[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(04):357-362.
 LI Gui-ying,WEI Ying,ZHANG Yang,et al.An adaptive neural network L2gain controller for nonlinear systems with uncertainty[J].CAAI Transactions on Intelligent Systems,2009,4(04):357-362.
点击复制

具有不确定性的非线性系统自适应神经网络L2增益控制(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第4卷
期数:
2009年04期
页码:
357-362
栏目:
出版日期:
2009-08-25

文章信息/Info

Title:
An adaptive neural network L2gain 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:
L2gain 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L2增益控制器设计方法,将基于HamiltonJacobi 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L2 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 L2gain controller was proposed for nonlinear systems with uncertainty. By combining the HamiltonJacobiIssacs (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 online adaptive adjustment of these weights, L2gain performance of the closedloop 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.

参考文献/References:

[1]李占山,王晓飞,杨新宇.一类非线性MIMO系统鲁棒自适应神经网络DSC设计[J].哈尔滨工程大学学报,2009,30(2):121125.
 LI Zhanshan, WANG Xiaofei, YANG Xinyu.DSC design of a robust adaptive NN control for a class of nonlinear MIMO systems[J].Journal of Harbin Engineering University,2009,30(2):121125.
[2]许 昌,吕剑虹,程 明,等.一种改进RBF网络与PID相协调的自适应控制[J].哈尔滨工程大学学报,2007,28(6): 660664.
 XU Chang,L Jianhong,CHENG Ming,et al.Selfadaptive control with coordinated PID and improved RBF network[J].Journal of Harbin Engineering University,2007,28(6): 660664.
[3]何文广.基于模糊神经控制的机器人避障算法[J].黑龙江工程学院学报,2008,22(3):6366.
 HE Wenguang.The caculation of avoiding barriers for robot based on fuzzy neural control[J].Journal of Heilongjiang Institute of Technology,2008,22(3):6366.
[4]吴 珠,刘国栋.线性不确定离散时滞系统的鲁棒非脆弱H∞控制[J].智能系统学报,2008,3(1):6670.
 WU Zhu,LIU Guodong.Robust and nonfragile H∞ control for linear discretetime systems with timedelay and uncertainties[J].CAAI Transactions on Intelligent Systems,2008,3(1):6670.
[5]冯筱林,李 斌,靳 炜,侯东良.一种非线性系统的神经网络自适应控制[J].应用科技,2007,34(5):3941.
FENG Xiaolin, LI Bin, JIN Wei, HOU Dongliang.Adaptive control of a kind of nonlinear system using neural networks[J].Applied Science and Technology,2007,34(5):3941.
[6]张子迎,刘 心,杨 霁.基于神经网络PID的AUV控制方法研究[J].应用科技,2007,34(8):2528.
 ZHANG Ziying, LIU Xin, YANG Ji. AUV’s motion control based on NN PID[J].Applied Science and Technology,2007,34(8):2528.
 [7]AHMED M S. Neural controllers for nonlinear state feedback L2gain control[C]//Control Theory and Applications. United Kingdom, 2000, 147(3): 239246.
[8]HASSAN H K. 非线性系统[M].3版.北京:电子出版社,2005:141154. 
[9】SCHAFT A J. L2gain analysis of nonlinear systems andnonlinear state feedback control[J]. IEEE Transactions on Automatic Control, 1992, 37(6):770784

备注/Memo

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(F200707);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