Bi-orthonormal basis functions for improved frequency domain system identification

R.M.A. Herpen, van; T.A.E. Oomen; O.H. Bosgra

doi:10.1109/CDC.2012.6426408

Bi-orthonormal basis functions for improved frequency domain system identification

R.M.A. Herpen, van
, T.A.E. Oomen
, O.H. Bosgra

Control Systems Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

3 Citations (Scopus)

Abstract

Frequency-domain identification algorithms are considered. The aim of this paper is to develop a new algorithm that i) converges to a minimum of the objective function, and ii) possesses optimal numerical properties. Hereto, recent results in instrumental variable system identification are exploited. In addition, a new bilinear form is proposed that leads to the novel introduction of bi-orthonormal polynomials in system identification. The combination of these aspects leads to the desired convergence properties in conjunction with optimal numerical conditioning. The results are supported by means of a simulation example.

Original language	English
Title of host publication	Proceedings of the 51st IEEE Conference on Decision and Control (CDC 2012), 10-13 December 2012, Maui, Hawaii
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	3451-3456
ISBN (Print)	978-1-4673-2064-1
DOIs	https://doi.org/10.1109/CDC.2012.6426408
Publication status	Published - 2012

Access to Document

10.1109/CDC.2012.6426408

Cite this

@inproceedings{90c346772f9943d4b4857f2736a95cef,

title = "Bi-orthonormal basis functions for improved frequency domain system identification",

abstract = "Frequency-domain identification algorithms are considered. The aim of this paper is to develop a new algorithm that i) converges to a minimum of the objective function, and ii) possesses optimal numerical properties. Hereto, recent results in instrumental variable system identification are exploited. In addition, a new bilinear form is proposed that leads to the novel introduction of bi-orthonormal polynomials in system identification. The combination of these aspects leads to the desired convergence properties in conjunction with optimal numerical conditioning. The results are supported by means of a simulation example.",

author = "\{Herpen, van\}, R.M.A. and T.A.E. Oomen and O.H. Bosgra",

year = "2012",

doi = "10.1109/CDC.2012.6426408",

language = "English",

isbn = "978-1-4673-2064-1",

pages = "3451--3456",

booktitle = "Proceedings of the 51st IEEE Conference on Decision and Control (CDC 2012), 10-13 December 2012, Maui, Hawaii",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Bi-orthonormal basis functions for improved frequency domain system identification. / Herpen, van, R.M.A.; Oomen, T.A.E.; Bosgra, O.H.
Proceedings of the 51st IEEE Conference on Decision and Control (CDC 2012), 10-13 December 2012, Maui, Hawaii. Piscataway: Institute of Electrical and Electronics Engineers, 2012. p. 3451-3456.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Bi-orthonormal basis functions for improved frequency domain system identification

AU - Herpen, van, R.M.A.

AU - Oomen, T.A.E.

AU - Bosgra, O.H.

PY - 2012

Y1 - 2012

N2 - Frequency-domain identification algorithms are considered. The aim of this paper is to develop a new algorithm that i) converges to a minimum of the objective function, and ii) possesses optimal numerical properties. Hereto, recent results in instrumental variable system identification are exploited. In addition, a new bilinear form is proposed that leads to the novel introduction of bi-orthonormal polynomials in system identification. The combination of these aspects leads to the desired convergence properties in conjunction with optimal numerical conditioning. The results are supported by means of a simulation example.

AB - Frequency-domain identification algorithms are considered. The aim of this paper is to develop a new algorithm that i) converges to a minimum of the objective function, and ii) possesses optimal numerical properties. Hereto, recent results in instrumental variable system identification are exploited. In addition, a new bilinear form is proposed that leads to the novel introduction of bi-orthonormal polynomials in system identification. The combination of these aspects leads to the desired convergence properties in conjunction with optimal numerical conditioning. The results are supported by means of a simulation example.

U2 - 10.1109/CDC.2012.6426408

DO - 10.1109/CDC.2012.6426408

M3 - Conference contribution

SN - 978-1-4673-2064-1

SP - 3451

EP - 3456

BT - Proceedings of the 51st IEEE Conference on Decision and Control (CDC 2012), 10-13 December 2012, Maui, Hawaii

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Bi-orthonormal basis functions for improved frequency domain system identification

Abstract

Access to Document

Fingerprint

Cite this