ZA22/Al_2O_(3f) 复合材料机械性能的神经网络模拟研究  

NEURAL NETWORK SIMULATION ON MECHANICAL PROPERTIES OF ZA22/Al_2O_3f COMPOSITES

作　　者：陈凯[1,2] 俞蒙槐[1,2] 胡上序[1,2] 于思荣[1,2] 何镇明[1,2] 

机构地区：[1]浙江大学化工系计算中心 [2]吉林工业大学金属材料工程系

出　　处：《复合材料学报》1997年第4期81-84,共4页Acta Materiae Compositae Sinica

基　　金：国家自然科学基金

摘　　要：采用人工神经网络的典型模型即Ｂ－Ｐ算法对ＺＡ２２／Ａｌ２Ｏ３ｆ复合材料的机械性能进行分析和预测，结果表明：Ｂ－Ｐ模型不仅适用于单变量输出非线性系统的拟合与预测，同时还适用于多变量输出的非线性系统；Ｂ－Ｐ模型对研究复合材料ＺＡ２２／Ａｌ２Ｏ３ｆ的机械性能有良好容错性。The typical model of neural network e.g. BP algorithm was adopted to analyze as well as predict the mechanical properties of ZA22/Al_2O_3f composites. The results show that BP model is not only suitable for the regression and prediction for the single variable output nonlinear system, but also suitable for the multivariables output nonlinear system. Perfect fault tolerance ability was also found in the BP model while it was used to analyze the mechanical properties of ZA22/Al2O3f composites.

关 键 词：锌铝合金 复合材料 机械性能 神经网络 

分 类 号：TB331.023[一般工业技术—材料科学与工程]