| 基于对角递归神经网络的建模及应用 |
| |
| 引用本文： | 段慧达,郑德玲,刘聪.基于对角递归神经网络的建模及应用[J].北京科技大学学报,2004,26(1):103-105. |
| |
| 作者姓名： | 段慧达 郑德玲 刘聪 |
| |
| 作者单位： | 北京科技大学信息工程学院,北京,100083 |
| |
| 摘 要： | 介绍了对角递归神经网络,针对BP算法收敛慢的缺点,将递推预报误差学习算法应用到神经网络权值和域值的训练.通过对非线性系统辨识的仿真及在磷化温控系统建模中的应用,验证了这种建模方法的有效性.
|
| 关 键 词： | 对角递归神经网络 非线性系统辨识 磷化 递推预报误差 对角递归神经网络 建模方法 应用 Recurrent Neural Network Diagonal Based Application 有效性 验证 系统建模 温控 磷化 仿真 线性系统辨识 训练 域值 网络权值 递推预报误差学习算法 算法收敛 |
| 修稿时间： | 2002年9月24日 |
Modeling and Application Based on Diagonal Recurrent Neural Network |
| |
| DUAN Huida,ZHENG Deling,LIU Cong Information Engineering School,University of Science and Technology Beijing,Beijing ,China.Modeling and Application Based on Diagonal Recurrent Neural Network[J].Journal of University of Science and Technology Beijing,2004,26(1):103-105. |
| |
| Authors: | DUAN Huida ZHENG Deling LIU Cong Information Engineering School University of Science and Technology Beijing Beijing China |
| |
| Institution: | DUAN Huida,ZHENG Deling,LIU Cong Information Engineering School,University of Science and Technology Beijing,Beijing 100083,China |
| |
| Abstract: | A simple recurrent neural network named as diagonal recurrent neural network was studied. To overcome the slow convergence of BP algorithm, the recursive prediction error (RPE) algorithm was proposed, which can train both the weight and the bias. A given model was identified by using diagonal recurrent neural network trained with RPE algorithm, and the model of a phosphating temperature control system was established. Both simulation and experiment demonstrate the effectiveness of the proposed algorithm. |
| |
| Keywords: | diagonal recurrent neural network nonlinear system dentification phosphating recursive prediction error algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
