高级检索
无机材料学报

无机材料学报

• 研究论文 • 上一篇    下一篇

矿渣微晶玻璃材料设计神经网络模型

文岐业1; 张培新2,3; 张怀武1   

  1. 1. 电子科技大学微电子与固体电子学院, 成都 610054; 2. 深圳大学师范学院化学与生物学系, 深圳 518060; 3. 广西大学化学化工学院,市南宁 530004
  • 收稿日期:2002-03-18 修回日期:2002-04-15 出版日期:2003-05-20 网络出版日期:2003-05-20

Applications of Artificial Neural Network in Slag Glass-Ceramic Expert System

WEN Qi-Ye1; ZHANG Pei-Xin2,3; ZHANG Huai-Wu1   

  1. 1. College of Micro-Electronic and Solid-Electronic; University of Electronic Science and Technology of China; Chengdu 610054; China; 2. Normal College; Shenzhen University; Shenzhen 518060, Chiina; 3. College of Chemistry and Chemical Engineering; Guangxi University; Nanning 530004; China
  • Received:2002-03-18 Revised:2002-04-15 Published:2003-05-20 Online:2003-05-20

PDF (PC)

931

被引次数

17

摘要： 研究了人工神经网络在矿渣微晶玻璃材料设计中的应用。采用基于变尺度法的新学习算法建立了三层前馈型神经网络,发现当网络结构为M-2M-1,取一定范围内的学习误差时,网络具有很好的学习效果。研究证明,建立的人工神经网络模型学习速度快,收敛稳定,强壮性好,能根据较少的实验样本有效抽取矿渣微晶玻璃组成、工艺和性能之间的内在规律,是进行微晶玻璃材料设计的有力工具。

关键词: 人工神经网络, 矿渣微晶玻璃, 材料设计

Abstract: Artificial neural network was introduced into slag glass-ceramic material designing. A 3 layers feedforward network was built with a new robust learning algorithm,
based on a concept of “entire error modifying”. The network has a excellent learning ability when its topology is M-2M-1 and
an appropriate study error chosen. The research results show that this slag glass-ceramic neural network is robust, quick and stable in training
and data predicting, which can disclose the relationship of elemental compositions, structure and material properties of slag glass-ceramic
effectively, even if some parameters are absent in samples.

Key words: artificial neural network, slag glass-ceramic, material designing

中图分类号: