基于机器学习及智能算法的Au_(20)原子团簇最稳态结构的研究  

Based on Machine Learning and Intelligent Algorithms for Au_(20) Clusters the Study of the most Stable Structure

作　　者：李超 熊桢 肖舒晴 王强 刘森 周才英[1] LI Chao;XIONG Zhen;XIAO Shuqing;WANG Qiang;LIU Sen;ZHOU Caiying(College of Science,Jiangxi University of Science and Technology,Ganzhou 341000,China)

机构地区：[1]江西理工大学理学院,江西赣州341000

出　　处：《数字通信世界》2021年第9期6-7,共2页Digital Communication World

基　　金：江西省教育厅科学技术研究项目:滑坡类地质灾害智能监测与预警系统的研发,项目编号:GJJ180448。

摘　　要：团簇是一种介于原子、分子与宏观固体之间的物质结构层次,其性质在很多领域都有深远影响。以Au_(20)原子团簇为代表,基于机器学习算法建立团簇能量的预测模型,构建原子团簇结构和能量的映射关系,拟合程度R2接近0.81。结合智能算法,对Au_(20)的原子团簇最稳态结构进行搜索,最终得到Au_(20)的最稳态结构为金字塔型,属于对称型结构,具有较好的稳定性。Clusters are a kind of material structure level between atoms,molecules and macroscopic solids,and their properties have far reaching effects in many fi elds.This paper takes Au_(20) atomic clusters as a representative,and establishes a mathematical model for cluster energy prediction based on machine learning algorithms.Construct the mapping relationship between atomic cluster structure and energy,and the fitting degree R^(2) is close to 0.81.Combined with the intelligent optimization algorithm,the most stable structure of Au_(20)'s atomic clusters is searched,and fi nally the most stable structure of Au_(20) is a pyramid type,which is a symmetrical structure and has good stability.

关 键 词：智能优化算法 机器学习 原子团簇 最稳态结构预测 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]