M.K. Karazhanova
Caspian University of Technology and Engineering named after Sh. Yessenov, Kazakhstan, Aktau
Rouzbeh G. Moghanloo
PhD. Professor, University of Oklahoma, USA E-mail: rouzbehmoghanloo@gmail.com
I.A. Piriverdiyev
Institute of Oil and Gas under the Ministry of Education of Azerbaijan, Baku
ASSESSMENT OF OILFIELD EQUIPMENT RELIABILITY CHARACTERISTICS AND DECISION-MAKING UNDER UNCERTAINTY
Abstract. The article is devoted to the results of information analysis and the establishment of the relationship between factors affecting the reliability of oilfield equipment using a fuzzy clustering algorithm. One of the main tasks of oilfield practice is to assess the influence of various factors on the efficiency of field operation and make the right technological decisions. The reliability of estimates and decisions is determined by how reliably the input and output variables and their values are selected. Situations often arise when, given the same data, fundamentally different results are obtained. To find specific expressions of these dependencies and the parameters characterizing them, in particular, methods of statistical data processing are used. As a result of the analysis of the causes of failures of deep-well pumps, factors influencing the efficiency of the pump in the fields under consideration were identified and subjected to fuzzy cluster analysis, which allows us to gain an understanding of the influence of selected factors on efficiency indicators under conditions of uncertainty. A relationship was obtained between the input and output variables, which can be expressed by a fuzzy expression of the IF-THEN rule.
Keywords: reliability, liquid flow rate, turnaround time, fuzzy set theory, fuzzy cluster analysis.
REFERENCES
nbsp;
[1].Yeremin NA. Modern oil and gas fields exploitation. Smart well. Intelligent oilfield. Virtual company. Moscow, #8220;Nedra-business center#8221;, 2008, 244 p. [in Russian]
[2].Altunin AE , Semukhin MV. Models and algorithms of decision-making in fuzzy conditions: Monograph. Tyumen: Publishing of Tyumen State University, 2002, 268 p. [in Russian]
[3].Aliev RA, Guirimov BG. Type-2 Fuzzy Neural Networks and Their Applications. http://www.springer.com/us/book/9783319090719
[4].Demidova LA, Konyaeva EI. Clustering of objects using FCM algorithm on the basis of type-2 fuzzy sets and genetic algorithm. Vestnik of RSREU, ʋ4 (Issue 26). Ryazan, 2008. – [in Russian]
[5].Mohaghegh S. Virtual intelligence and its applications in petroleum engineering. J. Pet. Technol. Distinguished Author Series (2000)
[6].Zadeh L A. #8220;Fuzzy Sets#8221;, #8220;Information and Control#8221;, Vol. 8, p. 338-353, 1965.
[7].Nikravesh Masoud, Dobie Chuck A., Patzek Tad W. Field-Wise Waterflood Management in Low Permeability, Fractured Oil Reservoirs: Neuro-Fuzzy Approach. SPE 37523, SPE International Thermal Operations #038; Heavy Oil Symposium held in Bakersfield, California, U.S.A., 10-12 February 1997.
[8].Ghallab SA, Badr N, Salem AB, Tolba MF. A Fuzzy Expert System For Petroleum Prediction. In: WSEAS, Croatia, vol. 2, p. 77-82 (2013)
[9].Yeremin NA. Modelling of hydrocarbon deposits using fuzzy logic methods. Moscow, “Nauka”, 1994, 462 p. [in Russian]
[10].M.K. Karazhanova, I.A. Piriverdiyev. Analysis of the Impact of Operating Conditions of Pumps on their Efficiency Indicators Using Fuzzy Clustering Algorithm. Procedia Computer Science, Volume 102, 2016, Pages 163-167, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2016.09.384.
УДК 622.24
ГРНТИ 38.59.15
DOI 10.56525/FLZQ3049