Online mass flow prediction in CFB boilers

Andriy Ivannikov, Mykola Pechenizkiy, Jorn Bakker, Timo Leino, Mikko Jegoroff, Tommi Kärkkäinen, Sami Äyrämö

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

2 Citations (Scopus)

Abstract

Fuel feeding and inhomogeneity of fuel typically cause process fluctuations in the circulating fluidized bed (CFB) process. If control systems fail to compensate for the fluctuations, the whole plant will suffer from fluctuations that are reinforced by the closed-loop controls. This phenomenon causes a reduction of efficiency and lifetime of process components. Therefore, domain experts are interested in developing tools and techniques for getting better understanding of underlying processes and their mutual dependencies in CFB boilers. In this paper we consider an application of data mining technology to the analysis of time series data from a pilot CFB reactor. Namely, we present a rather simple and intuitive approach for online mass flow prediction in CFB boilers. This approach is based on learning and switching regression models. Additionally, noise canceling, and windowing mechanisms are used for improving the robustness of online prediction. We validate our approach with a set of simulation experiments with real data collected from the pilot CFB boiler.
Original languageEnglish
Title of host publicationAdvances in Data Mining. Applications and Theoretical Aspects
Subtitle of host publication9th Industrial Conference, ICDM 2009 proceedings
EditorsPetra Perner
Place of PublicationBerlin - Heidelberg
PublisherSpringer
Pages206-219
ISBN (Electronic) 9783642030666
DOIs
Publication statusPublished - 2009
MoE publication typeA4 Article in a conference publication
EventAdvances in data mining : applications and theoretical aspects : 9th Industrial Conference, ICDM 2009 - Leipzig, Germany
Duration: 20 Jul 200922 Jul 2009

Publication series

SeriesLecture Notes in Computer Science
Number5633
ISSN0302-9743

Conference

ConferenceAdvances in data mining : applications and theoretical aspects
Abbreviated titleICDM 2009
CountryGermany
CityLeipzig
Period20/07/0922/07/09

Fingerprint

Fluidized beds
Boilers
Fluidized bed process
Data mining
Time series
Control systems
Experiments

Cite this

Ivannikov, A., Pechenizkiy, M., Bakker, J., Leino, T., Jegoroff, M., Kärkkäinen, T., & Äyrämö, S. (2009). Online mass flow prediction in CFB boilers. In P. Perner (Ed.), Advances in Data Mining. Applications and Theoretical Aspects: 9th Industrial Conference, ICDM 2009 proceedings (pp. 206-219). Berlin - Heidelberg: Springer. Lecture Notes in Computer Science, No. 5633 https://doi.org/10.1007/978-3-642-03067-3_17
Ivannikov, Andriy ; Pechenizkiy, Mykola ; Bakker, Jorn ; Leino, Timo ; Jegoroff, Mikko ; Kärkkäinen, Tommi ; Äyrämö, Sami. / Online mass flow prediction in CFB boilers. Advances in Data Mining. Applications and Theoretical Aspects: 9th Industrial Conference, ICDM 2009 proceedings. editor / Petra Perner. Berlin - Heidelberg : Springer, 2009. pp. 206-219 (Lecture Notes in Computer Science; No. 5633).
@inproceedings{a0e51ba2b8de4f4eb324fde45c1ee4a3,
title = "Online mass flow prediction in CFB boilers",
abstract = "Fuel feeding and inhomogeneity of fuel typically cause process fluctuations in the circulating fluidized bed (CFB) process. If control systems fail to compensate for the fluctuations, the whole plant will suffer from fluctuations that are reinforced by the closed-loop controls. This phenomenon causes a reduction of efficiency and lifetime of process components. Therefore, domain experts are interested in developing tools and techniques for getting better understanding of underlying processes and their mutual dependencies in CFB boilers. In this paper we consider an application of data mining technology to the analysis of time series data from a pilot CFB reactor. Namely, we present a rather simple and intuitive approach for online mass flow prediction in CFB boilers. This approach is based on learning and switching regression models. Additionally, noise canceling, and windowing mechanisms are used for improving the robustness of online prediction. We validate our approach with a set of simulation experiments with real data collected from the pilot CFB boiler.",
author = "Andriy Ivannikov and Mykola Pechenizkiy and Jorn Bakker and Timo Leino and Mikko Jegoroff and Tommi K{\"a}rkk{\"a}inen and Sami {\"A}yr{\"a}m{\"o}",
year = "2009",
doi = "10.1007/978-3-642-03067-3_17",
language = "English",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
number = "5633",
pages = "206--219",
editor = "Petra Perner",
booktitle = "Advances in Data Mining. Applications and Theoretical Aspects",
address = "Germany",

}

Ivannikov, A, Pechenizkiy, M, Bakker, J, Leino, T, Jegoroff, M, Kärkkäinen, T & Äyrämö, S 2009, Online mass flow prediction in CFB boilers. in P Perner (ed.), Advances in Data Mining. Applications and Theoretical Aspects: 9th Industrial Conference, ICDM 2009 proceedings. Springer, Berlin - Heidelberg, Lecture Notes in Computer Science, no. 5633, pp. 206-219, Advances in data mining : applications and theoretical aspects , Leipzig, Germany, 20/07/09. https://doi.org/10.1007/978-3-642-03067-3_17

Online mass flow prediction in CFB boilers. / Ivannikov, Andriy; Pechenizkiy, Mykola; Bakker, Jorn; Leino, Timo; Jegoroff, Mikko; Kärkkäinen, Tommi; Äyrämö, Sami.

Advances in Data Mining. Applications and Theoretical Aspects: 9th Industrial Conference, ICDM 2009 proceedings. ed. / Petra Perner. Berlin - Heidelberg : Springer, 2009. p. 206-219 (Lecture Notes in Computer Science; No. 5633).

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

TY - GEN

T1 - Online mass flow prediction in CFB boilers

AU - Ivannikov, Andriy

AU - Pechenizkiy, Mykola

AU - Bakker, Jorn

AU - Leino, Timo

AU - Jegoroff, Mikko

AU - Kärkkäinen, Tommi

AU - Äyrämö, Sami

PY - 2009

Y1 - 2009

N2 - Fuel feeding and inhomogeneity of fuel typically cause process fluctuations in the circulating fluidized bed (CFB) process. If control systems fail to compensate for the fluctuations, the whole plant will suffer from fluctuations that are reinforced by the closed-loop controls. This phenomenon causes a reduction of efficiency and lifetime of process components. Therefore, domain experts are interested in developing tools and techniques for getting better understanding of underlying processes and their mutual dependencies in CFB boilers. In this paper we consider an application of data mining technology to the analysis of time series data from a pilot CFB reactor. Namely, we present a rather simple and intuitive approach for online mass flow prediction in CFB boilers. This approach is based on learning and switching regression models. Additionally, noise canceling, and windowing mechanisms are used for improving the robustness of online prediction. We validate our approach with a set of simulation experiments with real data collected from the pilot CFB boiler.

AB - Fuel feeding and inhomogeneity of fuel typically cause process fluctuations in the circulating fluidized bed (CFB) process. If control systems fail to compensate for the fluctuations, the whole plant will suffer from fluctuations that are reinforced by the closed-loop controls. This phenomenon causes a reduction of efficiency and lifetime of process components. Therefore, domain experts are interested in developing tools and techniques for getting better understanding of underlying processes and their mutual dependencies in CFB boilers. In this paper we consider an application of data mining technology to the analysis of time series data from a pilot CFB reactor. Namely, we present a rather simple and intuitive approach for online mass flow prediction in CFB boilers. This approach is based on learning and switching regression models. Additionally, noise canceling, and windowing mechanisms are used for improving the robustness of online prediction. We validate our approach with a set of simulation experiments with real data collected from the pilot CFB boiler.

U2 - 10.1007/978-3-642-03067-3_17

DO - 10.1007/978-3-642-03067-3_17

M3 - Conference article in proceedings

T3 - Lecture Notes in Computer Science

SP - 206

EP - 219

BT - Advances in Data Mining. Applications and Theoretical Aspects

A2 - Perner, Petra

PB - Springer

CY - Berlin - Heidelberg

ER -

Ivannikov A, Pechenizkiy M, Bakker J, Leino T, Jegoroff M, Kärkkäinen T et al. Online mass flow prediction in CFB boilers. In Perner P, editor, Advances in Data Mining. Applications and Theoretical Aspects: 9th Industrial Conference, ICDM 2009 proceedings. Berlin - Heidelberg: Springer. 2009. p. 206-219. (Lecture Notes in Computer Science; No. 5633). https://doi.org/10.1007/978-3-642-03067-3_17