期刊文献+

基于正交匹配追踪改进的Hammerstein系统辨识方法 预览

An Improved Parameter Estimation Method for Hammerstein Systems Based on the Orthogonal Matching Pursuit Algorithm
在线阅读 下载PDF
收藏 分享 导出
摘要 针对在有限数据采样情况下Hammerstem CA R模型的阶次和参数辨识问题,本文将关键变 量分离原理和压缩感知(compressed sensing, CS)理论相结合,提出了一种改进的正交匹配追踪稀 疏辨识方法.该方法采用关键变量分离原理分离出系统线性模块中的关键变量,然后用非线性模 块表达式将其替换,从而将系统输出表示为含所有待估参数的线性回归方程,并将其表达在采用压 缩感知理论进行系统参数重构的标准框架之下,最后利用压缩感知原理的正交匹配追踪算法对系 统阶次和参数同时进行估计.仿真结果表明,参数估计误差随着迭代次数的增加逐渐减小,最终趋 于零,说明该算法是有效的.该研究能有效地获得系统阶次和参数估计,提高了估计辨识算法的运 算效率,在实际工业过程中具有一定的实用意义. This paper explores the order and parameter identification problems for the modularity Hammerstein CAR model with the limit data sampling, and then proposes an improved orthogonal matching pursuit sparse i- identification method based on the key term separation principle and the compressed sensing(CS)theory. In this paper, we apply the key term separation principle to separate the key term from the linear block of the Ham-merstein system, and then replace it with the expression of the nonlinear block, so that, we can describe the output of the system as a linear regression equation about all solve-for parameters, and the equation is ex-pressed under the standard framework of the system parameter reconstruction based on the CS theory. Finally, we apply the orthogonal matching pursuitalgorithm of the CS theory to estimate the system orders and parame-ters at the same time. The simulation results show that the estimation of parameter errors is becoming smaller with the increase of the iterations, and finally, the estimation of parameter errors is near to zero. Therefore, the algorithm proposed in this paper is effective. The proposed method can effectively get the estimations of the system orders and parameters, and can raise the operating efficiency of the estimation and identification algo-rithm. This study has a certain practical significance in the real industrial process.
作者 闫亚茹 王冬青 刘艳君 YAN Yaru1, WANG Dongqing1, LIU Yanjun2(1. College of Automation and Electrical Engineering, Qingdao University, Qingdao 266071, China;2. Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education) , Jiangnan University, Wuxi 214122, China)
出处 《青岛大学学报:工程技术版》 CAS 2016年第4期13-16,22共5页 Journal of Qingdao University(Engineering & Technology Edition)
基金 国家自然科学基金资助项目(61573205) 山东省自然科学基金资助(ZR2015FM017)
关键词 关键变量分离原理 压缩感知原理 正交匹配追踪算法 参数辨识 辅助模型 the key term separation principle the compressed sensing principle orthogonal matching pursuit parameter estimation auxiliary models
  • 相关文献

参考文献4

二级参考文献43

  • 1蔡金狮.动力学系统辨识与建模[M].北京:国防工业出版社,1994.. 被引量:5
  • 2李人厚 秦世引.智能控制理论和方法[M].陕西西安:西安交通大学出版社,1995.. 被引量:1
  • 3陈净植.股票市场的发展现状及对策[M].湖南长沙:湖南大学,1997.. 被引量:1
  • 4叶环保 林仲豪.股票买卖技巧大全[M].北京:中国经济出版社,1994.. 被引量:2
  • 5深圳君们商务投资咨询有限公司.股票投资权威理论[M].广东深圳:海天出版社,1996.. 被引量:1
  • 6丁锋.系统辨识理论与方法+Matlab仿真.北京:电力出版社,2009. 被引量:5
  • 7Ding F, Chen T. Identification of Hammerstein nonlinear ARMAX systems. Automatica, 2005 ;41(9) : 1479-1489. 被引量:1
  • 8Liu Y, Bai E W. lterative identification of Hammerstein systems. Automatica, 2007 ; 43 (2) : 346-354. 被引量:1
  • 9Voros J. Recursive identification of Hammerstein systems with discontinuous nonlinearities containing dead-zones . IEEE Transactions on Automatic Control, 2003 ; 48 ( 12 ) :2203-2206. 被引量:1
  • 10Ding Feng, Liu Xiaoping, Liu Guangjun. Identification Methods for Hammerstein Nonlinear Systems[J]. Digital Signal Processing, 2011, 21(2): 215-238. 被引量:1

共引文献7

投稿分析
职称考试

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈