Statement of the Synthesis Problem of the Intellectual System of Adaptive Management

  • Vladislav S. Mikhailenko
  • Mihail S. Solodovnik
Chapter
Part of the Lecture Notes in Economics and Mathematical Systems book series (LNE, volume 675)

Abstract

The paper presents the task of creating an intelligent system of adaptive management of the production facility. Neuro-fuzzy network is proposed for the adaptation of the traditional PI-controllers in the regulation of steam temperature. Is proposed f new three-level structure of the intellectual system of adaptive control with predictor of quality of the transition process. Simulation of intelligent system implemented by using neuro-fuzzy network for example boiler steam temperature under parametric perturbations showed successful results.

Keywords

Adaptive control system Intelligent system Boiler Superheated steam Neuro-fuzzy network PI - regulator 

References

  1. 1.
    G.D. Krokhin, V.S. Mukhin, I.L. Ivanova, in IFAC WS ESC’06. Energy Saving Control in Plants and Buildings (2006), pp. 177–181Google Scholar
  2. 2.
    V.J. Rotach, Automatic Control Theory (Moscow Power Engineering Institute (MPEI), Moscow, 2008), p. 396Google Scholar
  3. 3.
    V.J. Rotach, Teploenergetika 8, 21–26 (1979)Google Scholar
  4. 4.
    V.J. Rotach, Control Settings Modified by the Ziegler-Nichols (MPEI, Moscow, 2010), pp. 38–42Google Scholar
  5. 5.
    V.J. Rotach, Teploenergetika 10, 50–57 (2010)Google Scholar
  6. 6.
    K.J. Astrom, T.T. Hagglund, Advanced PID Control, vol. 460 (The Instrumentation, Systems, and Automation Society, Research Triangle Park, NC, 2006)Google Scholar
  7. 7.
    A. S. Kluev, Setting up automatic control of boiler. Energy, p. 280 (1970)Google Scholar
  8. 8.
    A.P. Kopelovich, Engineering methods of calculation of automatic regulators, GNTI (1960), p. 190Google Scholar
  9. 9.
    G.P. Pletnev, Computer-aided facilities management of TPP, Energoizdat, p. 361 (1981)Google Scholar
  10. 10.
    V.S. Mikhailenko, R.J. Harchenko, Using of hybrid networks in adaptive control systems of thermal power facilities. VNTU 1, 1–9 (2012)Google Scholar
  11. 11.
    A. Jankowska, Neural models of air pollutants emission in power units combustion processes, in Symposium on Methods of Artificial Intelligence (2003), pp. 141–144Google Scholar
  12. 12.
    A.J. Leonenko, Fuzzy Modeling in Matlab and fuzzyTech (SPb.:BHV, St. Petersburg, 2003), p. 720Google Scholar
  13. 13.
    I.M. Sharovin, Industrial Controllers 2, 27–32 (2010)Google Scholar
  14. 14.
    P. Yang, D.G. Peng, Y.H. Yang, Z.P. Wang, in Proceedings of 2010 International Conference on Machine Learning and Cybernetics, vol. 5 (2010), pp. 3300–3303Google Scholar
  15. 15.
    Monitoring and control of stoker-fired boiler plant using neural networks, UK Department of Trade and Industry, PS-156 (1999)Google Scholar
  16. 16.
    T. Takagi, M. Sugeno, IEEE Trans. Syst. Man Cybern. 15, 116–132 (1985)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Vladislav S. Mikhailenko
    • 1
  • Mihail S. Solodovnik
    • 1
  1. 1.Educational and Scientific Institute of Refrigeration, Cryogenic Technologies and BioenergeticsOdessa National Academy of Food TechnologiesOdessaUkraine

Personalised recommendations