Convergence analysis for recursive Hammerstein identification

被引:16
|
作者
Mattsson, Per [1 ]
Wigren, Torbjorn [1 ]
机构
[1] Uppsala Univ, Dept Informat Technol, Uppsala, Sweden
基金
欧洲研究理事会;
关键词
Averaging; Cement mill; Convergence analysis; Hammerstein system; Recursive identification; NONLINEAR-SYSTEMS; ALGORITHMS; MODEL;
D O I
10.1016/j.automatica.2016.04.014
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper derives a recursive prediction error identification method based on the Hammerstein model structure. The convergence properties of the algorithm are analysed by application of Ljung's associated differential equation method. It is proved that the algorithm can only converge to stable stationary points of the associated ordinary differential equation. General conditions for local convergence to the true parameter vector are given, and the cases with piecewise linear and polynomial nonlinearities are treated in detail. The derived identification method is illustrated in a numerical study that treats identification of a subsystem of a cement mill. (C) 2016 Elsevier Ltd. All rights reserved.
引用
收藏
页码:179 / 186
页数:8
相关论文
共 50 条