skip to main content
tutorial

Online mass flow prediction in CFB boilers with explicit detection of sudden concept drift

Published: 27 May 2010 Publication History

Abstract

Fuel feeding and inhomogeneity of fuel typically cause fluctuations in the circulating fluidized bed (CFB) process. If control systems fail to compensate the fluctuations, the whole plant will suffer from dynamics that is reinforced by the closed-loop controls. This phenomenon causes reducing efficiency and the lifetime of process components. In this paper we address the problem of online mass flow prediction, which is a part of control. Particularly, we consider the problem of learning an accurate predictor with explicit detection of abrupt concept drift and noise handling mechanisms. We emphasize the importance of having domain knowledge concerning the considered case and constructing the ground truth for facilitating the quantitative evaluation of different approaches. We demonstrate the performance of change detection methods and show their effect on the accuracy of the online mass flow prediction with real datasets collected from the experimental laboratory-scale CFB boiler.

References

[1]
J. Bakker, M. Pechenizkiy, I. Zliobaite, A. Ivannikov, and T. Kärkkäinen. Handling outliers and concept drift in online mass flow prediction in CFB boilers. In KDD Workshop on Knowledge Discovery from Sensor Data, pages 13--22. ACM, 2009.
[2]
A. Bifet and R. Gavald`a. Learning from time-changing data with adaptive windowing. In Proc. of SIAM Int. Conf. on Data Mining (SDM 2009). SIAM, 2007.
[3]
V. Chandola, A. Banerjee, and V. Kumar. Anomaly detection: A survey. ACM Computing Surveys, 2009.
[4]
J. Gama and C. G. Learning with local drift detection. In Proc. Int. Conf. on Advanced Data Mining and Applications (ADMA 2006), volume 4093 of LNCS, pages 42--55. Springer, 2006.
[5]
R. A. Horn and C. R. Johnson. Topics in matrix analysis. Cambridge University Press, Cambridge, 1991.
[6]
A. Ivannikov, M. Pechenizkiy, J. Bakker, T. Leino, M. Jegoroff, T. Kärkkäinen, and S. Äyrämö. Online mass flow prediction in CFB boilers. In Proc. of Industrial Conf. on Data Mining (ICDM 2009), volume 5633 of LNCS, pages 206--219. Springer, 2009.
[7]
M. Kubat and G. Widmer. Adapting to drift in continuous domains. In In Proc. of European Conf. on Machine Learning (ECML 1995), pages 307--310. Springer, 1995.
[8]
L. I. Kuncheva. Classifier ensembles for detecting concept change in streaming data: Overview and perspectives. In Proc. of ECAI Workshop SUEMA'08, pages 5--10, 2008.
[9]
A. Kusiak and A. Burns. Mining temporal data: A coal-fired boiler case study. In Proc. of Int. Conf. on Knowledge-Based Engineering Systems (KES 2005), volume 3683 of LNAI, pages 953--958. Springer, 2005.
[10]
B. R. C. Y. L. Huilin, Z. Guangboa and D. Gidaspowb. A coal combustion model for circulating fluidized bed boilers. Fuel, 79:165--172, 2000.
[11]
C. L. Lawson and R. J. Hanson. Solving Least Squares Problems. Prentice-Hall, Englewood Cliffs, 1974.
[12]
H. B. Mann and D. R. Whitney. On a test of whether one of two random variables is stochastically larger than the other. Annals of Math. Statistics, 18:50--60, 1947.
[13]
C. K. Park and P. Bas. A model for prediction of transient response to the change of fuel feed rate to a circulating fluidized bed boiler furnace. Chemical Engineering Science, 52:3499--3509, 1997.
[14]
J. Saastamoinen. Modelling of dynamics of combustion of biomass in fluidized beds. Thermal Science, 8:107--126, 2004.
[15]
I. Zliobaite, J. Bakker, and M. Pechenizkiy. OMFP: An approach for online mass flow prediction in CFB boilers. In Proc. of Int. Conf. Discovery Science (DS'09), volume 5808 of LNCS, pages 272--286. Springer, 2009.

Cited By

View all
  • (2024)How Does a Firm Adapt in a Changing World? The Case of Prosper MarketplaceMarketing Science10.1287/mksc.2022.019843:3(673-693)Online publication date: 1-May-2024
  • (2024)Concept drift challenge in multimedia anomaly detection: A case study with facial datasetsSignal Processing: Image Communication10.1016/j.image.2024.117100123(117100)Online publication date: Apr-2024
  • (2022)The TriLS Approach for Drift-Aware Time-Series Prediction in IIoT EnvironmentIEEE Transactions on Industrial Informatics10.1109/TII.2021.312982518:10(6581-6591)Online publication date: Oct-2022
  • Show More Cited By
  1. Online mass flow prediction in CFB boilers with explicit detection of sudden concept drift

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM SIGKDD Explorations Newsletter
    ACM SIGKDD Explorations Newsletter  Volume 11, Issue 2
    December 2009
    128 pages
    ISSN:1931-0145
    EISSN:1931-0153
    DOI:10.1145/1809400
    Issue’s Table of Contents

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 27 May 2010
    Published in SIGKDD Volume 11, Issue 2

    Check for updates

    Qualifiers

    • Tutorial

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)6
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 19 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2024)How Does a Firm Adapt in a Changing World? The Case of Prosper MarketplaceMarketing Science10.1287/mksc.2022.019843:3(673-693)Online publication date: 1-May-2024
    • (2024)Concept drift challenge in multimedia anomaly detection: A case study with facial datasetsSignal Processing: Image Communication10.1016/j.image.2024.117100123(117100)Online publication date: Apr-2024
    • (2022)The TriLS Approach for Drift-Aware Time-Series Prediction in IIoT EnvironmentIEEE Transactions on Industrial Informatics10.1109/TII.2021.312982518:10(6581-6591)Online publication date: Oct-2022
    • (2022)Practical Evaluation of Poisoning Attacks on Online Anomaly Detectors in Industrial Control SystemsComputers & Security10.1016/j.cose.2022.102901122(102901)Online publication date: Nov-2022
    • (2021)FlexSketch: Estimation of Probability Density for Stationary and Non-Stationary Data StreamsSensors10.3390/s2104108021:4(1080)Online publication date: 4-Feb-2021
    • (2021)Poisoning attacks on cyber attack detectors for industrial control systemsProceedings of the 36th Annual ACM Symposium on Applied Computing10.1145/3412841.3441892(116-125)Online publication date: 22-Mar-2021
    • (2021)Online Rebuilding Regression Random ForestsKnowledge-Based Systems10.1016/j.knosys.2021.106960221(106960)Online publication date: Jun-2021
    • (2020)Targeting Prospective CustomersManagement Science10.1287/mnsc.2019.330866:6(2495-2522)Online publication date: 1-Jun-2020
    • (2020)Streaming Data Classification using Hybrid Classifiers to tackle Stability-Plasticity Dilemma and Concept Drift2020 IEEE 4th Conference on Information & Communication Technology (CICT)10.1109/CICT51604.2020.9312077(1-10)Online publication date: 3-Dec-2020
    • (2019)Exploiting Evolving Micro-clusters for Data Stream Classification with Emerging Class DetectionInformation Sciences10.1016/j.ins.2019.08.050Online publication date: Aug-2019
    • Show More Cited By

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media