| 运用机器学习方法设计原子链 人工边界条件 |
| |
| 引用本文： | 张慊,乔丹,唐少强. 运用机器学习方法设计原子链 人工边界条件[J]. 力学与实践, 2020, 42(1): 13-16. DOI: 10.6052/1000-0879-19-412 |
| |
| 作者姓名： | 张慊 乔丹 唐少强 |
| |
| 作者单位： | 北京大学工学院力学与工程科学系;北京大学数学科学学院概率统计系 |
| |
| 基金项目： | 1) 国家自然科学基金资助项目(11832001) |
| |
| 摘 要： | 本文运用机器学习方法设计一维线性原子链的人工边界条件。该方法基于前馈神经网络,通过对一小部分数值解进行训练后得到人工边界条件。应用该法不需要较多先验知识,编程简单,实现速度快,算例表明数值反射较小。
|
| 关 键 词： | 分子动力学模拟 人工边界条件 机器学习 前馈神经网络 |
| 收稿时间： | 2019-11-11 |
DESIGNING ARTIFICIAL BOUNDARY CONDITIONS FOR ATOMIC CHAINS BY MACHINE LEARNING 1) |
| |
| ZHANG Qian,QIAO Dan,TANG Shaoqiang. DESIGNING ARTIFICIAL BOUNDARY CONDITIONS FOR ATOMIC CHAINS BY MACHINE LEARNING 1)[J]. Mechanics and Engineering, 2020, 42(1): 13-16. DOI: 10.6052/1000-0879-19-412 |
| |
| Authors: | ZHANG Qian QIAO Dan TANG Shaoqiang |
| |
| Affiliation: | (Department of Mechanics and Engineering Science,College of Engineering,Peking University,Beijing 100871,China;Department of Probability and Statistics,School of Mathematical Sciences,Peking University,Beijing 100871,China) |
| |
| Abstract: | In this paper, we adopt machine learning techniques to design artificial boundary conditions for one-dimensional linear atomic chain. Training a feedforward neural network with a small amount of numerical solutions, we obtain artificial boundary conditions. This approach requires little prior information, and programming and computation are fast. Numerical examples illustrate a relatively small reflection. |
| |
| Keywords: | molecular dynamics simulation artificial boundary conditions machine learning feedforward neural network |
| 本文献已被 维普 等数据库收录！ |
| 点击此处可从《力学与实践》浏览原始摘要信息 |
|
点击此处可从《力学与实践》下载全文 |
