Data-Driven Modeling of a CO2 Refrigeration System

Glenn Andreasen, Jakob Stoustrup, Roozbeh Izadi-Zamanabadi, Ángel Á. Pardiñas, Armin Hafner

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

Resumé

This paper describes a data-driven method for system identification of a CO2 refrigeration system. Traditionally, the interaction between the measured variables is not utilized as they are highly dependent on the refrigeration system. In this work a data-driven method, namely subspace identification, is investigated for deriving a control-oriented model such that the dynamic interaction in the refrigeration systems can be utilized for e.g. fault detection and diagnosis. The subspace identification is applied on laboratory data obtained from a test setup located at NTNU in Trondheim, Norway. The obtained results offer promising perspectives for performance improvement in fault detection and diagnosis methods as well as control strategies.

OriginalsprogEngelsk
Titel 2019 American Control Conference (ACC)
Antal sider6
ForlagIEEE
Publikationsdato29 aug. 2019
Sider5385-5390
ISBN (Trykt)978-1-5386-7901-2
ISBN (Elektronisk)978-1-5386-7926-5
StatusUdgivet - 29 aug. 2019
Begivenhed2019 American Control Conference (ACC) - Philadelphia, USA
Varighed: 10 jul. 201912 jul. 2019

Konference

Konference2019 American Control Conference (ACC)
LandUSA
ByPhiladelphia
Periode10/07/201912/07/2019
NavnAmerican Control Conference
ISSN0743-1619

Fingerprint

Refrigeration
Data structures
Fault detection
Failure analysis
Identification (control systems)

Citer dette

Andreasen, G., Stoustrup, J., Izadi-Zamanabadi, R., Á. Pardiñas, Á., & Hafner, A. (2019). Data-Driven Modeling of a CO2 Refrigeration System. I 2019 American Control Conference (ACC) (s. 5385-5390). IEEE. American Control Conference
Andreasen, Glenn ; Stoustrup, Jakob ; Izadi-Zamanabadi, Roozbeh ; Á. Pardiñas, Ángel ; Hafner, Armin. / Data-Driven Modeling of a CO2 Refrigeration System. 2019 American Control Conference (ACC). IEEE, 2019. s. 5385-5390 (American Control Conference).
@inproceedings{600c5a077abd412382f8f9a711e6e962,
title = "Data-Driven Modeling of a CO2 Refrigeration System",
abstract = "This paper describes a data-driven method for system identification of a CO2 refrigeration system. Traditionally, the interaction between the measured variables is not utilized as they are highly dependent on the refrigeration system. In this work a data-driven method, namely subspace identification, is investigated for deriving a control-oriented model such that the dynamic interaction in the refrigeration systems can be utilized for e.g. fault detection and diagnosis. The subspace identification is applied on laboratory data obtained from a test setup located at NTNU in Trondheim, Norway. The obtained results offer promising perspectives for performance improvement in fault detection and diagnosis methods as well as control strategies.",
author = "Glenn Andreasen and Jakob Stoustrup and Roozbeh Izadi-Zamanabadi and {{\'A}. Pardi{\~n}as}, {\'A}ngel and Armin Hafner",
year = "2019",
month = "8",
day = "29",
language = "English",
isbn = "978-1-5386-7901-2",
series = "American Control Conference",
publisher = "IEEE",
pages = "5385--5390",
booktitle = "2019 American Control Conference (ACC)",
address = "United States",

}

Andreasen, G, Stoustrup, J, Izadi-Zamanabadi, R, Á. Pardiñas, Á & Hafner, A 2019, Data-Driven Modeling of a CO2 Refrigeration System. i 2019 American Control Conference (ACC). IEEE, American Control Conference, s. 5385-5390, Philadelphia, USA, 10/07/2019.

Data-Driven Modeling of a CO2 Refrigeration System. / Andreasen, Glenn; Stoustrup, Jakob; Izadi-Zamanabadi, Roozbeh; Á. Pardiñas, Ángel ; Hafner, Armin.

2019 American Control Conference (ACC). IEEE, 2019. s. 5385-5390 (American Control Conference).

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Data-Driven Modeling of a CO2 Refrigeration System

AU - Andreasen, Glenn

AU - Stoustrup, Jakob

AU - Izadi-Zamanabadi, Roozbeh

AU - Á. Pardiñas, Ángel

AU - Hafner, Armin

PY - 2019/8/29

Y1 - 2019/8/29

N2 - This paper describes a data-driven method for system identification of a CO2 refrigeration system. Traditionally, the interaction between the measured variables is not utilized as they are highly dependent on the refrigeration system. In this work a data-driven method, namely subspace identification, is investigated for deriving a control-oriented model such that the dynamic interaction in the refrigeration systems can be utilized for e.g. fault detection and diagnosis. The subspace identification is applied on laboratory data obtained from a test setup located at NTNU in Trondheim, Norway. The obtained results offer promising perspectives for performance improvement in fault detection and diagnosis methods as well as control strategies.

AB - This paper describes a data-driven method for system identification of a CO2 refrigeration system. Traditionally, the interaction between the measured variables is not utilized as they are highly dependent on the refrigeration system. In this work a data-driven method, namely subspace identification, is investigated for deriving a control-oriented model such that the dynamic interaction in the refrigeration systems can be utilized for e.g. fault detection and diagnosis. The subspace identification is applied on laboratory data obtained from a test setup located at NTNU in Trondheim, Norway. The obtained results offer promising perspectives for performance improvement in fault detection and diagnosis methods as well as control strategies.

UR - https://ieeexplore.ieee.org/document/8814871

M3 - Article in proceeding

SN - 978-1-5386-7901-2

T3 - American Control Conference

SP - 5385

EP - 5390

BT - 2019 American Control Conference (ACC)

PB - IEEE

ER -

Andreasen G, Stoustrup J, Izadi-Zamanabadi R, Á. Pardiñas Á, Hafner A. Data-Driven Modeling of a CO2 Refrigeration System. I 2019 American Control Conference (ACC). IEEE. 2019. s. 5385-5390. (American Control Conference).