| 基于主成分分析的输出集成反馈网络及其在化工动态过程建模中的应用 |
| |
| 引用本文： | 程华农,韩方煜,钱宇. 基于主成分分析的输出集成反馈网络及其在化工动态过程建模中的应用[J]. 化工自动化及仪表, 2003, 30(2): 22-25 |
| |
| 作者姓名： | 程华农 韩方煜 钱宇 |
| |
| 作者单位： | 1. 青岛科技大学,计算机与化工研究所,山东,青岛,266042
2. 华南理工大学化工学院,广东,广州,510640 |
| |
| 基金项目： | 国家基金项目 ( 2 983 614 0 )，973重点基础规划项目(G2 0 0 0 0 2 63 ) |
| |
| 摘 要： | 针对主成分分析和反馈神经网络的优点，提出基于主成分分析的输出集成反馈网络建模方法，并对训练算法作了推导，在动态化工过程建模中取得满意的效果。
|
| 关 键 词： | 主成分分析 输出集成反馈网络 化工动态过程 建模 应用 反馈神经网络 |
| 文章编号： | 1000-3932(2003)(03)-0022-04 |
| 修稿时间： | 2002-07-29 |
A PCA Based Output Integrated Recurrent Neural Network for Dynamic Process Modeling |
| |
| CHENG Hua nong ,HAN Fang yu ,QIAN Yu. A PCA Based Output Integrated Recurrent Neural Network for Dynamic Process Modeling[J]. Control and Instruments In Chemical Industry, 2003, 30(2): 22-25 |
| |
| Authors: | CHENG Hua nong HAN Fang yu QIAN Yu |
| |
| Affiliation: | CHENG Hua nong 1,HAN Fang yu 1,QIAN Yu 2 |
| |
| Abstract: | A new methodology for modeling of dynamic process system,the output integrated recurrent neural network (OIRNN) is presented in this paper.OIRNN can be regarded as a modified Jordan recurrent neural network in which the past value for certain steps of the output variables are integrated with the input variables,and the original input variables are pre processed using principal component analysis (PCA) for the purpose of dimension reduction.The main advantage of the PCA based OIRNN is that the input dimension is reduced so that the network can be used to model the dynamic behavior of multiple input multiple output (MIMO) system effectively.The new method is illustrated by reference to the Tennessee Eastman process and compared with principal component regression and feed forward neural network. |
| |
| Keywords: | principal component analysis recurrent neural networks dynamic process dimension reduction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
