无机材料学报

• 研究论文 • 上一篇    下一篇

用人工神经网络对PZT陶瓷进行性能分析与优化

郭栋; 齐西伟; 李龙土; 南策文; 桂治轮   

  1. 清华大学材料系新型陶瓷与精细工艺国家重点实验室 北京 100084
  • 收稿日期:2002-11-18 修回日期:2003-01-13 出版日期:2004-01-20 网络出版日期:2004-01-20

Property Analysis and Optimization of PZT Ceramic Material Throughan ANN Method

GUO Dong; QI Xi-Wei; LI Long-Tu; NAN Ce-Wen; .GUI Zhi-Lun   

  1. Dept. Materials Science & Engineering; Tsinghua University; Beijing 100084; China
  • Received:2002-11-18 Revised:2003-01-13 Published:2004-01-20 Online:2004-01-20

摘要: 选取了几种常用的金属氧化物掺杂剂,在均匀实验结构的基础上用人工神经网络方法对掺杂PZT陶瓷的性能进行分析和优化.实验结果表明,掺杂PZT体系的人工神经网络模型要比多重非线形回归模型准确得多,而且以人工神经网络模型为指导对材料进行优化后的性能预测也比较准确,说明人工神经网络在陶瓷这种多组分固溶体材料的性能分析中具有良好的使用前景.

关键词: 压电陶瓷, 人工神经网络, 误差反向传播算法, 电学性能

Abstract: Artificial neural network (ANN) technique was applied to model the PZT based piezoelectric ceramics system. After selecting several dopants, the experimental results of 21 PZT
samples were analyzed by a BP network based on the homogenous experimental design. Calculated results indicated that the ANN model was much more accurate than multiple
nonlinear regression analysis (MNLR) model for the same set of data. Optimized formulations were also calculated and the optimized d33 and Kp output values agreed well with predicted values. These results suggest that the ANN based modeling is a very
useful tool in dealing with problems with serious non-linearity encountered in the property analysis of the complicated solid solution material.

Key words: piezoelectric ceramics, artificial neural network, back-propagation algorithm, electrical properties

中图分类号: