Predictor input selection for two stage identification in dynamic networks

Arne Dankers; Paul M.J. Van Den Hof; Xavier Bombois; Peter S.C. Heuberger

doi:10.23919/ECC.2013.6669779

Predictor input selection for two stage identification in dynamic networks

Arne Dankers, Paul M.J. Van Den Hof, Xavier Bombois, Peter S.C. Heuberger

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

6 Citations (Scopus)

Abstract

Recently, the Two-Stage method has been proposed as a tool to obtain consistent estimates of modules embedded in dynamic networks [1], [2]. However, for this method the variables that are included in the predictor model are currently not considered as a user choice. In this paper it is shown that there is considerable freedom as to which variables can be included in the predictor model as inputs, and still obtain consistent estimates of the module of interest. Conditions that the choice of predictor inputs must satisfy are presented. The conditions could be used to find the smallest number of predictor inputs for instance. Algorithms are presented for checking the conditions and obtaining the estimates.

Original language	English
Title of host publication	2013 European Control Conference, ECC 2013
Publisher	Institute of Electrical and Electronics Engineers
Pages	1422-1427
Number of pages	6
ISBN (Print)	9783033039629
DOIs	https://doi.org/10.23919/ECC.2013.6669779
Publication status	Published - 1 Dec 2013
Event	12th European Control Conference, ECC 2013 - Zurich, Switzerland, Zürich, Switzerland Duration: 17 Jul 2013 → 19 Jul 2013 Conference number: 12 http://www.ecc2013.ethz.ch/

Conference

Conference	12th European Control Conference, ECC 2013
Abbreviated title	ECC 2013
Country/Territory	Switzerland
City	Zürich
Period	17/07/13 → 19/07/13
Other	European Control Conference 2013
Internet address	http://www.ecc2013.ethz.ch/

Access to Document

10.23919/ECC.2013.6669779

Cite this

@inproceedings{5a9b9a9ca40a4e0282d5cc8533ac835b,

title = "Predictor input selection for two stage identification in dynamic networks",

abstract = "Recently, the Two-Stage method has been proposed as a tool to obtain consistent estimates of modules embedded in dynamic networks [1], [2]. However, for this method the variables that are included in the predictor model are currently not considered as a user choice. In this paper it is shown that there is considerable freedom as to which variables can be included in the predictor model as inputs, and still obtain consistent estimates of the module of interest. Conditions that the choice of predictor inputs must satisfy are presented. The conditions could be used to find the smallest number of predictor inputs for instance. Algorithms are presented for checking the conditions and obtaining the estimates.",

author = "Arne Dankers and {Van Den Hof}, {Paul M.J.} and Xavier Bombois and Heuberger, {Peter S.C.}",

year = "2013",

month = dec,

day = "1",

doi = "10.23919/ECC.2013.6669779",

language = "English",

isbn = "9783033039629",

pages = "1422--1427",

booktitle = "2013 European Control Conference, ECC 2013",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "12th European Control Conference, ECC 2013, ECC 2013 ; Conference date: 17-07-2013 Through 19-07-2013",

url = "http://www.ecc2013.ethz.ch/",

}

Dankers, A, Van Den Hof, PMJ, Bombois, X & Heuberger, PSC 2013, Predictor input selection for two stage identification in dynamic networks. in 2013 European Control Conference, ECC 2013., 6669779, Institute of Electrical and Electronics Engineers, pp. 1422-1427, 12th European Control Conference, ECC 2013, Zürich, Switzerland, 17/07/13. https://doi.org/10.23919/ECC.2013.6669779

Predictor input selection for two stage identification in dynamic networks. / Dankers, Arne; Van Den Hof, Paul M.J.; Bombois, Xavier et al.
2013 European Control Conference, ECC 2013. Institute of Electrical and Electronics Engineers, 2013. p. 1422-1427 6669779.

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

TY - GEN

T1 - Predictor input selection for two stage identification in dynamic networks

AU - Dankers, Arne

AU - Van Den Hof, Paul M.J.

AU - Bombois, Xavier

AU - Heuberger, Peter S.C.

N1 - Conference code: 12

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Recently, the Two-Stage method has been proposed as a tool to obtain consistent estimates of modules embedded in dynamic networks [1], [2]. However, for this method the variables that are included in the predictor model are currently not considered as a user choice. In this paper it is shown that there is considerable freedom as to which variables can be included in the predictor model as inputs, and still obtain consistent estimates of the module of interest. Conditions that the choice of predictor inputs must satisfy are presented. The conditions could be used to find the smallest number of predictor inputs for instance. Algorithms are presented for checking the conditions and obtaining the estimates.

AB - Recently, the Two-Stage method has been proposed as a tool to obtain consistent estimates of modules embedded in dynamic networks [1], [2]. However, for this method the variables that are included in the predictor model are currently not considered as a user choice. In this paper it is shown that there is considerable freedom as to which variables can be included in the predictor model as inputs, and still obtain consistent estimates of the module of interest. Conditions that the choice of predictor inputs must satisfy are presented. The conditions could be used to find the smallest number of predictor inputs for instance. Algorithms are presented for checking the conditions and obtaining the estimates.

UR - http://www.scopus.com/inward/record.url?scp=84883203142&partnerID=8YFLogxK

U2 - 10.23919/ECC.2013.6669779

DO - 10.23919/ECC.2013.6669779

M3 - Conference contribution

AN - SCOPUS:84883203142

SN - 9783033039629

SP - 1422

EP - 1427

BT - 2013 European Control Conference, ECC 2013

PB - Institute of Electrical and Electronics Engineers

T2 - 12th European Control Conference, ECC 2013

Y2 - 17 July 2013 through 19 July 2013

ER -

Predictor input selection for two stage identification in dynamic networks

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this