| 用B-样条神经网络设计非线性观测器 |
| |
| 引用本文： | 张洪钺, 金宏, 陈志炜, 张祺忠. 用B-样条神经网络设计非线性观测器. 自动化学报, 2000, 26(2): 199-205. |
| |
| 作者姓名： | 张洪钺 金宏 陈志炜 张祺忠 |
| |
| 作者单位： | 1.北京航空航天大学自动控制系,北京;;2.香港大学机械工程系,香港 |
| |
| 摘 要： | 对线性部分已知、非线性部分未知的一类非线性系统,提出了一种新的状态观测器的设计方法.首先针对线性部分设计线性观测器,随后在线性观测器中加入非线性补偿项.该补偿项先由"反卷积"的方式确定,再用B-样条神经网络拟合.对三个非线性系统设计了观测器,通过与已有的解析方法进行比较,说明了该方法的优越性.
|
| 关 键 词： | 非线性系统 观测器 神经元网络 |
| 收稿时间： | 1998-11-12 |
| 修稿时间： | 1998-11-12 |
NONLINEAR OBSERVER DESIGN FOR SYSTEMS WITH UNKNOWN NONLINEARITY VIA B-SPLINE NETWORK APPROACH |
| |
| Zhang Hongyue, Jin Hong, C.W.Chan, K.C.Cheung. Nonlinear Observer Design for Systems with Unknown Nonlinearity Via B-Spline Network Approach. ACTA AUTOMATICA SINICA, 2000, 26(2): 199-205. |
| |
| Authors: | ZHANG Hongyue JIN Hong C. W. Chan K.C. Cheung |
| |
| Affiliation: | 1. Department of Automatic Control,Beijing University of Aeronautics and Astronautics,Beijing;Department of Mechanical Engineering,University of Hong Kong,Hong Kong |
| |
| Abstract: | A novel approach is proposed for the state estimation of a class of nonlinear systems which consist of known linear part and unknown nonlinear part. A linear observer is first designed, then a nonlinear compensation term in the nonlinear observer is estimated by using a "deconvolution method". The B-spline neural network is used to model the obtained compensation term. Three simulation examples are given to show the effectiveness of the proposed approach |
| |
| Keywords: | Nonlinear system observer neural network. |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
|
