تخمین مدول یانگ با نگارهای پتروفیزیکی و الگوریتم‌های یادگیری عمیق در یکی از میادین هیدروکربنی ایران

نوع مقاله : علمی-پژوهشی

نویسندگان

1 دانشجوی دکترا، دانشکده مهندسی معدن، دانشکدگان فنی، دانشگاه تهران، تهران

2 استاد، دانشکده مهندسی معدن، دانشکدگان فنی، دانشگاه تهران، تهران

3 استادیار، دانشکده مهندسی معدن، دانشکدگان فنی، دانشگاه تهران، تهران

چکیده

مدول یانگ یکی از پارامترهای مهم در مدل‌سازی‌ ژئومکانیکی و یکی از پیش نیازهای اساسی برای تحلیل پایداری دیواره چاه در طول مسیر حفاری چاه‌های نفت و گازی است. برای تعیین مدول یانگ مدل‌های تجربی زیادی معرفی شده‌اند که هر کدام از آنها مختص منطقه‌ای خاص هستند. یکی از روش‌هایی که اخیرا زیاد مورد استفاده قرار می‌گیرد روش‌های هوشمند است. در این مطالعه سعی شده است تا مدول یانگ دینامیک با استفاده از الگوریتم‌های یادگیری عمیق در یکی از چاه‌های مخازن هیدروکربنی جنوب غرب ایران پیش‌بینی شود. برای استفاده از الگوریتم‌های یادگیری عمیق ویژگی‌های موثر برای تخمین مدول یانگ برای ورودی الگوریتم‌ها با تعیین ضریب همبستگی پیرسون مشخص شدند. در ادامه با استفاده از شبکه‌های ترکیبی CNN+LSTM, LSTM+MLP مدول یانگ تخمین زده شد و مقدار ضریب تعیین برای این الگوریتم‌ها برای داده‌های آموزش و تست نزدیک به 1 و خطای پیش‌بینی هر دو الگوریتم بسیار کم به دست آمده است. همچنین برای اطمینان از نتایج الگوریتم‌ها بخشی از داده به عنوان داده شاهد کنار گذاشته شد و خطا و ضریب تعیین برای آن محاسبه گردید که مقادیر خطا (MSE) برای شبکه‌های ترکیبی CNN+LSTM و LSTM+MLP به ترتیب برابر 99/25 و 51/30 و مقادیر ضریب تعیین (R2) آنها به ترتیب برابر 81/0 و 77/0 به دست آمده است. نتایج حاصل بیان‌کننده کارآیی الگوریتم‌های یادگیری عمیق معرفی شده در پیش‌بینی مدول یانگ است ولی در مقایسه دو الگوریتم ارایه شده، الگوریتم CNN+LSTM دقت بالاتر و خطای کمتری دارد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Estimation of Young's Modulus Using Petrophysical Logs and Deep Learning Algorithms in One of Iran's Hydrocarbon Fields

نویسندگان [English]

  • F. Mollaei 1
  • A. Moradzadeh 2
  • R. Mohebian 3
1 Ph.D Student, School of Mining, College of Engineering, University of Tehran, Tehran, Iran
2 Professor, School of Mining, College of Engineering, University of Tehran, Tehran, Iran
3 Assistant Professor, School of Mining, College of Engineering, University of Tehran, Tehran, Iran
چکیده [English]

Young's modulus is one of the important parameters in geomechanical and petrophysical modelling, which is an indicator of rock hardness. Calculation of this parameter is one of the basic prerequisites for analyzing the stability of the well wall during the drilling of oil and gas wells. Many experimental models have been introduced to determine Young's modulus; each of them is used for a specific area. One of the recently used methods is intelligent methods. In this study, an attempt has been made to predict dynamic Young's modulus using deep learning algorithms in one of the hydrocarbon reservoir wells in southwest Iran. In order to use deep learning algorithms, it is first necessary to determine the effective features to estimate the Young's modulus as input of the algorithms. In this article, Pearson's correlation coefficient was used to select these features. In the following, Young's modulus was estimated using CNN+LSTM and LSTM+MLP hybrid networks, and their coefficient of determination (R2) values were determined to be close to 1, and the prediction error of both algorithms was very low for training and test data. Moreover, to ensure the results of the algorithms, a part of the data was set aside as blind data, and the error and R2 values were calculated for it. The mean square error (MSE) of the LSTM+MLP and CNN+LSTM hybrid algorithms was obtained as equal to 30.51 and 25.99, and their R2 values were determined as 0.77 and 0.81, respectively. The results show the effectiveness of deep learning algorithms introduced in predicting Young's modulus, but comparing the two presented algorithms, the CNN+LSTM algorithm has higher accuracy and less error.

کلیدواژه‌ها [English]

  • Young's modulus
  • petrophysical data
  • CNN+LSTM algorithm
  • LSTM+MLP algorithm
  • Model evaluation

مراجع

  1. Tutuncu, A. N., Podio, A. L., Gregory, A. R., and Sharma, M. M. (1998). “Nonlinear Viscoelastiic Behavior of Sedimentary Rocks, Part I: Effect of Frequency on Strain Amplitude”. Geophysics, 63(1): 11-318.
  2. Jaeger, J. C., and Cook, N. G. W. (1976). “Fundamentals of Rock Mechanics”. Chapman and Hall, London, pp. 585.
  3. Valim, S. M., and Antia, L. S. (2021). “The Use of Well-Log Data in the Geomechanical Characterization of Middle Cambrian Tight Sandstone Formation: A Case Study from Eastern Pomerania, Poland”. Energies, 14(19): 6022. DOI: https://doi.org/10.3390/en14196022.
  4. Roy, D. G., and Singh, T. N. (2018). “Regression and soft computing models to estimate young’s modulus of CO2 saturated coals”. Measurement, 129: 91-101.
  5. Matin, S. S., Farahzadi, L., Makaremi, S., Chelgani, S. C., and Sattari, G. (2018). “Variable selection and prediction of uniaxial compressive strength and modulus of elasticity by random forest”. Applied Soft Computing, 70: 980-987.
  6. Tariq, Z., Abdulraheem, A., Mah, M., and Ahmed, A. (2018). “A rigorous data-driven approach to predict Poisson’s ratio of carbonate rocks using a functional network”. Petrophysics-The SPWLA Journal of Formation Evaluation and Reservoir Description, 59(06): 761-777.
  7. Abdi, Y., Garavand, A. T., and Sahamieh, R. Z. (2018). “Prediction of strength parameters of sedimentary rocks using artificial neural networks and regression analysis”. Arabian Journal of Geosciences, 11: 587.
  8. Ghasemi, E., Kalhori, H., Bagherpour, R., and Yagiz, S. (2018). “Model tree approach for predicting uniaxial compressive strength and Young’s modulus of carbonate rocks”. Bulletin of Engineering Geology and the Environment, 77: 331-343.
  9. Umrao, R. K., Sharma, L. K., Singh, R., and Singh, T. N. (2018). “Determination of strength and modulus of elasticity of heterogenous sedimentary rocks: An ANFIS predictive technique”. Measurement, 126: 194-201.
  10. Mahmoud, A. A., Elkatatny, S., Ali, A., and Moussa, T. (2019)., “Estimation of static young’s modulus for sandstone formation using artificial neural networks”. Energies, 12(11): 2125. DOI: https://doi.org/10.3390/en12112125.
  11. Yang, L., Feng, X., and Sun, Y. (2019). “Predicting the Young’s Modulus of granites using the Bayesian model selection approach”. Bulletin of Engineering Geology and the Environment, 78: 3413-3423.
  12. Davarpanah, S. M., Ván, P., and Vásárhelyi, B. (2020). “Investigation of the relationship between dynamic and static deformation moduli of rocks”. Geomechanics and Geophysics for Geo-Energy and Geo-Resources, 6: 29.
  13. Waqas, U., and Ahmed, M. F. (2020). “Prediction Modeling for the Estimation of Dynamic Elastic Young’s Modulus of Thermally Treated Sedimentary Rocks Using Linear–Nonlinear Regression Analysis, Regularization, and ANFIS”. Rock Mechanics and Rock Engineering, 53: 5411-5428.
  14. Mahmoud, A. A., Elkatatny, S., Alsabaa, A., and Shehri, D. A. (2020). “Functional neural networks-based model for prediction of the static Young’s modulus for sandstone formations”. In Conference: 54th US Rock Mechanics/Geomechanics Symposium, OnePetro.
  15. Shahani, N. M., Zheng, X., Liu, C., Hassan, F. U., and Li, P. (2021). “Developing an XGBoost Regression Model for Predicting Young’s Modulus of Intact Sedimentary Rocks for the Stability of Surface and Subsurface Structures”. Frontiers in Earth Science, 9: 761990.
  16. Ceryan, N. (2021). “Prediction of Young’s modulus of weathered igneous rocks using GRNN, RVM, and MPMR models with a new index”. Journal of Mountain Science, 18: 233-251.
  17. Köken, E. (2021). “Assessment of Deformation Properties of Coal Measure Sandstones through Regression Analyses and Artificial Neural Networks”. Archives of Mining Sciences (AMS), 66: 523-542.
  18. Awais Rashid, H. M., Ghazzali, M., Waqas, U., Malik, A. A., and Abubakar, M. Z. (2021). “Artificial Intelligence-Based Modeling for the Estimation of Q-Factor and Elastic Young’s Modulus of Sandstones Deteriorated by a Wetting-Drying Cyclic Process”. Archives of Mining Sciences (AMS), 66: 635-658.
  19. Cao, J., Gao, J., Nikafshan Rad, H., Mohammed, A. S., Hasanipanah, M., and Zhou, J. (2022). “A novel systematic and evolved approach based on XGBoost-firefly algorithm to predict Young’s modulus and unconfined compressive strength of rock”. Engineering with Computers, 38(Suppl 5): 3829-3845. DOI: https://doi.org/10.1007/s00366-020-01241-2.
  20. Siddig, O., Gamal, H., Elkatatny, S., and Abdulraheem, A. (2021). “Real-time prediction of Poisson’s ratio from drilling parameters using machine learning tools”. Scientific Reports, 11: 12611. DOI: https://doi.org/10.1038/s41598-021-92082-6.
  21. Ahmed, A., Elkatatny, S., and Alsaihati, S. (2021). “Applications of Artificial Intelligence for Static Poisson’s Ratio Prediction While Drilling”. Computational Intelligence and Neuroscience, 2021: 9956128. DOI: https://doi.org/10.1155/2021/9956128.
  22. Siddig, O., and Elkatatny, S. (2021). “Workflow to build a continuous static elastic moduli profile from the drilling data using artificial intelligence techniques”. Journal of Petroleum Exploration and Production Technology, 11: 3713-3722. DOI: https://doi.org/10.1007/s13202-021-01274-3.
  23. Singh, R., Kainthola, A., and Singh, T. N. (2012). “Estimation of elastic constant of rocks using an ANFIS approach”. Applied Soft Computing, 12(1): 40-45. DOI: https://doi.org/10.1016/j.asoc.2011.09.010.
  24. Yesiloglu-Gultekin, N., and Gokceoglu, C. (2022). “A Comparison Among Some Non-linear Prediction Tools on Indirect Determination of Uniaxial Compressive Strength and Modulus of Elasticity of Basalt”. Journal of Nondestructive Evaluation, 41: 10. DOI: https://doi.org/10.1007/s10921-021-00841-2.
  25. Shahani, N. M., Xigui Zheng, X., Guo, X., and Wei, X. (2022). “Machine Learning-Based Intelligent Prediction of Elastic Modulus of Rocks at Thar Coalfield”. Sustainability, 14(6): 3689. DOI: https://doi.org/10.3390/su14063689.
  26. Jin, X., Zhao, R., and Ma, Y. (2022). “Application of a Hybrid Machine Learning Model for the Prediction of Compressive Strength and Elastic Modulus of Rocks”. Minerals, 12(12): 1506. DOI: https://doi.org/10.3390/min12121506.
  27. Motiei, H. (2009). “Petroleum geology of the Persian Gulf”. Tehran University Press.
  28. Mehrgini, B., Izadi, H., and Memarian, H. (2019). “Shear wave velocity prediction using Elman artificial neural network”. Carbonates and Evaporites, 34: 1281-1291. DOI: https://doi.org/10.1007/s13146-017-0406-x.
  29. Salehinejad, H., Sankar, S., Barfett, J., Colak, E., and Valaee, S. (2017). “Recent advances in recurrent neural networks”. arXiv preprint arXiv:1801.01078. DOI: https://doi.org/10.48550/arXiv.1801.01078.
  30. Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, L., Wang, G., Cai, J., and Chen, T. (2017). “Recent advances in convolutional neural networks”. Pattern Recognition, 77: 354-377. DOI: https://doi.org/10.1016/j.patcog.10.013.

فایل ها

سابقه مقاله

  • تاریخ دریافت: 31 اردیبهشت 1403
  • تاریخ بازنگری: 16 دی 1403
  • تاریخ پذیرش: 23 بهمن 1403

هم رسانی

ارجاع به این مقاله

آمار