Advertisement

Quality Assessment of Oil that Difficult to Recover Based on Fuzzy Clustering and Statistical Analysis

  • M. K. KarazhanovaEmail author
  • L. B. Zhetekova
  • K. K. Aghayeva
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1095)

Abstract

Based on the analysis and generalization of literature data, results of the classification of difficult to recover oil selected from Uzen, Zhetibay, Kalamkas, Karakudyk and Karamandybas oil fields of Kazakhstan using fuzzy cluster analysis are presented. Classification of types of difficult to recover oil is considered according to a set of features, including content of sulfur, chlorides, oil density, oil viscosity, permeability of occurrence conditions. Analysis of the classification results of difficult to recover reserves was performed, which showed the need to divide the total sample (set) into homogeneous groups according to a set of classification criteria, for which fuzzy cluster analysis is most suitable. A parameter characterizing the quality of oil is proposed.

Keywords

Hard-to-extract reserves Sulfur Chlorides Viscosity Oil density Quality indicator 

References

  1. 1.
    Maksutov, R., Orlov, G., Osipov, A.: High-viscosity oil reserves completion in Russia. Technol. FEC 6, 36–40 (2005)Google Scholar
  2. 2.
    Yashenko, I.G., Polishyk, U.M.: Difficult to recover oil and tits properties analysis based on the oil quality qualifications. Vestnik Russian Natural Sciences Academy (West-Siberian department), vol. 19, pp. 37–44 (2016)Google Scholar
  3. 3.
    Akhmetov, D.A., Efendiyev, G.M., Karazhanova, M.K., Koylibaev, B.N.: Classification of hard-to-recover hydrocarbon reserves of Kazakhstan with the use of fuzzy cluster-analysis. In: 13th International Conference on Application of Fuzzy Systems and Soft Computing-ICAFS 2018, pp. 865–872 (2018)Google Scholar
  4. 4.
    Efendiyev, G.M., Mammadov, P.Z., Piriverdiyev, I.A., Mammadov, V.N.: Clustering of geological objects using FCM-algorithm and evaluation of the rate of lost circulation. Proc. Comput. Sci. 102, 159–162 (2016)CrossRefGoogle Scholar
  5. 5.
    Efendiyev, G., Mammadov, P., Piriverdiyev, I., Mammadov, V.: Estimation of the lost circulation rate using fuzzy clustering of geological objects by petrophysical properties. Visnyk Taras Shevchenko Nat. Univ. Kyiv 2(81), 28–33 (2018)CrossRefGoogle Scholar
  6. 6.
    Aliev, R.A., Guirimov, B.G.: Type-2 Fuzzy Neural Networks and Their Applications (2014). http://www.springer.com/us/book/9783319090719. Accessed 19 July 2019Google Scholar
  7. 7.
    Turksen, I.B.: Full Type 2 to type n fuzzy system models. In: Seventh International Conference on Soft Computing, Computing with Words and Perceptions in System Analysis, Decision and Control, Turkey, Izmir, pp. 21–22 (2013)Google Scholar
  8. 8.
    Lisovsky, N.N., Khalimov, E.M.: About reserves difficult to recover qualifications. Vestnik CDC Rosnedra. 6, 33–35 (2009)Google Scholar
  9. 9.
    Purtova, I.P., Varichenko, A.I., Shpurov, I.V.: Oil reserves difficult to recover. Terminology. The problems and conditions of completion in Russia, Science and FEC (technical scientific research), vol. 6, pp. 21–26 (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Caspian State University of Technology and Engineering named after Sh. YessenovAktauRepublic of Kazakhstan
  2. 2.Oil and Gas Institute of Azerbaijan National Academy of SciencesBakuAzerbaijan

Personalised recommendations