摘要
运用连续型Ｈｏｐｆｉｌｅｄ网络以及连续双向联想存储器（ＢＡＭ）详述结构分析的两种新方法。新的方法是建立在比较上述两种方法的能量函数与结构位移法的能量函数（也就是所谓的刚度矩阵法）的关系基础上的，并且利用了人工神经网络所具备且优于经典数值方法的计算特点。几个相关结构分析的例子说明了以ＢＡＭ为基础的神经网络优于其他传统的数值方法及Ｈｏｐｆｉｅｌｄ模型。
We use the continuous
Hopfield networks and the continuous bi directional associative memory system (BAM) in order
to develop two novel methods for structural analysis. The development of the technique is
based on the analogous relationship that results comparing the energy functions of the above
two models with that of the structural displacement method and it takes advantage of the fact
that classical numerical methods do not have the characteristics of parallel computation that
artificial neural networks have. Two examples to illustrate the superiority of BAM based
method over other traditional numerical methods and the Hopfield model.
基金
国家"九五"重点科技攻关项目
