| 回归神经网络辩识电液伺服系统模型与仿真 |
| |
| 引用本文： | 叶金杰,岑豫皖,潘紫微,甄茂新. 回归神经网络辩识电液伺服系统模型与仿真[J]. 系统仿真学报, 2004, 16(9): 2056-2058 |
| |
| 作者姓名： | 叶金杰 岑豫皖 潘紫微 甄茂新 |
| |
| 作者单位： | 1. 安徽工业大学,马鞍山,243002
2. 上海宝山钢铁公司,上海,201900 |
| |
| 基金项目： | 安徽省教育厅自然科学重点研究项目(2004kj056zd) |
| |
| 摘 要： | 建立了一种回归神经网络辩识非线性电液伺服控制系统数学模型的辩识方法,研究了基于回归神经网络内部状态反馈的辩识算法,利用辩识实验获得的过程输入/输出数据动态调整神经网络权值。仿真结果辨明:神经网络描述的电液伺服控制系统数学模型具有较高精度,算法全局逼近能力良好。
|
| 关 键 词： | 回归神经网络 系统辩识 电液伺服系统 动态BP算法 |
| 文章编号： | 1004-731X(2004)09-2056-03 |
| 修稿时间： | 2003-11-10 |
Modeling and Simulation of Electro-Hydraulic Servo System Identification By Recurrent Neural Networks |
| |
| YE Jin-jie,CAN Yu-wan,PAN Zi-wei,ZHEN Mao-xin. Modeling and Simulation of Electro-Hydraulic Servo System Identification By Recurrent Neural Networks[J]. Journal of System Simulation, 2004, 16(9): 2056-2058 |
| |
| Authors: | YE Jin-jie CAN Yu-wan PAN Zi-wei ZHEN Mao-xin |
| |
| Affiliation: | YE Jin-jie1,CAN Yu-wan1,PAN Zi-wei1,ZHEN Mao-xin2 |
| |
| Abstract: | The method of identifying was built to identify mathematical model of nonlinear electro-hydraulic servo control system. The algorithm of identifying was researched based on inner state feedback of recurrent neural networks. The weights of neural networks were dynamic adjusted by input/output data of process which were acquired by experiments of identifying. The results of simulation show that mathematical model of neural networks of electro-hydraulic servo control system has better precision and the algorithm has ability to approximate error of global. |
| |
| Keywords: | recurrent neural networks system identification electro-hydraulic servo system dynamic BP algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
