Identification methods of Hammerstein nonelinear CARAR systems

摘要：

A recursive generalized least squares and a generalized stochastic gradient algorithms are developed for Hammerstein nonlinear systems with memoryless nonlinear blocks followed by linear dynamical blocks described by CARAR models (HCARAR models). The basic idea is to replace the unmeasurable noise terms in the information vectors with their estimates and to compute the noise estimates through different methods. The simulation results show the performance of the proposed algorithms.

关键词： Recursive Identification Parameter Estimation Hammerstein Models Stochastic Gradient Least Squares

作者: Yongsong Xiao Na Yue Feng Ding

作者单位: Control Science and Engineering Research Center, Jiangnan University, Wuxi, P. R. China 214122

会议类型: 国际会议

会议名称: The 22nd China Control and Decision Conference(2010年中国控制与决策会议)

会议地点: 徐州

会议语种:英文

页码: 3284-3288

在线出版日期: 2010-05-26（万方平台首次上网日期，不代表论文的发表时间）