Artificial neural network molecular mechanics of iron grain boundaries
Artificial neural network molecular mechanics of iron grain boundaries
复制标题
铁晶界的人工神经网络分子力学
DOI：
10.1016/j.scriptamat.2021.114268
复制
发表时间：
2022
影响因子：
6
通讯作者：
Mori Hideki
中科院分区：
文献类型：
--
作者：
Shiihara Yoshinori;Kanazawa Ryosuke;Matsunaka Daisuke;Lobzenko Ivan;Tsuru Tomohito;Kohyama Masanori;Mori Hideki
本文报道了基于人工神经网络（ANN）势的分子力学计算α-铁中46个对称倾斜晶界（GB）能，并将计算结果与基于密度泛函理论（DFT）、嵌入原子法（EAM）和改进的EAM （MEAM）计算结果进行了比较。神经网络电位的结果与DFT的结果非常吻合（平均为5%），而EAM和MEAM的结果与DFT的结果有显著差异（平均约为27%）。在∑3(1 1¯2)GB的单轴拉伸计算中，ANN电位再现了DFT中观察到的GB脆性断裂倾向，而EAM和MEAM则错误地表现出延性行为。这些结果证明了人工神经网络势在计算铁的晶界方面的有效性，这在现代工业中有很高的需求。
This study reports grain boundary (GB) energy calculations for 46 symmetric-tilt GBs in α-iron using molecular mechanics based on an artificial neural network (ANN) potential and compares the results with calculations based on the density functional theory (DFT), the embedded atom method (EAM), and the modified EAM (MEAM). The results by the ANN potential are in excellent agreement with those of the DFT (5% on average), while the EAM and MEAM significantly differ from the DFT results (about 27% on average). In a uniaxial tensile calculation of∑ 3 (1 1¯ 2) GB, the ANN potential reproduced the brittle fracture tendency of the GB observed in the DFT while the EAM and MEAM mistakenly showed ductile behaviors. These results demonstrate the effectiveness of the ANN potential in calculating grain boundaries of iron, which is in high demand in modern industry.