تخمین پارامترهای ژئومکانیکی، تجزیه و تحلیل تنش های برجا، و تعیین پنجره وزن بهینه گل با استفاده از الگوریتم های یادگیری ماشین

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشگاه فردوسی مشهد- گروه زمین شناسی مهندسی- دانشکده علوم

2 گروه زمین‌شناسی، دانشکده علوم، دانشگاه فردوسی مشهد، مشهد، ایران

3 استاد. دانشگاه منابع انرژی استاونگر نروژ

4 دکتری شرکت نفت جنوب

چکیده

نگاره‌های مربوط به چاه‌های نفتی تفسیر/پردازش می‌شوند تا خصوصیات پتروفیزیکی، مکانیکی و ژئومکانیکی درجا را برای سنگ‌های پیرامون چاه‌های نفتی تشخیص دهند. اما همه نگاره‌ها به دلیل هزینه بالا و مشکلات زمین‌شناسی امکان برداشت امکان‌پذیر نمی‌باشد. به‌طور مثال نگاره‌های مربوط به‌کندی موج‌های صوتی حاوی اطلاعات ژئوفیزیکی و ژئومکانیکی حیاتی برای تعیین مدول‌های الاستیسیته دینامیکی، مدول یانگ، مدول بالک، مقاومت/آمپدانس صوتی، مدول برشی و نسبت پواسون سنگ‌های پیرامون در اطراف دیواره چاه هستند. بنابراین در این تحقیق ابتدا دو چاه تصادفی از یکی از میدان‌های نفتی جنوب ایران برگزیده شد که یکی به‌عنوان چاه آموزشی جهت تعیین مدل مناسب و دیگری جهت پیش‌بینی زمان موج‌های صوتی انتخاب شد. این داده‌ها با استفاده از طیف وسیعی از روش‌های یادگیری ماشین و تنظیم فراپارمترها (Hyperparameter Tuning) روی الگوریتم‌ها، بهترین مدل‌ها جهت پیش‌بینی/ تخمین لاگ‌های صوتی ارائه شد، در این فرایند، از بین روش‌های رگرسیون، روش k - نزدیک‌ترین همسایه (KNN) و از بین روش‌های ترکیبی الگوریتم جنگل تصادفی (Random Forest Regression) و الگوریتم درختان اضافی (Extra Tree Regression) بالاترین ضریب همبستگی را نشان داده‌اند. درنتیجه الگوریتم درختان اضافی جهت مدل‌سازی بر روی داده‌های آموزشی و آزمایشی چاه انجام گرفت. سپس این مدل جهت پیش‌بینی/سنتز زمان موج‌های صوتی طولی و برشی چاه هدف بکار گرفته شد. سپس با مقایسه داده‌های واقعی چاه هدف، مقدار خطای جذر میانگین مربعات و مجذور R به دست آمد. در ادامه با استفاده از روابط پورالاستیک تنش‌های برجا میدان تعیین شدند و معلوم گردید مخزن سروک و ایلام در رژیم تنش معکوس و مخزن آسماری در رژیم تنش نرمال تا امتدادلغز قرار دارند. در پایان با استفاده از معیارهای مکانیک سنگ بهترین وزن بهینه گل حفاری در چاه مورد مطالعه ارائه شد.

کلیدواژه‌ها


عنوان مقاله [English]

Estimation of Geomechanical Parameters, In Situ Stress Measurement Techniques, and Determination of Safe Mud Weight Windows Using Machine Learning Algorithm Methods

نویسندگان [English]

  • Hamid Ghalibaf Mohammad Abadi 1
  • HAMID Hafezi Moghaddas 2
  • Gholam Reza Lashkaripour 2
  • Raoof Gholami 3
  • Hossin Talebi, 4
1 Ferdowsi University of Mashhad
2 Department of Geology, Faculty of Science, Ferdowsi University of Mashhad, Mashhad, Iran
3 Department of Energy Resources at University of Stavanger
4 Southern Oilfields Company
چکیده [English]

Oil wells & boreholes logs data are interpreted/processed to identify petrophysical, mechanical, and in-situ geomechanical properties for rocks around oil wells, due to high cost and geological problems, some well logs cannot be measured. For example, sonic logs contain geophysical, and geomechanical information critical to determining the modulus of dynamic elasticity, Young's modulus, the bulk modulus, acoustic resistance/impedance, the shear modulus, and the Poisson's ratio of rocks around the well’s wall. Therefore, in this paper, two random wells were selected from one of the oil fields in southern Iran, one of which was selected as training well to determine the appropriate model and the other to predict the shear and compressional wave slowness. Data analyses were performed using a range of machine learning methods and setting hyperparameter tuning on algorithms, the best models were selected for predicting/estimating sonic logs. In this process, among the regression methods, the K-nearest neighbors algorithm (KNN), and among the combined methods, the Random Forest Regression algorithm and the Extra Tree Regression algorithm show the highest correlation coefficient. As a result, the extra tree algorithm for modeling was performed on the training sets and testing sets data of the well. Then this model was used to predict and synthesize the slowness acoustic compressional and the slowness acoustic shear of the target well. Then, by comparing the actual data of the target well, the root mean square error and the R-squared were obtained. Then, using poroelastic equations, the field stresses were determined and found that Sarvak and Ilam reservoirs are in reverse stress regime and Asmari reservoir is in normal stress regime up to Strike-slip. At the end of this article, using the rock mechanics criteria, the best optimal safe mud weight windows in the studied was presented.

کلیدواژه‌ها [English]

  • Machine Learning Methods
  • Hyperparameter Tuning
  • K-Nearest Neighbor Method (KNN)
  • Combined Methods
  • Random Forest Regression
  • Extra Tree Regression
  • Geomechanical Parameter Estimation
[1] Halliburton Geomechanics, “http”//www.halliburton.com/en- US/ps/consulting/ petroleum- geomechanics. Page? Node- id=hkv12s6j”
[2] Schlumberger (2016) Real-time drilling geomechanics. http://www. slb.com/~/media/Files/dcs/product_sheets/geomechanics/geome chanics_rt_ps.pdf. Checked on 18 Nov 2016.
[3] Aadnoy BS (2003) Introduction to special issue on borehole stability. J Pet Sci Eng 38(3–4):79–82.
[4] Mody FK (2013) Bridging the gap: challenges in deploying leading edge geomechanics technology to reducing well construction costs. In: SPE/IADC Indian drilling technology conference and exhibition. Mumbai, India, 16 October 2006. Society of Petroleum Engineers.
[5] Aslannezhad M, Khaksar manshad A, Jalalifar H (2016) Determination of a safe mud window and analysis of wellbore stability to minimize drilling challenges and non-productive time. J Pet Explor Prod Technol 6:493–503. https://doi.org/10.1007/s1320 2-015-0198-2
[6] Kolawole O, Federer-Kovács G, Szabó I (2018) susceptibility to wellbore instability and sand production in the Pannonian Basin, Hungary. American Rock Mechanics Association, Alexandria.
[7] Wang Y, Watson R, Rostami J et al (2014) Study of borehole stability of Marcellus shale wells in longwall mining areas. J Pet Explor Prod Technol 4:59–71. https://doi.org/10.1007/s1320 2-013-0083-9.
[8] Ashena, R., Elmgerbi, A., Rasouli, V., Ghalambor, Rabiei, M., Bahrami, A., (2020). Severe wellbore instability in a complex lithology formation necessitating casing while drilling and continuous circulation system, Journal of Petroleum Exploration and Production Technology (2020) 10:1511–1532 https://doi.org/10.1007/s13202-020-00834-3.
 [9] Yu, Yanxiang, (2020). Synthetic Sonic Log Generation, SPWLA, viewed 20 April 2020.
[10] Hall, B., oct, (2016). Facies classification using machine learning. Lead. Edge 35 (10), 906–909. https://doi.org/10.1190/tle35100906.1.
[11] Bestagini, P., Lipari, V., Tubaro, S., aug, )2017(. A machine learning approach to facies classification using well logs. In: SEG Technical Program Expanded Abstracts 2017. Society of Exploration Geophysicists, pp. 2137–2142. https://doi.org/10.1190/ segam2017-17729805.1.
[12] Ashraf, U., Zhu, P., Yasin, Q., Anees, A., Imraz, M., Mangi, H.N., Shakeel, S., (2019). Classification of reservoir facies using well log and 3D seismic attributes for prospect evaluation and field development: a case study of Sawan gas field, Pakistan. J. Petrol. Sci. Eng. 175, 338–351. https://doi.org/10.1016/j.petrol.2018.12.060.
[13] Ashraf, U., Zhang, H., Anees, A., Mangi, H.N., Ali, M., Ullah, Z., Zhang, X., (2020a). Application of unconventional seismic attributes and unsupervised machine learning for the identification of fault and fracture network. Appl. Sci. https://doi.org/ 10.3390/app10113864 Jiang, R., (2020). Building a rock physics model for the.
[14] Ali, M., Ma, H., Pan, H., Ashraf, U., formation evaluation of the Lower Goru sand reservoir of the Southern Indus Basin in Pakistan. J. Petrol. Sci. Eng. https://doi.org/10.1016/j.petrol.2020.107461
[15] Marco, I., John, F., Fred, J., (2021). Improving facies prediction by combining supervised and unsupervised learning methods: Journal of Petroleum Science and Engineering 200 (2021) 108300
[16] Muhammad Ali, A., Ren Jiang, B., Huolin Ma, A., Heping Pan, A., Khizar Abbas, C., Umar Ashraf, D., (2021). Machine learning - A novel approach of well logs similarity based on synchronization measures to predict shear sonic logs: Journal of Petroleum Science and Engineering 203 (2021) 108602.
[17] Thiago Santi, B., Marcelo Kehl, D., Tiago, J., Girelli, F., Chemale, J., (2020). Evaluation of machine learning methods for lithology classification using geophysical data: Computers and Geosciences 139(2020)104475.
[18] M. Anemangely, A. Ramezanzadeh, H. Amiri, S.A. Hoseinpour, (2019). Machine learning technique for the prediction of shear wave velocity using petrophysical logs J. Petrol. Sci. Eng., 174 (2019), pp. 306-32.
[19] A.Al-Anazi, I.D.Gates, (2010). A support vector machine algorithm to classify lithofacies and model permeability in heterogeneous reservoirs. Engineering Geology. Volume 114, Issues 3–4, 10 August 2010, Pages 267-277.
[20] Scikit Learn, (2020). K Nearest Neighbors Documentation, sklearn, viewed 20 April 2020, <https://scikit-     learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsRegressor.html#sklearn.neighbors.KNeigh borsRegressor>
[21] Scikit Learn, (2020), GridSearchCV Documentation, sklearn, viewed 20 April 2020, <https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html>
[22] Fjaer E, Holt RM, Raaen AM, Risnes R, Horsrud P (2008) Petroleum related rock mechanics, 2nd edn. Elsevier Science, Amsterdam.
[23] Zoback, M.D., (2007) Reservoir Geomechanics. Cambridge, United Kingdom; Cambridge University Press
[24] Singh R., Kainthola, A, and Singh T.N. (2012). “Estimation of elastic constant of rocks using an ANFIS approach”, Applied Soft Computing, 12, pp. 40–45.
[25] Roy S, Gebert J., Stasiuk G., Romana P., Weidenmann K. A., and Wanner, A. (2011). “Complete determination of elastic moduli of interpenetrating metal/ceramic composites using ultrasonic techniques and micromechanical modeling”, Materials Science and Engineering A, 528, pp. 8226-8235.
[26] Ghalibaf, H., Hafezi Moghaddas, N., Lashkaripoor, G.R., Raoof G., Hossin T., (2022). Determination of geomechanical zones based on evaluation of Unsupervised Machine Learning algorithm methods “JOURNAL OF PETROLEUM GEOMECHANICS (JPG).: (DOI) 10.22107/jpg.2022.329417.1158.
[27] Fjaer E., Holt R.M., Hordrud P., Raaen A.M. and R. Risnes. (2008). “Petroleum related rock Rock Mechanic”, Developments in Petroleum Science, Elsevier.
[28] Barton N (2006) Rock quality, seismic velocity, attenuation and anisotropy. Taylor and Francis, Oxford
[29] Holt RM (2013) Static and dynamic moduli—so equal, and yet so different. Presented at the 47th US rock mechanics symposium held in San Francisco, CA, USA, 23–26 June
[30] Wang Z (2000) Dynamic vs. static properties of reservoir rocks. In: Wang Z, Nur A (eds) Seismic and acoustic velocities in reservoir rocks, vol 3: recent developments. SEG, Tulsa.
[31] Larsen I, Fjaer E, Renlie L (2000) Static and dynamic Poisson’s ratio of weak sandstones. In: ARMA-2000-0077, 4th North American rock mechanics symposium, 31 July–3 August, Seattle, Washington.
[32] Bradford I.D.R., Fuller J., Thompson P.J and Walsgrove T.R.: “Benefits of Assessing Solids Production Risk In A North Sea Reservoir Using Elastoplastic Modelling,” SPE/ISRM 47360, SPE/ISRM Eurock ’98 held in Trondheim, Norway, 8-10 July 1998.
[33] Chang C, Zoback M, Khaksar A (2006) Empirical relations between rock strength and physical properties in sedimentary rocks. J Pet Sci Eng 51(3–4):223–237
[34] Plumb R (1994) Infuence of composition and texture on the failure properties of clastic rocks. In: SPE 28022-MS, Rock mechanics in petroleum engineering, 29–31 August, Delft, Netherlands
[35] Schlumberger (2016) Real-time drilling geomechanics. http://www. slb.com/~/media/Files/dcs/product_sheets/geomechanics/geome chanics_rt_ps.pdf. Checked on 18 Nov 2016.
[36] Dugan B, Flemings PB (1998) Pore pressure prediction from stacking velocities in the Eugene Island 330 Field (Ofshore Lousiana). Gas Research Institute, Chicago, p 23
[37] Zhang J (2011) Pore pressure prediction from well logs: methods, modifcations, and new approaches. Earth Sci Rev 108(1–2):50–63.
[38] Mouchet JP, Mitchell A (1989) Abnormal pressures while drilling: origins, prediction, detection, evaluation. Elf EP-Editions, Editions Technip, Paris.
[39] Mavko G, Mukerji T, Godfrey N (1995) Predicting stress-induced velocity anisotropy in rocks. Geophysics 60:1081–1087. https:// doi.org/10.1190/1.1443836.
[40] Breckels, I. M. and Van Eekelen, H. A. M. (1981). “Relationship between horizontal stress and depth in sedimentary basins: Paper SPE10336, 56th Annual Fall Technical Conference.” Society of Petroleum Engineers of AIME, San Antonio, Texas, October 5–7.
[41] Blanton TL, Olson JE (1997) Stress magnitudes from logs: efects of tectonic strains and temperature. SPE-38719-MS, Presented at SPE annual technical conference and exhibition, 5–8 October, San Antonio, Texas.
[42] Kidambi, T., Kumar, G. S., “Mechanical Earth Modeling for a vertical well drilled in a naturally fractured tight carbonate gas reservoir in the Persian Gulf”, Journal of Petroleum Science and Engineering, Vol. 141, pp. 38-51, 2016.
[43] Zoback M (2010) Reservoir geomechanics. Cambridge University Press, Cambridge
[44] Sinha BK, Vissapragada B, Renlie L, Skomedal E (2006) Horizontal stress magnitude estimation using the three shear moduli—a norwegian sea case study. Soc Petrol Eng. https://doi. org/10.2118/103079-MS
[45] Sayers C, Nagy Z, Vasudev S, Tagbor K, Hooyman P (2009) Determination of in situ stress and rock strength using borehole acoustic data. SEG Technical Program
[46] Kirsch G, (1898) Die Theorie der Elastizitat und die Bedurfnisse der Festigkeitslehre. Zeitschrift des Verlines Deutscher Ingenieure. 42:707.
[47] Goodman RE (1989) Introduction to rock mechanics. Wiley, Hoboken.
[48] Nelson, E.J., (2005). Transverse drilling-induced tensile fractures in the West Tuna area,Gippsland Basin, Australia: implications for the in situ stress regime. 42, pp. 361- 371.
[49] Al-Ajmi, A.M., and Zimmerman, R.W. (2006). “Stability analysis of vertical boreholes using the Mogi–Coulomb failure criterion”. Int. J. Rock Mech. Min. Sci., 43, pp. 1200- 1211.
[50] Guo B, Ghalambor A (2002) Gas volume requirements for underbalanced drilling. Pennwell Corporation, Tulsa. ISBN 0-87814-802-7.
[51] Aadnoy BS, Looyeh R (2010) Petroleum rock mechanics: drilling operations and well design. Gulf Professional Publishing, Elsevier, Amsterdam
[52] Bowes C, Procter R (1997) Drillers stuck pipe handbook, guidelines and drillers handbook credits. Schlumberger, UK
[53] Simangunsong RA, Villatoro JJ, Davis AKM (2006) Wellbore stability assessment for highly inclined wells using limited rockmechanics data. SPE-99644. Presented at the 2006 SPE annual technical conference and exhibition, San Antonio, Texas, USA, 24–27 September
 [54] Zhang J, Yu M, Al-Bazali TM, Ong S, Chenevert ME, Sharma MM, Clarc DE (2006) Maintaining the stability of deviated and horizontal wells: efects of mechanical, chemical, and thermal phenomena on well designs. SPE-100202, Presented at the 2006 SPE international oil and gas conference and exhibition, Beijing, China, 5–7 December.