| 用模糊神经网络求解多级交换网路由重排问题 |
| |
| 引用本文： | 郑佩,郑君里.用模糊神经网络求解多级交换网路由重排问题[J].清华大学学报(自然科学版),1997(1). |
| |
| 作者姓名： | 郑佩 郑君里 |
| |
| 作者单位： | 清华大学电子工程系 |
| |
| 摘 要： | 研究利用人工神经网络求解多级交换网路由重排问题，提出了一种求解路由重排问题的模糊控制神经网络算法。大量的计算机模拟结果表明，该算法与其它同类算法相比较具有收敛速度快，结果有效性高，自适应性强等特点。利用ＴＭＳ３２０Ｃ３０数字信号处理器构成了虚拟硬件系统，实时实现了多级交换网路由重排控制器，理论计算与测试结果一致。该工作为神经网络与模糊系统相结合探索了一条新的途径。
|
| 关 键 词： | 人工神经网络 WTA神经网络 模糊系统 多级交换网路由重排 |
Fuzzy controlled neural network for rearrangeable multistage switching networks |
| |
| Zheng Pei,Zheng Junli.Fuzzy controlled neural network for rearrangeable multistage switching networks[J].Journal of Tsinghua University(Science and Technology),1997(1). |
| |
| Authors: | Zheng Pei Zheng Junli |
| |
| Institution: | Zheng Pei,Zheng Junli Department of Electronic Engineering,Tsinghua University,Beijing 100084 |
| |
| Abstract: | A fuzzy controlled WTA neural network algorithm to solve the problem of rearranging for multistage switching networks is proposed. A large number of simulation results show that compared with other algorithms, the fuzzy controlled algorithm has advantages of accurate and rapid convergence as well as adaptive parameter control. Besides software simulation, the virtual hardware of the fuzzy controlled WTA neural network algorithm for reswitching is realized successfully on the digital signal processors TMS320C30. The results agree well with the theoretical calculate results. Since the research of the fuzzy controlled neural network is seldom applied to WTA neural networks, a new way of combinating the fuzzy systems with neural network is explored by work in this paper. |
| |
| Keywords: | artificial neural network WTA neural network fuzzy system rearrangement for multistage switching networks |
| 本文献已被 CNKI 等数据库收录！ |
