高等学校化学学报 ›› 1996, Vol. 17 ›› Issue (5): 698.

• 论文 • 上一篇    下一篇

人工神经网络用于预测离子交换分配系数

刘满仓, 张海霞, 张瑞生, 张丽华, 胡之德   

  1. 兰州大学化学系, 兰州 730000
  • 收稿日期:1995-05-29 出版日期:1996-05-24 发布日期:1996-05-24
  • 通讯作者: 胡之德
  • 作者简介:刘满仓,男,51岁,副教授.

The Prediction of Cation Exchange Distribution Coefficients with Artificial Neural Network

LIU Man-Cang, ZHANG Hai-Xia, ZHANG Rui-Sheng, ZHANG Li-Hua, HU Zhi-De   

  1. Department of Chemistry, Lanzhou University, Lanzhou 730000
  • Received:1995-05-29 Online:1996-05-24 Published:1996-05-24

摘要: 用前向网络和扩展的delta-bar-delta算法对主族特征价阳离子的离子交换分配系数(Kd)进行了预测,对网络结构、学习次数进行了优化并研究了学习集的大小。1nKd的均方根偏差(RMS)小于7%.

关键词: 离子交换, 分配系数, 人工神经网络

Abstract: The ion exchange distribution coefficients of cat ions having characteristie valence in main groups were predicted by using extented delta-bar-delta neural networks, The effect of structure of network, the learning Epochs and the size of learning set on predicted results was investigated.The suitable conditions are;input nodes 4; output node; 1; the learning epochs; 3000; the size of learning set;112.The RMS(root-mean-square error) is smaller than 7%under the suitable conditios.

Key words: Cation exchange, Distribution coefficient, Artificial neural networks

TrendMD: