Parameters selection in predictive online simulation

Gerardo Santillán Martinez (Corresponding author), Tuomas Miettinen, Antti Aikala, Jouni Savolainen, Kalle Kondelin, Tommi Karhela, Valeiry Vyatkin

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

2 Citations (Scopus)

Abstract

Industrial applications with reliable predictive features are becoming increasingly important. A tracking simulator is an example of an online simulation system with great capabilities that fills the gap left by other predictive applications. In a tracking simulator, a simulation model is run in parallel with a physical process controlled by the process' control system. At the same time, a tracking mechanism is used to keep the state of the simulation model as close as possible to the real process by continually adjusting parameters of the model. The selection of these parameters impacts directly on the quality of the tracking simulation results and it is a complex task in processes with a big number of variables. This paper presents two case studies of tracking simulation where the controlled parameters are selected using different techniques. The first case study deals with a laboratory-scale hot water generation process where the parameters' selection is performed manually. The second case study deals with a combined heat and power production process with major uncertainties in the process structure. In this case, we focus on the variance decomposition method used to determine the most suitable controlled parameters. Conclusions and future work are finally presented.
Original languageEnglish
Title of host publication2016 IEEE 14th International Conference on Industrial Informatics (INDIN)
PublisherInstitute of Electrical and Electronic Engineers IEEE
Pages726-729
Number of pages4
ISBN (Electronic)978-1-5090-2870-2
ISBN (Print)978-1-5090-2871-9
DOIs
Publication statusPublished - 19 Jul 2016
MoE publication typeA4 Article in a conference publication

Fingerprint

Simulators
Industrial applications
Process control
Decomposition
Control systems
Water
Uncertainty
Hot Temperature

Cite this

Santillán Martinez, G., Miettinen, T., Aikala, A., Savolainen, J., Kondelin, K., Karhela, T., & Vyatkin, V. (2016). Parameters selection in predictive online simulation. In 2016 IEEE 14th International Conference on Industrial Informatics (INDIN) (pp. 726-729). Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/INDIN.2016.7819254
Santillán Martinez, Gerardo ; Miettinen, Tuomas ; Aikala, Antti ; Savolainen, Jouni ; Kondelin, Kalle ; Karhela, Tommi ; Vyatkin, Valeiry. / Parameters selection in predictive online simulation. 2016 IEEE 14th International Conference on Industrial Informatics (INDIN). Institute of Electrical and Electronic Engineers IEEE, 2016. pp. 726-729
@inproceedings{9179a541453148f7b91f32a48aa65d8e,
title = "Parameters selection in predictive online simulation",
abstract = "Industrial applications with reliable predictive features are becoming increasingly important. A tracking simulator is an example of an online simulation system with great capabilities that fills the gap left by other predictive applications. In a tracking simulator, a simulation model is run in parallel with a physical process controlled by the process' control system. At the same time, a tracking mechanism is used to keep the state of the simulation model as close as possible to the real process by continually adjusting parameters of the model. The selection of these parameters impacts directly on the quality of the tracking simulation results and it is a complex task in processes with a big number of variables. This paper presents two case studies of tracking simulation where the controlled parameters are selected using different techniques. The first case study deals with a laboratory-scale hot water generation process where the parameters' selection is performed manually. The second case study deals with a combined heat and power production process with major uncertainties in the process structure. In this case, we focus on the variance decomposition method used to determine the most suitable controlled parameters. Conclusions and future work are finally presented.",
author = "{Santill{\'a}n Martinez}, Gerardo and Tuomas Miettinen and Antti Aikala and Jouni Savolainen and Kalle Kondelin and Tommi Karhela and Valeiry Vyatkin",
year = "2016",
month = "7",
day = "19",
doi = "10.1109/INDIN.2016.7819254",
language = "English",
isbn = "978-1-5090-2871-9",
pages = "726--729",
booktitle = "2016 IEEE 14th International Conference on Industrial Informatics (INDIN)",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Santillán Martinez, G, Miettinen, T, Aikala, A, Savolainen, J, Kondelin, K, Karhela, T & Vyatkin, V 2016, Parameters selection in predictive online simulation. in 2016 IEEE 14th International Conference on Industrial Informatics (INDIN). Institute of Electrical and Electronic Engineers IEEE, pp. 726-729. https://doi.org/10.1109/INDIN.2016.7819254

Parameters selection in predictive online simulation. / Santillán Martinez, Gerardo (Corresponding author); Miettinen, Tuomas; Aikala, Antti; Savolainen, Jouni; Kondelin, Kalle; Karhela, Tommi; Vyatkin, Valeiry.

2016 IEEE 14th International Conference on Industrial Informatics (INDIN). Institute of Electrical and Electronic Engineers IEEE, 2016. p. 726-729.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Parameters selection in predictive online simulation

AU - Santillán Martinez, Gerardo

AU - Miettinen, Tuomas

AU - Aikala, Antti

AU - Savolainen, Jouni

AU - Kondelin, Kalle

AU - Karhela, Tommi

AU - Vyatkin, Valeiry

PY - 2016/7/19

Y1 - 2016/7/19

N2 - Industrial applications with reliable predictive features are becoming increasingly important. A tracking simulator is an example of an online simulation system with great capabilities that fills the gap left by other predictive applications. In a tracking simulator, a simulation model is run in parallel with a physical process controlled by the process' control system. At the same time, a tracking mechanism is used to keep the state of the simulation model as close as possible to the real process by continually adjusting parameters of the model. The selection of these parameters impacts directly on the quality of the tracking simulation results and it is a complex task in processes with a big number of variables. This paper presents two case studies of tracking simulation where the controlled parameters are selected using different techniques. The first case study deals with a laboratory-scale hot water generation process where the parameters' selection is performed manually. The second case study deals with a combined heat and power production process with major uncertainties in the process structure. In this case, we focus on the variance decomposition method used to determine the most suitable controlled parameters. Conclusions and future work are finally presented.

AB - Industrial applications with reliable predictive features are becoming increasingly important. A tracking simulator is an example of an online simulation system with great capabilities that fills the gap left by other predictive applications. In a tracking simulator, a simulation model is run in parallel with a physical process controlled by the process' control system. At the same time, a tracking mechanism is used to keep the state of the simulation model as close as possible to the real process by continually adjusting parameters of the model. The selection of these parameters impacts directly on the quality of the tracking simulation results and it is a complex task in processes with a big number of variables. This paper presents two case studies of tracking simulation where the controlled parameters are selected using different techniques. The first case study deals with a laboratory-scale hot water generation process where the parameters' selection is performed manually. The second case study deals with a combined heat and power production process with major uncertainties in the process structure. In this case, we focus on the variance decomposition method used to determine the most suitable controlled parameters. Conclusions and future work are finally presented.

U2 - 10.1109/INDIN.2016.7819254

DO - 10.1109/INDIN.2016.7819254

M3 - Conference article in proceedings

SN - 978-1-5090-2871-9

SP - 726

EP - 729

BT - 2016 IEEE 14th International Conference on Industrial Informatics (INDIN)

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Santillán Martinez G, Miettinen T, Aikala A, Savolainen J, Kondelin K, Karhela T et al. Parameters selection in predictive online simulation. In 2016 IEEE 14th International Conference on Industrial Informatics (INDIN). Institute of Electrical and Electronic Engineers IEEE. 2016. p. 726-729 https://doi.org/10.1109/INDIN.2016.7819254