| Hopfield神经网络在有限元求解中的应用 |
| |
| 引用本文： | 崔立堃,王伟,李卓. Hopfield神经网络在有限元求解中的应用[J]. 计算机工程与应用, 2010, 46(16): 46-47. DOI: 10.3778/j.issn.1002-8331.2010.16.013 |
| |
| 作者姓名： | 崔立堃 王伟 李卓 |
| |
| 作者单位： | 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 |
| |
| 基金项目： | 内蒙古自治区自然科学基金，内蒙古自治区高等学校科学研究项目 |
| |
| 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。
|
| 关 键 词： | Hopfield 神经网络 有限元 |
| 收稿时间： | 2009-01-06 |
| 修稿时间： | 2009-2-19 |
Application of Hopfield neural network in finite element solving |
| |
| CUI Li-kun,WANG Wei,LI Zhuo. Application of Hopfield neural network in finite element solving[J]. Computer Engineering and Applications, 2010, 46(16): 46-47. DOI: 10.3778/j.issn.1002-8331.2010.16.013 |
| |
| Authors: | CUI Li-kun WANG Wei LI Zhuo |
| |
| Affiliation: | 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 |
| |
| 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. |
| |
| Keywords: | Hopfield neural network finite element |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
