计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (16): 46-47.DOI: 10.3778/j.issn.1002-8331.2010.16.013

• 研究、探讨 • 上一篇    下一篇

Hopfield神经网络在有限元求解中的应用

崔立堃1,2,王 伟1,李 卓3   

  1. 1.内蒙古工业大学 理学院,呼和浩特 010051
    2.呼和浩特职业学院,呼和浩特 010051
    3.内蒙古动力机械研究所,呼和浩特 010050
  • 收稿日期:2009-01-06 修回日期:2009-02-19 出版日期:2010-06-01 发布日期:2010-06-01
  • 通讯作者: 崔立堃

Application of Hopfield neural network in finite element solving

CUI Li-kun1,2,WANG Wei1,LI Zhuo3   

  1. 1.College of Science of Inner Mongolia University of Technology,Huhhot 010051,China
    2.Huhhot Vocational College,Huhhot 010051,China
    3.Inner Mongolia Dynamical Machine Academy,Huhhot 010050,China
  • Received:2009-01-06 Revised:2009-02-19 Online:2010-06-01 Published:2010-06-01
  • Contact: CUI Li-kun

摘要: 计算机本身固有的计算与存储之间是一对很难解决的矛盾,许多工程力学问题因计算规模大等原因还没有突破性进展,因此,需要发展新的理论与计算方法。通过对有限元求解方法和Hopfield神经网络的深入研究,在对Hopfield神经网络适当改造后,得到了有限元的神经网络计算方法,在电路实现中避免了采用高增益传递函数的假设,进而在理论上实现了有限元神经网络计算的无误差求解。

Abstract: There is an unsolved contradiction between the computation and memory of the Von Neumann computer.So many problems of engineering mechanics haven’t breakthrough because of such reason as large computation scale,etc.Therefore,new theory and method of computational mechanics need to be developed to solve above problems.Solving method of finite element and neural network design are studied.The neural network of finite element solving is obtained on the basis of Hopfield neural network that is reformed and avoids using of high-gain transfer function in the circuit.Then the no error solving of finite element neural net computation is realized in theory.

中图分类号: