field. The implications of the present study regarding its potential to guide the design of austenitic alloys with desired properties are also discussed.