Subspace identification for MIMO systems in the presence of trends and outliers

Mikael Manngård; Jari Böling; Hannu Toivonen

doi:10.1016/B978-0-444-63965-3.50053-2

Subspace identification for MIMO systems in the presence of trends and outliers

Mikael Manngård
, Jari Böling
, Hannu Toivonen

Research output: Chapter in Book/Conference proceeding › Published conference proceeding › Scientific › peer-review

3 Citations (Scopus)

Abstract

In this paper we present a framework for subspace identification of multiple-input multiple output linear time-invariant systems from data corrupted by outliers and piece-wise linear trends. The subspace identification problem is formulated as a sparsity constrained rank minimization problem that is relaxed using the nuclear norm and the l1-norm. The proposed identification method has been validated on a simulated example and on a case study using data from a pilot-plant distillation column.

Original language	Undefined/Unknown
Title of host publication	27th European Symposium on Computer Aided Process Engineering
Editors	Antonio Espuña, Moisès Graells, Luis Puigjaner
Publisher	Elsevier
Pages	307–312
ISBN (Electronic)	978-0-444-63970-7
ISBN (Print)	978-0-444-63965-3
DOIs	https://doi.org/10.1016/B978-0-444-63965-3.50053-2
Publication status	Published - 2017
MoE publication type	A4 Article in a conference publication
Event	European Symposium on Computer Aided Process Engineering (ESCAPE) - 27th European Society of Computer-Aided Process Engineering (ESCAPE) Duration: 1 Oct 2017 → 5 Oct 2017

Conference

Conference	European Symposium on Computer Aided Process Engineering (ESCAPE)
Period	01/10/17 → 05/10/17

Access to Document

10.1016/B978-0-444-63965-3.50053-2

https://www.elsevier.com/books/27th-european-symposium-on-computer-aided-process-engineering/espuna/978-0-444-63965-3

Cite this

@inproceedings{11f922f6d5464de286fe20f593fbcedc,

title = "Subspace identification for MIMO systems in the presence of trends and outliers",

abstract = "In this paper we present a framework for subspace identification of multiple-input multiple output linear time-invariant systems from data corrupted by outliers and piece-wise linear trends. The subspace identification problem is formulated as a sparsity constrained rank minimization problem that is relaxed using the nuclear norm and the l1-norm. The proposed identification method has been validated on a simulated example and on a case study using data from a pilot-plant distillation column.",

author = "Mikael Manng{\aa}rd and Jari B{\"o}ling and Hannu Toivonen",

note = "rt. Konferenspublikationen finns p{\aa} en minnespinne hos A.F.; European Symposium on Computer Aided Process Engineering (ESCAPE) ; Conference date: 01-10-2017 Through 05-10-2017",

year = "2017",

doi = "10.1016/B978-0-444-63965-3.50053-2",

language = "Odefinierat/ok{\"a}nt",

isbn = "978-0-444-63965-3",

pages = "307–312",

editor = "Antonio Espu{\~n}a and Mois{\`e}s Graells and Luis Puigjaner",

booktitle = "27th European Symposium on Computer Aided Process Engineering",

publisher = "Elsevier",

}

Manngård, M, Böling, J & Toivonen, H 2017, Subspace identification for MIMO systems in the presence of trends and outliers. in A Espuña, M Graells & L Puigjaner (eds), 27th European Symposium on Computer Aided Process Engineering. Elsevier, pp. 307–312, European Symposium on Computer Aided Process Engineering (ESCAPE), 01/10/17. https://doi.org/10.1016/B978-0-444-63965-3.50053-2

Subspace identification for MIMO systems in the presence of trends and outliers. / Manngård, Mikael; Böling, Jari ; Toivonen, Hannu.
27th European Symposium on Computer Aided Process Engineering. ed. / Antonio Espuña; Moisès Graells; Luis Puigjaner. Elsevier, 2017. p. 307–312.

Research output: Chapter in Book/Conference proceeding › Published conference proceeding › Scientific › peer-review

TY - GEN

T1 - Subspace identification for MIMO systems in the presence of trends and outliers

AU - Manngård, Mikael

AU - Böling, Jari

AU - Toivonen, Hannu

N1 - rt. Konferenspublikationen finns på en minnespinne hos A.F.

PY - 2017

Y1 - 2017

N2 - In this paper we present a framework for subspace identification of multiple-input multiple output linear time-invariant systems from data corrupted by outliers and piece-wise linear trends. The subspace identification problem is formulated as a sparsity constrained rank minimization problem that is relaxed using the nuclear norm and the l1-norm. The proposed identification method has been validated on a simulated example and on a case study using data from a pilot-plant distillation column.

AB - In this paper we present a framework for subspace identification of multiple-input multiple output linear time-invariant systems from data corrupted by outliers and piece-wise linear trends. The subspace identification problem is formulated as a sparsity constrained rank minimization problem that is relaxed using the nuclear norm and the l1-norm. The proposed identification method has been validated on a simulated example and on a case study using data from a pilot-plant distillation column.

U2 - 10.1016/B978-0-444-63965-3.50053-2

DO - 10.1016/B978-0-444-63965-3.50053-2

M3 - Publicerad konferensartikel

SN - 978-0-444-63965-3

SP - 307

EP - 312

BT - 27th European Symposium on Computer Aided Process Engineering

A2 - Espuña, Antonio

A2 - Graells, Moisès

A2 - Puigjaner, Luis

PB - Elsevier

T2 - European Symposium on Computer Aided Process Engineering (ESCAPE)

Y2 - 1 October 2017 through 5 October 2017

ER -