Operating regime model based multi-objective sensor placement for data reconciliation

G. Dorgo, Mate Haragovics, J. Abonyi

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Although the number of sensors in chemical production plants is increasing thanks to the IoT revolution, it is still a crucial problem what to measure and how to place the sensors as such the resulted sensor network be robust and cost-effectively provide the required information. This problem is especially relevant inflexible multi-purpose, multi-product production plants when there are significant differences among the operating regions. The present work aims the development of a sensor placement methodology that utilizes the advantages of local linear models. Realizing the often conflicting nature of the key objectives of sensor placement, the problem is formulated as a multi-objective optimization task taking into consideration the cost, estimation accuracy, observability and fault detection performance of the designed networks and simultaneously seeking for the optimal solutions under multiple operating regimes. The effectiveness of the Non-dominated Sorting Genetic Algorithm-II (NSGA-II)-based solution of the defined problem is demonstrated through benchmark examples.

Original languageEnglish
Title of host publicationComputer Aided Chemical Engineering
PublisherElsevier B.V.
Pages1027-1032
Number of pages6
DOIs
Publication statusPublished - Jan 1 2019

Publication series

NameComputer Aided Chemical Engineering
Volume46
ISSN (Print)1570-7946

Fingerprint

Sensors
Observability
Multiobjective optimization
Fault detection
Sorting
Sensor networks
Costs
Genetic algorithms
Internet of things

Keywords

  • data reconciliation
  • multi-objective optimization
  • sensor placement

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Computer Science Applications

Cite this

Dorgo, G., Haragovics, M., & Abonyi, J. (2019). Operating regime model based multi-objective sensor placement for data reconciliation. In Computer Aided Chemical Engineering (pp. 1027-1032). (Computer Aided Chemical Engineering; Vol. 46). Elsevier B.V.. https://doi.org/10.1016/B978-0-12-818634-3.50172-7

Operating regime model based multi-objective sensor placement for data reconciliation. / Dorgo, G.; Haragovics, Mate; Abonyi, J.

Computer Aided Chemical Engineering. Elsevier B.V., 2019. p. 1027-1032 (Computer Aided Chemical Engineering; Vol. 46).

Research output: Chapter in Book/Report/Conference proceedingChapter

Dorgo, G, Haragovics, M & Abonyi, J 2019, Operating regime model based multi-objective sensor placement for data reconciliation. in Computer Aided Chemical Engineering. Computer Aided Chemical Engineering, vol. 46, Elsevier B.V., pp. 1027-1032. https://doi.org/10.1016/B978-0-12-818634-3.50172-7
Dorgo G, Haragovics M, Abonyi J. Operating regime model based multi-objective sensor placement for data reconciliation. In Computer Aided Chemical Engineering. Elsevier B.V. 2019. p. 1027-1032. (Computer Aided Chemical Engineering). https://doi.org/10.1016/B978-0-12-818634-3.50172-7
Dorgo, G. ; Haragovics, Mate ; Abonyi, J. / Operating regime model based multi-objective sensor placement for data reconciliation. Computer Aided Chemical Engineering. Elsevier B.V., 2019. pp. 1027-1032 (Computer Aided Chemical Engineering).
@inbook{635dbfb16b6341da9e8fd3553d8244c4,
title = "Operating regime model based multi-objective sensor placement for data reconciliation",
abstract = "Although the number of sensors in chemical production plants is increasing thanks to the IoT revolution, it is still a crucial problem what to measure and how to place the sensors as such the resulted sensor network be robust and cost-effectively provide the required information. This problem is especially relevant inflexible multi-purpose, multi-product production plants when there are significant differences among the operating regions. The present work aims the development of a sensor placement methodology that utilizes the advantages of local linear models. Realizing the often conflicting nature of the key objectives of sensor placement, the problem is formulated as a multi-objective optimization task taking into consideration the cost, estimation accuracy, observability and fault detection performance of the designed networks and simultaneously seeking for the optimal solutions under multiple operating regimes. The effectiveness of the Non-dominated Sorting Genetic Algorithm-II (NSGA-II)-based solution of the defined problem is demonstrated through benchmark examples.",
keywords = "data reconciliation, multi-objective optimization, sensor placement",
author = "G. Dorgo and Mate Haragovics and J. Abonyi",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/B978-0-12-818634-3.50172-7",
language = "English",
series = "Computer Aided Chemical Engineering",
publisher = "Elsevier B.V.",
pages = "1027--1032",
booktitle = "Computer Aided Chemical Engineering",

}

TY - CHAP

T1 - Operating regime model based multi-objective sensor placement for data reconciliation

AU - Dorgo, G.

AU - Haragovics, Mate

AU - Abonyi, J.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Although the number of sensors in chemical production plants is increasing thanks to the IoT revolution, it is still a crucial problem what to measure and how to place the sensors as such the resulted sensor network be robust and cost-effectively provide the required information. This problem is especially relevant inflexible multi-purpose, multi-product production plants when there are significant differences among the operating regions. The present work aims the development of a sensor placement methodology that utilizes the advantages of local linear models. Realizing the often conflicting nature of the key objectives of sensor placement, the problem is formulated as a multi-objective optimization task taking into consideration the cost, estimation accuracy, observability and fault detection performance of the designed networks and simultaneously seeking for the optimal solutions under multiple operating regimes. The effectiveness of the Non-dominated Sorting Genetic Algorithm-II (NSGA-II)-based solution of the defined problem is demonstrated through benchmark examples.

AB - Although the number of sensors in chemical production plants is increasing thanks to the IoT revolution, it is still a crucial problem what to measure and how to place the sensors as such the resulted sensor network be robust and cost-effectively provide the required information. This problem is especially relevant inflexible multi-purpose, multi-product production plants when there are significant differences among the operating regions. The present work aims the development of a sensor placement methodology that utilizes the advantages of local linear models. Realizing the often conflicting nature of the key objectives of sensor placement, the problem is formulated as a multi-objective optimization task taking into consideration the cost, estimation accuracy, observability and fault detection performance of the designed networks and simultaneously seeking for the optimal solutions under multiple operating regimes. The effectiveness of the Non-dominated Sorting Genetic Algorithm-II (NSGA-II)-based solution of the defined problem is demonstrated through benchmark examples.

KW - data reconciliation

KW - multi-objective optimization

KW - sensor placement

UR - http://www.scopus.com/inward/record.url?scp=85069709692&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069709692&partnerID=8YFLogxK

U2 - 10.1016/B978-0-12-818634-3.50172-7

DO - 10.1016/B978-0-12-818634-3.50172-7

M3 - Chapter

AN - SCOPUS:85069709692

T3 - Computer Aided Chemical Engineering

SP - 1027

EP - 1032

BT - Computer Aided Chemical Engineering

PB - Elsevier B.V.

ER -