| 神经网络用于精确预言含F铋系高温超导的T_C |
| |
| 引用本文： | 潘涛,彭石安.神经网络用于精确预言含F铋系高温超导的T_C[J].苏州科技学院学报(社会科学版),1996(1). |
| |
| 作者姓名： | 潘涛 彭石安 |
| |
| 作者单位： | 苏州铁道师范学院物理系 苏州215009 |
| |
| 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 T_c 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 T_c。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。
|
| 关 键 词： | 人工神经网络 B-P 学习算法 材料设计 零电阻转换温度 T(?) |
ANN Applied to Predict Accurately T_C of BiPbSrCaCuOF Superconductors |
| |
| Pan Tao Peng Shian.ANN Applied to Predict Accurately T_C of BiPbSrCaCuOF Superconductors[J].Journal of University of Science and Technology of Suzhou:Social Science,1996(1). |
| |
| Authors: | Pan Tao Peng Shian |
| |
| Abstract: | By selecting a proper topologie structure,especially by compressing and re- ducing the Tcdata,we have established an ANN(artificial neural network)Based on the B-P learning algorithm,which can be used to predict guite accurately Tc of the F-droped ceramic supercondoctors from some of their experimental parameters.The present work is of gener- ality and thus has prompted the development of computer-aided materials design. |
| |
| Keywords: | Artifcal neural network Back Propagation algorithm Material design Ceramic temperature |
| 本文献已被 CNKI 等数据库收录！ |
