您的位置:首页  > 论文页面

基于因子分析的BP神经网络在微孔化合物定向合成中的应用

发表时间:2010-03-15  浏览量:1989  下载量:899
全部作者: 霍卫峰,李激扬,于吉红,徐如人
作者单位: 吉林大学化学学院无机合成与制备化学国家重点实验室
摘 要: 针对微孔晶体化合物的定向合成问题,提出先利用因子分析方法对数据进行预处理,抽取公共因子,然后再建立神经网络预测模型的挖掘过程模式。经过无机微孔晶体合成反应数据库测试,结果表明:该方法极大地缩减了数据规模,并且明显地提高了定向合成预测的准确率,达到 86.58%.这对微孔化合物的定向合成研究有一定的指导意义。
关 键 词: 无机化学;数据挖掘;误差逆传播神经网络;因子分析;定向合成
Title: Application of BP neural network based on factor analysis on rational synthesis of microporous materials
Author: HUO Weifeng, LI Jiyang, YU Jihong, XU Ruren
Organization: State Key Laboratory of Inorganic Synthesis and Preparative Chemistry, College of Chemistry,Jilin University
Abstract: Aiming at the directional synthesis problem of microporous crystal compounds, this work presents a new mode of data mining process in which the pretreatment by factor analysis was used to reduce the redundant attributes and then the back propagation (BP) neural network built with these factors as input was used to predict the type of the products. The application of such method on the analysis of the synthesis data of aluminiumphosphate shows that the method can not only diminish computation, but also build product predicting model which has good predicting capacity. The prediction correct rate is 86.58%. This work will further assist in rational synthesis of microporous materials.
Key words: inorganic chemistry; data mining; back propagation neural network; factor analysis; rational synthesis
发表期数: 2010年3月第5期
引用格式: 霍卫峰,李激扬,于吉红,等. 基于因子分析的BP神经网络在微孔化合物定向合成中的应用[J]. 中国科技论文在线精品论文,2010,3(5):462-467.
 
0 评论数 0
暂无评论
友情链接