[1]李桂英,魏 莹,张 扬,等.具有不确定性的非线性系统自适应神经网络L2增益控制[J].智能系统学报,2009,4(4):357-362.
LI Gui-ying,WEI Ying,ZHANG Yang,et al.An adaptive neural network L2gain controller for nonlinear systems with uncertainty[J].CAAI Transactions on Intelligent Systems,2009,4(4):357-362.
点击复制
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
4
期数:
2009年第4期
页码:
357-362
栏目:
学术论文—机器学习
出版日期:
2009-08-25
- Title:
-
An adaptive neural network L2gain controller for nonlinear systems with uncertainty
- 文章编号:
-
1673-4785(2009)04-0357-06
- 作者:
-
李桂英,魏 莹,张 扬,孙来军
-
黑龙江大学电气工程及其自动化实验室,黑龙江哈尔滨150080
- Author(s):
-
LI Gui-ying, WEI Ying, ZHANG Yang, SUN Lai-jun
-
Laboratory of Electrical Engineering & Automation, Heilongjiang University, Harbin 150080, China
-
- 关键词:
-
L2 增益; 神经网络控制; HJI不等式
- Keywords:
-
L2gain; neural network control; HJI inequality
- 分类号:
-
TP273
- 文献标志码:
-
A
- 摘要:
-
针对存在不确定性的非线性系统,提出了自适应神经网络L2增益控制器设计方法,将基于HamiltonJacobi Issacs(HJI)不等式和自适应神经网络策略相结合,有效地克服了需要被控对象精确建模的局限性.神经网络对系统模型的偏差进行拟合;为了补偿拟合误差,引入补偿控制器和神经网络权值自适应调节律,通过在线自适应修正神经网络权值,来保证闭环系统满足相应的L2 性能准则.仿真结果表明提出的控制器设计方法是有效的,克服了一般方法需要被控对象精确建模的局限性.
- Abstract:
-
A scheme for an adaptive neural network L2gain controller was proposed for nonlinear systems with uncertainty. By combining the HamiltonJacobiIssacs (HJI) inequality with an adaptive neural network, limitations on the precision of previous models can be effectively overcome. With this controller, errors from the model were fitted by the neural network. In order to compensate for the fitting errors, a compensation controller and an adaptive law for the weights of the neural network were introduced. By online adaptive adjustment of these weights, L2gain performance of the closedloop system could be guaranteed.Simulation results are shown to demonstrate the effectiveness and the advantages of the proposed approach. To avoid the limitation of the precision model of the plant in the common approach.
备注/Memo
收稿日期:2008-03-21.
基金项目:黑龙江省自然科学基金资助项目(F200707);黑龙江大学青年科学基金资助项目(QL200736).
通信作者:李桂英.E-mail:lgy996032@163.com.
作者简介:
李桂英,女,1974年生,讲师,主要研究方向为智能系统、优化算法.发表学术论文3篇.
魏 莹,女,1978年生,硕士研究生,主要研究方向为自动化测试与控制.发表学术论文2篇.
?张扬,男,1982年生,硕士研究生,主要研究方向为微控制器及嵌入式系统应用.发表学术论文3篇.
?孙来军,1977年生,男,博士,讲师,硕士生导师,主要研究方向为设备监测与故障诊断技术、无损检测技术.
更新日期/Last Update:
2009-11-16