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. BP algorithm was adopted to analyze as well as predict the mechanical properties of ZA22/Al_2O_3f composites. The results show that BP model is not only suitable for the regression and prediction for the single variable output nonlinear system, but also suitable for the multivariables output nonlinear system. Perfect fault tolerance ability was also found in the BP model while it was used to analyze the mechanical properties of ZA22/Al2O3f composites.
出处
《复合材料学报》
EI
CAS
CSCD
北大核心
1997年第4期81-84,共4页
Acta Materiae Compositae Sinica
基金
国家自然科学基金
关键词
锌铝合金
复合材料
机械性能
神经网络
ZA22 alloy, composite, mechanical property, neural network
