Rationale for the type of the membership function of fuzzy parameters of locomotive intelligent control systems

Authors

  • Тетяна Василівна Бутько Ukrainian State Academy of Railway Transport Square Feuerbach, 7, Kharkov, Ukraine, 61050, Ukraine
  • Олександр Борисович Бабанін Ukrainian University of Railway Transport area Feierbakha, 7, Kharkov, Ukraine, 61050, Ukraine https://orcid.org/0000-0001-7500-336X
  • Олександр Миколайович Горобченко Ukrainian University of Railway Transport area Feierbakha, 7, Kharkov, Ukraine, 61050, Ukraine https://orcid.org/0000-0002-9868-3852

DOI:

https://doi.org/10.15587/1729-4061.2015.35996

Keywords:

train control, fuzzy number, locomotive crew, membership function

Abstract

Presentation of the train speed as a fuzzy number is justified by the impossibility to accurately predict this value. This is caused by deviation of many train and locomotive parameters in operating conditions. According to statistics, the actual train speed is different from the design speed by up to 5 km/h. According to the distribution of the speed deviation from the design value, a hypothesis about using t- and π-class membership functions was proposed. It was found that with the fuzziness coefficient values less than 2, it is necessary to use the triangular activation function to present the fuzzy variables. If the fuzziness coefficients are greater than 2, it is reasonable to use both classes of membership functions. This will allow to apply artificial intelligence theory methods in modeling the decision support system for locomotive crews.

Author Biographies

Тетяна Василівна Бутько, Ukrainian State Academy of Railway Transport Square Feuerbach, 7, Kharkov, Ukraine, 61050

Professor
Management of operational work

Олександр Борисович Бабанін, Ukrainian University of Railway Transport area Feierbakha, 7, Kharkov, Ukraine, 61050

Professor, Doctor of technical sciences

The department Maintenance and repair of rolling stock

Олександр Миколайович Горобченко, Ukrainian University of Railway Transport area Feierbakha, 7, Kharkov, Ukraine, 61050

Associate professor, Candidate of technical science

The department Maintenance and repair of rolling stock

References

  1. Gorobchenko, O. M. (2014). Metodologіchnі osnovi pobudovi іntelektual'nih sistem pіdtrimki prijnyattya rіshen' dlya lokomotivnih brigad. Mezhdunarodnyj informacionnyj nauchno-tekhnicheskij zhurnal "Lokomotiv-inform", 8, 12–13.
  2. Jiang, C., Yang, J., Yuan, J., Xu, F. (2012). Overview of Intelligent Railway Transportation Systems in China. Intelligent Automation & Soft Computing, 18 (6), 627–634. doi:10.1080/10798587.2012.10643272
  3. But'ko, T. V., Prohorchenko, A. V. (2007). Udoskonalennya sistemi operativnogo upravlіnnya pasazhirs'kimi perevezennyami na osnovі vikoristannya іntelektual'nih tekhnologіj. Suchasnі іnformacіjnі tekhnologії na transportі, v promislovostі ta osvіtі. Dnіpropetrovs'k:DNUZT, 55.
  4. Gapanovich, V. A., Rozenberg, E. N. (2011). Osnovnye napravleniya razvitiya intellektual'nogo zheleznodorozhnogo transporta Zheleznodorozhnyj transport, 4, 5–11.
  5. Rozenberg, E. N. (2011). Sovremennye tekhnologii dlya perekhoda k intellektual'nomu zheleznodorozhnomu transportu». Vsemirnyj ehlektrotekhnicheskij kongresse (VEHLK-2011). Moscow. Available at: http://www.ruscable.ru/print.html?p=/article/Sovremennye_texnologii_dlya_perexoda_k/
  6. Intelligent Transport Systems (ITS) for sustainable mobility (2012). UN, Economic Commission for Europe, UNECE. Geneva, 120.
  7. Tarasov, V. A. Gerasimov, B. M., Levin, I. A., Kornejchuk, V. A. (2007). Intellektual'nye sistemy podderzhki prinyatiya reshenij. Teoriya, sintez, ehffektivnost'. Kiev: MAKNS, 336.
  8. Mitaim, S., Kosko, B. (2001). The shape of fuzzy sets in adaptive function approximation. IEEE Trans. Fuzzy Syst., 9 (4), 637–656. doi:10.1109/91.940974
  9. Raskin, L. G., Seraya, O. V. (2008). Nechetkaya matematika: monogr. Kharkiv: Parus, 352.
  10. Demin, D. A. (2013). Nechetkaya klasterizaciya v zadache postroenie modelej «sostav – svojstvo» po dannym passivnogo ehksperimenta v usloviyah neopredelyonnosti. Problemy mashinostroeniya, 6, 15–23.
  11. Danilova, N. V. (2010). Primenenie metoda nechetkih srednih dlya postroeniya funkcij prinadlezhnosti parametrov tekhnologicheskogo processa. Innovacionnye tekhnologii, modelirovanie i avtomatizaciya v metallurgii. Sankt-Peterburg, 11–12.
  12. Dzharratano Dzh., Rajli, G. (2007). Ekspertnye sistemy: principy razrabotki i programmirovanie. Moscow: OOO "I.D.Vil'yams", 1152.
  13. Rutkovskaya, D. Pilin'skij, M., Rutkovskij, L. (2006). Nejronnye seti, geneticheskie algoritmy i nechetkie sistemy M.: Goryachaya liniya –Telekom, 452.
  14. Gorobchenko, O. M. (2014). Modelyuvannya viniknennya neshtatnoї situacії v ergatichnіj sistemі «lokomotivna brigada – poїzd», 38, 144–147.
  15. Osipov, S. I., Mironov, K. A., Revich, V. I. (1972). Osnovy lokomotivnoj tyagi. Moscow: Transport, 336.

Published

2015-02-27

How to Cite

Бутько, Т. В., Бабанін, О. Б., & Горобченко, О. М. (2015). Rationale for the type of the membership function of fuzzy parameters of locomotive intelligent control systems. Eastern-European Journal of Enterprise Technologies, 1(3(73), 4–8. https://doi.org/10.15587/1729-4061.2015.35996

Issue

Section

Control processes