Новый подход к выбору методов увеличения нефтеотдачи на основе нечеткой логики и байесовских механизмов вывода

Главная

Статья в Elpub

РУС ENG

Территория «НЕФТЕГАЗ». 2015; : 48-55

Новый подход к выбору методов увеличения нефтеотдачи на основе нечеткой логики и байесовских механизмов вывода

Сулейманов Б. А., Исмаилов Ф. С., Дышин О. А., Маммедбейли Т. Э.

Аннотация

Список литературы

1. Альварадо В., Манрик Э. Методы увеличения нефтеотдачи пластов. Планирование и стратегии применения. - М.: Премиум Инжиниринг, 2011. - 244 с.

2. Shokir E.M., Sayyoch M.H. Selertion and evaLuation EOR method using artifical intelligence. SPE 79163. 2002.

3. ELements of the Petroleum Industry. Ed. by de Golyer E. AIME, New York, 289, 289 (1940).

4. Taber J. Research on enchanced oiL recovery: past, present and future. Pure & Appl. Chem. Vol. 52. P. 1323-1347. Pergamon Press Ltd., 1980. Printed in Great Britain.

5. Taber J.J., Martin F.D., and Seright R.S. EOR Screcning Criteria Revisited. Part 1: Introduction to Screenig Criteria and Enhanccd Recovery Field Projects; Part 2: Applications and Impact of Oil Prices. SPE Reservour Engineering, August 1997. P. 189-198; 199-205.

6. Barrutet M.A. Introduction to Enhanced Oil Recorery (EOR) Methods. Class Notes for PETE 609, Module 1. P. 1/57-44/57.

7. Syed Fahad I., Tunio Abdul H., Ghirano Naveed A. Compositional Analysis and Screening for Enhanced Oil Recovery Process in Different Reservourand Operating Conditions. Intern. Journal of Applied Science and Technology, Vol. 1. No. 4; July 2011. P. 143-160.

8. Zerafat M.M., Ayatolahi Sh, Mehranbod N., Barregan D. Bayesian Network Analysis as a Tool for Efficient EOR Screening. SPE 143282, July 2011. P. 1-16.

9. Wang С. Bayesian Network Simulation. Department of Computer Science Florida State University. February 24, 2003. P. 73.

10. Parkinson W.J. et al. Screening EOR Methods with Fuzzy logic. Presented at 1991 International Reservoir Characterization Conference, Tulsa, Oklahoma, 3-5 November.

11. Ivanov E.N., Roslyak A.T. The Selection and Evaluation of Enhanced Oil Recovery Methods Effectiveness for Oil Fields in the Western Siberia. International Journal of Science «Georesources», 2012, 6(48): 87-90.

12. Morooka C.K., Guilherne I.R., Mendes J.R.P. Development of intelligent systems for well drilling and petroleum production (2001). 32, 191-199.

13. Mohagheugh Sh.D. A new methodology for the identification of best practices in the oil and gas industry intelligent systems. Journal Pet. Sci. & Eng., 2005. 49, 239-260.

14. De Cristo M.A.P., Calado P.P., Silva M.l.S.I., Muntz R., Riberto-Neto B. Bayesian belief networks for IR. International J. Approximate Reasoning, 2003. 34, 163-179.

15. Korb K.B., Nicholson A.E. Bayesian artificial intelligence. Chapman & Hall/CRC, 2004.

16. Cheng J. Efficient stochastic sampling algorithms for Bayesian networks. University of Pittsburgh, 2001. 154 pp.

17. Дюбуа Д., Прад А. Теория возможностей. Приложения к представлению знаний в информатике / Пер. с фр. - М.: Радио и связь, 1990. - 288 с.

18. Заложенкова И.А., Парасюк И.Н. Интегрированная система проверки гипотез: программно-алгоритмические средства // Кибернетика и системный анализ. - 1997. - № 5. -С. 50-58.

19. Веревка О.В., Заложенкова И.А., Парасюк И.Н. Обобщение интервальных байсовских механизмов вывода и перспективы их использования // Кибернетика и системный анализ. - 1998. - № 6. - С. 3-13.

20. Zadeh L.A. A meaning representation Language for naturaL Languages. Memo No.UCB/ERL M77/61, University of California, Berkeley, CA (1977).

21. Shaw J., Bachu, S. Screening, Evaluation, and Ranking of Oil Reservoirs Suitable for CO2 -Flood EOR and Carbon Dioxide Sequestration. Review and Publication Process, September 2002, Vol. 49, No. 9. P. 51-61.

22. Aladasani A., Bai B. Recent Developments and Updated Screening Criteria of Enhanced Oil Recovery Techniques, SPE 130726, 2010.

23. Bang V., Phillips C. A New Screening Model for Gas and Water Based EOR Processer. SPE 165217, 2013.

Territorija “NEFTEGAS” [Oil and Gas Territory]. 2015; : 48-55

A new approach to selection of enhanced oil recovery methods on the basis of the fuzzy logics and Bayesian inference mechanisms

Suleimanov B. A., Ismailov F. S., Dyshyn O. A., Mammedbeyli T. E.

Abstract

Currently, the procedure for selecting the enhanced oil recovery methods (EORM) when designing the oil fields development represents the procedure that is not formalized in full. At the same time, selection of the best available technology of enhanced oil recovery for certain geological, physical and economic conditions of the development is one of the most complicated tasks for development engineers. Informative review of the history, present and prospects for development of EORM studies is provided by Taber, who also proposed the tables known in literature as Taber tables. However, the Taber's approach does not allow performing a mathematically strict ranking of EORM by extent of their applicability for certain field. This paper proposes the approach to EORM selection on the basis of a fuzzy logics, possibility theory and Bayesian inference mechanisms. The methods are ranked by each criterion parameter by marking the best method for this parameter applying rules for fuzzy interval comparison. The results obtained after assessing the extent of applicability of each EORM are specified with the use of the summarized interval Bayesian inference mechanisms. Applying this method for physical and geological conditions of the Albert field allowed selecting EORM in a more correct way confirming the reliability and practicality of the proposed approach. Simple calculation procedure (no more than five iterations) allows computerizing the process of selecting the most acceptable EORM for a certain field.

References

1. Al'varado V., Manrik E. Metody uvelicheniya nefteotdachi plastov. Planirovanie i strategii primeneniya. - M.: Premium Inzhiniring, 2011. - 244 s.

2. Shokir E.M., Sayyoch M.H. Selertion and evaLuation EOR method using artifical intelligence. SPE 79163. 2002.

3. ELements of the Petroleum Industry. Ed. by de Golyer E. AIME, New York, 289, 289 (1940).

4. Taber J. Research on enchanced oiL recovery: past, present and future. Pure & Appl. Chem. Vol. 52. P. 1323-1347. Pergamon Press Ltd., 1980. Printed in Great Britain.

6. Barrutet M.A. Introduction to Enhanced Oil Recorery (EOR) Methods. Class Notes for PETE 609, Module 1. P. 1/57-44/57.

8. Zerafat M.M., Ayatolahi Sh, Mehranbod N., Barregan D. Bayesian Network Analysis as a Tool for Efficient EOR Screening. SPE 143282, July 2011. P. 1-16.

9. Wang S. Bayesian Network Simulation. Department of Computer Science Florida State University. February 24, 2003. P. 73.

10. Parkinson W.J. et al. Screening EOR Methods with Fuzzy logic. Presented at 1991 International Reservoir Characterization Conference, Tulsa, Oklahoma, 3-5 November.

12. Morooka C.K., Guilherne I.R., Mendes J.R.P. Development of intelligent systems for well drilling and petroleum production (2001). 32, 191-199.

13. Mohagheugh Sh.D. A new methodology for the identification of best practices in the oil and gas industry intelligent systems. Journal Pet. Sci. & Eng., 2005. 49, 239-260.

14. De Cristo M.A.P., Calado P.P., Silva M.l.S.I., Muntz R., Riberto-Neto B. Bayesian belief networks for IR. International J. Approximate Reasoning, 2003. 34, 163-179.

15. Korb K.B., Nicholson A.E. Bayesian artificial intelligence. Chapman & Hall/CRC, 2004.

16. Cheng J. Efficient stochastic sampling algorithms for Bayesian networks. University of Pittsburgh, 2001. 154 pp.

17. Dyubua D., Prad A. Teoriya vozmozhnostei. Prilozheniya k predstavleniyu znanii v informatike / Per. s fr. - M.: Radio i svyaz', 1990. - 288 s.

18. Zalozhenkova I.A., Parasyuk I.N. Integrirovannaya sistema proverki gipotez: programmno-algoritmicheskie sredstva // Kibernetika i sistemnyi analiz. - 1997. - № 5. -S. 50-58.

19. Verevka O.V., Zalozhenkova I.A., Parasyuk I.N. Obobshchenie interval'nykh baisovskikh mekhanizmov vyvoda i perspektivy ikh ispol'zovaniya // Kibernetika i sistemnyi analiz. - 1998. - № 6. - S. 3-13.

20. Zadeh L.A. A meaning representation Language for naturaL Languages. Memo No.UCB/ERL M77/61, University of California, Berkeley, CA (1977).

22. Aladasani A., Bai B. Recent Developments and Updated Screening Criteria of Enhanced Oil Recovery Techniques, SPE 130726, 2010.

23. Bang V., Phillips C. A New Screening Model for Gas and Water Based EOR Processer. SPE 165217, 2013.

Новый подход к выбору методов увеличения нефтеотдачи на основе нечеткой логики и байесовских механизмов вывода

Аннотация

A new approach to selection of enhanced oil recovery methods on the basis of the fuzzy logics and Bayesian inference mechanisms

Abstract

События