摘要
本工作通过选取适当的拓朴结构，特别是对零电阻转变温度Ｔｃ的数据采用压缩与还原的技术处理，建立了一个基于误差反向传播（简记为Ｂ－Ｐ）算法的人工神经网络。该网络可根据制备含Ｆ铋系高温超导材料的几个主要实验参数，相当精确地预言此类超导体的Ｔｃ。本方法显然具有一般意义，从而有力地促进了材料的计算机辅助设计的研究工作，使之进一步趋于成熟。
By selecting a proper topologic structure, especially by compressing and reducing the T.data,we have established an ANN(artificial neural network) Based on the B-P learning algorithm, which can be used to predict guite accurately To of the F-droped ceramic supercondoctors from some of their experimental parameters. The present work is of generality and thus has prompted the development of computer-aided materials design.
出处
《苏州科技学院学报（社会科学版）》
1996年第1期1-5,共5页
Journal of University of Science and Technology of Suzhou:Social Science
