Frequency domain weighted nonlinear least squares estimation of parameter-varying differential equations

Jan Goos; John Lataire; Ebrahim Louarroudi; Rik Pintelon

doi:10.1016/j.automatica.2016.09.031

Frequency domain weighted nonlinear least squares estimation of parameter-varying differential equations

Jan Goos, John Lataire, Ebrahim Louarroudi, Rik Pintelon

Research output: Contribution to journal › Article › peer-review

14 Citations (Scopus)

195 Downloads (Pure)

Abstract

This paper presents a frequency domain identification technique for estimation of Linear Parameter-Varying (LPV) differential equations. In a band-limited setting, it is shown that the time derivatives of the input and output signals can be computed exactly in the frequency domain, even for non-periodic inputs and parameter variations. The method operates in an errors-in-variables framework (noisy input and output), but the scheduling signal is assumed to be known. Under these conditions, the proposed estimator is proven to be consistent.

Original language	English
Pages (from-to)	191-199
Number of pages	9
Journal	Automatica
Volume	75
Issue number	1
DOIs	https://doi.org/10.1016/j.automatica.2016.09.031
Publication status	Published - 1 Jan 2017

Keywords

Identification methods
Linear Parameter-Varying systems

Access to Document

10.1016/j.automatica.2016.09.031

Automatica - LPV IOSubmitted manuscript, 690 KB

http://dx.doi.org/10.1016/j.automatica.2016.09.031

Handle.net

Persistent link

Cite this

@article{de1576f7b0824e359bb97c724aa11e7a,

title = "Frequency domain weighted nonlinear least squares estimation of parameter-varying differential equations",

abstract = "This paper presents a frequency domain identification technique for estimation of Linear Parameter-Varying (LPV) differential equations. In a band-limited setting, it is shown that the time derivatives of the input and output signals can be computed exactly in the frequency domain, even for non-periodic inputs and parameter variations. The method operates in an errors-in-variables framework (noisy input and output), but the scheduling signal is assumed to be known. Under these conditions, the proposed estimator is proven to be consistent.",

keywords = "Identification methods, Linear Parameter-Varying systems",

author = "Jan Goos and John Lataire and Ebrahim Louarroudi and Rik Pintelon",

year = "2017",

month = jan,

day = "1",

doi = "10.1016/j.automatica.2016.09.031",

language = "English",

volume = "75",

pages = "191--199",

journal = "Automatica",

issn = "0005-1098",

publisher = "Elsevier Limited",

number = "1",

}

TY - JOUR

T1 - Frequency domain weighted nonlinear least squares estimation of parameter-varying differential equations

AU - Goos, Jan

AU - Lataire, John

AU - Louarroudi, Ebrahim

AU - Pintelon, Rik

PY - 2017/1/1

Y1 - 2017/1/1

N2 - This paper presents a frequency domain identification technique for estimation of Linear Parameter-Varying (LPV) differential equations. In a band-limited setting, it is shown that the time derivatives of the input and output signals can be computed exactly in the frequency domain, even for non-periodic inputs and parameter variations. The method operates in an errors-in-variables framework (noisy input and output), but the scheduling signal is assumed to be known. Under these conditions, the proposed estimator is proven to be consistent.

AB - This paper presents a frequency domain identification technique for estimation of Linear Parameter-Varying (LPV) differential equations. In a band-limited setting, it is shown that the time derivatives of the input and output signals can be computed exactly in the frequency domain, even for non-periodic inputs and parameter variations. The method operates in an errors-in-variables framework (noisy input and output), but the scheduling signal is assumed to be known. Under these conditions, the proposed estimator is proven to be consistent.

KW - Identification methods

KW - Linear Parameter-Varying systems

UR - http://www.scopus.com/inward/record.url?scp=84993940948&partnerID=8YFLogxK

U2 - 10.1016/j.automatica.2016.09.031

DO - 10.1016/j.automatica.2016.09.031

M3 - Article

SN - 0005-1098

VL - 75

SP - 191

EP - 199

JO - Automatica

JF - Automatica

IS - 1

ER -

Frequency domain weighted nonlinear least squares estimation of parameter-varying differential equations

Abstract

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

DWTC282: Dynamical systems, control and optimization

Cite this

Frequency domain weighted nonlinear least squares estimation of parameter-varying differential equations

Abstract

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Projects

DWTC282: Dynamical systems, control and optimization

Cite this