نشریه ژئومکانیک و ژئوانرژی

نشریه ژئومکانیک و ژئوانرژی

تخمین کندی فشارشی و فشار منفذی با رزولوشن بالا در میدان نفتی بینالود با استفاده از داده های NMR در آموزش شبکه عصبی

نوع مقاله : مقاله پژوهشی

نویسندگان
1 دانشکده مهندسی معدن، دانشگاه صنعتی اصفهان، اصفهان، ایران
2 اداره پتروفیزیک، شرکت ملی نفت فلات قاره ایران، تهران؛ ایران
چکیده
فشار منفذی یکی از پارامترهای اساسی در مهندسی نفت است. عدم تعیین صحیح و دقیق این پارامتر می تواند به مشکلاتی جدی نظیر فوران چاه در زمان حفاری و یا مدلسازی نادرست مخزن منجر شود. از سوی دیگر استفاده از روشهای تجربی محاسبه فشار منفذی نیز عموما با استفاده از داده های کندی فشارشی نمودار صوتی سنتی انجام می شود که رزولوشن قائم محدودی در حد 1/0 متر دارند. به این ترتیب ممکن است پدیده هایی نازک که تغییرات فشار منفذی قابل توجهی دارند شناسایی نشوند. برای رفع این مشکل، پژوهش حاضر ابتدا با استفاده از داده های متنوع نمودار NMR به تخمین کندی فشارشی با رزولوشن 005/0 متر در چاه شماره 6 میدان نفتی بینالود پرداخته و سپس با استفاده از این کندی فشار منفذی را محاسبه کرده است. به این منظور از داده‌های نمودار NMR و کندی فشارشی نمودار صوتی سنتی برای طراحی یک شبکه‌ی عصبی پرسپترون چندلایه استفاده شد که کندی موج فشارشی را با استفاده از پارامترهای NMR تخمین می زند. شبکه یاد شده در مرحله اعتبار سنجی توانست کندی فشارشی را با ضریب همبستگی 94/0 و خطای نسبی 03/0 تخمین بزند. با تعمیم شبکه عصبی به کل اعماق دارای داده NMR، کندی فشارشی با رزولوشن بالا در اعماق 2179 تا 2275 متری در سازند بورگان محاسبه شد. سپس فشار منفذی با استفاده معادله ایتون و به کارگیری داده های نمودار صوتی و کندی فشارشی تخمین زده شد. بر اساس نمودار فشار منفذی به دست آمده، شرایط فشار نرمال تا حدود عمق 1700 متری برقرار است و در اعماق بیشتر پدیده فرافشار به صورت غیر یکنواخت تا کف چاه ادامه دارد. این تحقیق همچنین نشان داد که استفاده از کندی تخمین زده شده با رزولوشن بالا توانست تغییراتی تا حد psi50 را در چاه بارزسازی کند که بدون استفاده از آن داده ها قابل تشخیص نبودند.
کلیدواژه‌ها

عنوان مقاله English

High-resolution estimation of compressional slowness and pore pressure in the Binaloud oil field using NMR data in neural network training

نویسندگان English

Arghavan Haghighatjou 1
Sayyed Mohammad Abtahi Foroshani 1
Nader Fathianpour 1
Bita Arbab 2
1 Department of Minining Engineering, Isfahan University of Technology, Isfahan, Iran
2 Department of Petrophysics, Iranian Offshore Oil Company, Tehran, Iran
چکیده English

Pore pressure is a fundamental parameter in petroleum engineering. Failure to determine this parameter correctly and accurately can lead to serious problems, such as well blowouts during drilling or incorrect reservoir modeling. On the other hand, empirical methods of calculating pore pressure are generally based on compressional slowness data obtained from conventional sonic logs, which have a limited vertical resolution of about 0.1 m. Consequently, thin features with significant pore pressure variations may not be identified. To address this problem, the present study first estimated compressional slowness with a vertical resolution of 0.005 m using diverse Nuclear Magnetic Resonance (NMR) log data in Well No. 6 of the Binaloud oil field, and then calculated pore pressure using this slowness. For this purpose, NMR log data and compressional slowness from the conventional sonic log were employed to design a multilayer perceptron neural network that predicts compressional slowness from NMR parameters. In the validation stage, the network was able to estimate compressional slowness with a correlation coefficient of 0.94 and a relative error of 0.03. By generalizing the neural network to all depths containing NMR data, high-resolution compressional slowness was calculated in the depth interval of 2179 to 2275 m within the Burgan Formation. Subsequently, pore pressure was estimated using Eaton’s equation, which employed both sonic log data and compressional slowness. According to the resulting pore pressure profile, normal pressure conditions are maintained down to approximately 1700 m, whereas at greater depths, overpressure occurs heterogeneously down to the bottom of the well. This study also demonstrated that using high-resolution estimated slowness enabled the identification of variations up to 50 psi in the well, which could not have been detected without these data.

کلیدواژه‌ها English

NMR log
MDT pressure measurement
compressional slowness
pore pressure
artificial neural networks
Ogbu, A. D., K. A. Iwe, W. Ozowe, and A. H. Ikevuje, "Advances in rock physics for pore pressure prediction: A comprehensive review and future directions," Engineering Science & Technology Journal, vol. 5, no. 7, pp. 2304-2322, 2024 .
[2] Ringrose P. and M. Bentley, Reservoir model design. Springer, 2016 .
[3] B. E. Law and C. Spencer, "Abnormal pressure in hydrocarbon environments," 1998 .  
[4] Ebrom D., P. Heppard, M. Mueller, and L. Thomsen, "Pore pressure prediction from Swave, C-wave, and P-wave velocities," in SEG International Exposition and Annual Meeting, 2003: SEG, pp. SEG-2003-1370  
[5] Azadpour M. and N. Shad Manaman, "Determination of pore pressure from sonic log: a case study on one of Iran carbonate reservoir rocks," Iranian Journal of Oil and Gas Science and Technology, vol. 4, no. 3, pp. 37-50, 2015 .                
 [6] Setiawan, B. N. Hendri, and W. Triyoso, "Pore Pressure Prediction Using Seismic Velocity And Analysis Mechanisme Overpressure Cased Study In BW Field, North Sumatera Basin ".
[7] Alam, J.,  R. Chatterjee, and S. Dasgupta, "Estimation of pore pressure, tectonic strain and stress magnitudes in the Upper Assambasin: a tectonically active part of India," Geophysical Journal International, vol. 216, no. 1, pp. 659-675, 2019 . 
 Talinga D. and  C. Reine, "Integrating pore pressure and lithology prediction from well and seismic data to characterize abnormal pressures in the compartmentalized Volve oil field," Central North Sea: Canadian SEG, Recorder, vol. 25, 2021 .
[9] Li,  H., et al., "A Comprehensive Prediction Method for Pore Pressure in Abnormally High-Pressure Blocks Based on Machine Learning," Processes, vol. 11, no. 9, p. 2603, 2023 .
[10] Al-Hamad, H., A. A. Shaikh, L. a. Bo Gammaz, M. Al-Ajmi, and A. Al-Jasmi, "Reservoir characterization of  heavy oil in Burgan Formation of North Kuwait," in SPE International Heavy Oil Conference and Exhibition, 2018: SPE, p. D022S032R002  .
[11] Ebrahimi, D., A. Amini, A. Solgi, and E. Hajikazemi, "An Integrated Appraisal of Burgan Reservoir in Soroosh Oil Field, Using Petrographic and Petrophysical Approaches," Open Journal of Geology, vol. 6, no. 09, p. 1014, 2016 .
[12] Mehrabi, H., B. Esrafili-Dizaji, E. Hajikazemi, B. Noori, and H. MohammadRezaei, "Reservoir characterization of the Burgan Formation in northwestern Persian Gulf," Journal of Petroleum Science and Engineering, vol. 174, pp. 328-350, 2019 .
[13] Dasgupta, T. S. Mukherjee, T. Dasgupta, and S. Mukherjee, "Pore pressure determination methods," Sediment compaction and applications in petroleum geoscience, pp. 1930, 2020 .
[14] Li, C. L. Zhan, and H. Lu, "Mechanisms for overpressure development in marine sediments," Journal of Marine Science and Engineering, vol. 10, no. 4, p. 490, 2022 .
[15] Dutta, N. C. R. Bachrach, and T. Mukerji, Quantitative analysis of geopressure for geoscientists and engineers. Cambridge University Press, 2021 .
[16] Neuzil, C. "Abnormal pressures as hydrodynamic phenomena," American journal of Science, vol. 295, no. 6, pp. 742786, 1995 .
[17] Zhang, J. "Pore pressure prediction from well logs: Methods, modifications, and new approaches," Earth-Science Reviews, vol. 108, no. 1-2, pp. 50-63, 2011 . [18] Zhang, J., et al., "In-situ stresses, abnormal pore pressures and their impacts on the Triassic Xujiahe reservoirs in tectonically active western Sichuan basin," Marine and Petroleum Geology, vol. 122, p. 104708, 2020 . 
[18] Zhang, J., et al., "In-situ stresses, abnormal pore pressures and their impacts on the Triassic Xujiahe reservoirs in tectonically active western Sichuan basin," Marine and Petroleum Geology, vol. 122, p. 104708, 2020 . 
[19] Tingay, M. R., R. R. Hillis, R. E. Swarbrick, C. K. Morley, and A. R. Damit, "Origin of overpressure and pore-pressure prediction in the Baram province, Brunei  ",Aapg Bulletin, vol. 93, no. 1, pp. 51-74, 2009 .
[20] Zhang, J., "Effective stress, porosity, velocity and abnormal pore pressure prediction accounting for compaction disequilibrium and unloading," Marine and Petroleum Geology, vol. 45, pp. 2-11, 2013 .
[21] Hottman C. and R. Johnson, "Estimation of formation pressures from log-derived shale properties," AAPG Bulletin, vol. 49, no. 10, pp. 1754-1754, 1965 .
[22] Azadpour,  M., N. S. Manaman, A. Kadkhodaie-Ilkhchi, and M.-R. Sedghipour, "Pore pressure prediction and modeling using well-logging data in one of the gas fields in south of Iran," Journal of Petroleum Science and Engineering, vol. 128, pp. 15-23, 2015 .
[23] Allen, D., et al., "Trends in NMR logging," Oilfield review, vol. 12, no. 3, pp. 2-19, 2000 .
[24] Coates, G. R., L. Xiao, and M. G. Prammer, "NMR logging: principles and applications," No Title), 1999 .
[25] Chang, Y., K. Zhang, and Y. Zhang, "New Model for Absolute Permeability Prediction in Coal Samples: Application of Modified Purcell Model to Mercury Injection Pressure and Nuclear Magnetic Resonance Data," ACS omega, vol. 8, no. 23, pp. 21120-21132, 2023 .
[26] Chi, L., and Z. Heidari, "Directionalpermeability assessment in formations with complex pore geometry with a new nuclearmagnetic-resonance-based permeability model," SPE Journal, vol. 21, no. 04, pp. 1436-1449, 2016 .
[27] Kenyon,  W., P. Day, C. Straley, and J. Willemsen, "A three-part study of NMR longitudinal relaxation properties of watersaturated sandstones," SPE formation evaluation, vol. 3, no. 03, pp. 622-636, 1988 .
[28] Chollet, F. and F. Chollet, Deep learning with Python. Simon and Schuster, 2021.  
[29]     Elshahawi, H., K, Fathy and  S. Hiekal, "Capillary pressure and rock wettability effects on wireline formation-tester measurements", In SPE Annual Technical Conference and Exhibition (paper SPE56712-MS, 1999.
[30]     Hillis, R. R., and  S. D. Thomas, "Wellbore failure induced by formation testing", Petroleum Geoscience, 5(3), 235–239, 1999.