摘要
复合材料层合板的刚度退化相当复杂,并且是非线性的,目前缺乏足够的理论依据,很难按实际情况计算。本文从神经网络的角度出发,借助于神经网络的自适应性,通过对材料的实际载荷和实测应变值进行学习,使网络掌握其中各层的刚度变化规律。并且通过数值仿真和实验验证,证明此方法是完全可行的。
In this paper, a new computational ply modulus degenerate method is presented for the composites laminations. Using adaptive linear neural networks and composite mechanic theory, all plies group modulus values are obtained in terms of the actual stress and strain of the laminations. The numerical example and the experiment results are used to demonstrate the effectiveness of the method.
出处
《航空计算技术》
2006年第4期100-104,共5页
Aeronautical Computing Technique
关键词
复合材料层合板
刚度退化
神经网络
composite materials lamination
ply modulus degeneration
neural networks
