English

应用科学学报 ›› 1996, Vol. 14 ›› Issue (3): 375-378.

• 论文 • 上一篇    

人工神经网络法用于V-PTC材料诸性能的预报

陆文聪1, 阎立诚1, 陈念贻2   

  1. 1. 上海大学, 嘉定校区;
    2. 中国科学院上海冶金研究所
  • 收稿日期:1994-12-29 修回日期:1995-04-04 出版日期:1996-09-30 发布日期:1996-09-30
  • 作者简介:陆文聪:讲师,上海大学,嘉定校区化学系,上海 201800

ARTIFICIAL NEURAL NETWORK METHOD APPLIED TO PREDICTION OF MULTIPLE PROPERTIES OF V PTC MATERIALS

LU WENCONG1, YAN LICHENG1, CHEN NIANYI2   

  1. 1. Shanghai University Jiading Oampus;
    2. Shanghai Institute of Metallurgy, Academia Sinica, Shanghai
  • Received:1994-12-29 Revised:1995-04-04 Online:1996-09-30 Published:1996-09-30

PDF

128

被引次数

8

摘要： 人工神经网络(Artificial Neural Networks,ANNs)是一类试图模拟生物体神经系统结构的新型信息处理系统.文中用反向传播网络研究V-PTC材料诸性能与其配方及工艺间的关系,通过B-P算法建立了V-PTC材料诸性能与其配方及工艺间的非线性映照关系,根据V-PTC材料的优化配方和工艺条件,计算机预报相应材料诸性能的结果与实验值相一致.

关键词: 人工神经网络, V-PTC材料, 模式识别, 计算机化学

Abstract: The Artificial Neural Network is a new type of information processing system based on modelling the neural system structure of the human brain. It can be used to extract useful information from the experimental data of V-PTC materials. The nonlinear relationships between the multiple properties and the affecting factors including technical conditions and compositions are available by using the B-P algorithm. The results of computer-aided prediction of the multiple properties of V-PTC materials have been proved to be consistent with the experimental values.

Key words: V-PRC materials, artificial neural network, computational chemistry, pattern recognition