IDENTIFICATION METHOD FOR LINEAR CONTINUOUS-TIME SYSTEMS

被引：0

作者：

Okou, Francis A. ^{[1
]}

Nganga-Kouya, Donatien ^{[3
]}

Amissanda, Arsene ^{[2
]}

机构：

[1] Royal Mil Coll Canada, Elect & Comp Engn Dept, Kingston, ON, Canada

[2] ETS, Elect Engn Dept, Montreal, PQ, Canada

[3] ENSET, Dept Mech Engn, Libreville, Gabon

来源：

2018 IEEE 14TH INTERNATIONAL CONFERENCE ON CONTROL AND AUTOMATION (ICCA) | 2018年

关键词：

Identification method; dynamic linear systems; continuous-time newton method; gradient method;

D O I：

暂无

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 presents a new method for the identification of linear continuous-time systems. Its main advantage is that estimated parameters converge to true system parameters even when the input is not a sufficiently rich signal. Estimated parameters are computed from a system of 2n equations with 2n unknown for a system of order n. A systematic method for obtaining this system of 2n equations is proposed. Algebraic and iterative resolutions are presented The new identification method is evaluated in simulation. It is compared to the gradient method. Results show that estimated parameters converge much faster with the proposed method.

引用

页码：647 / 653

页数：7