کاربرد یادگیری ماشین در پیش‌بینی و مدیریت تولید ماسه در چاه‌های نفت و گاز - مطالعه ی مروری

نوع مقاله : مقاله مروری

نویسندگان
محمدالیاس خداشناس 1
میثم محمدزاده شیرازی 2
بهنام شاهسونی 2
1 دانشجوی کارشناسی ارشد، گروه مهندسی نفت، دانشکده مهندسی شیمی، نفت و گاز، دانشگاه شیراز، شیراز، ایران
2 استادیار، گروه مهندسی نفت، دانشکده مهندسی شیمی، نفت و گاز، دانشگاه شیراز، شیراز، ایران
چکیده
تولید ماسه در چاه‌های نفت و گاز، مشکلات متعددی مانند کاهش بهره‌وری از چاه و خرابی تجهیزات را به‌همراه دارد. به‌منظور جلوگیری از مشکلات و پیامدهای تولید ماسه، اجرای فرایندهای پیش‌بینی و کنترل ماسه در چاه‌ها توصیه می‌شود. این فرایندها شامل بررسی عوامل متعددی از جمله: عمق چاه، گرادیان شکست سازند و سایر پارامترهای زمین‌شناسی می‌باشد. به‌علت حجم انبوه داده‌ها و پیچیدگی‌های تحلیل، روش‌های مرسوم سنتی، زمان‌بر و با عدم قطعیت و احتمال خطای زیادی مواجه‌اند؛ به همین دلیل، استفاده از روش‌های کارآمدتر از اهمیت زیادی برخوردار است؛ در سال‌های اخیر، به‌کارگیری تکنیک‌های یادگیری ماشین برای تحلیل داده‌های زیاد و پیچیده، به‌عنوان روشی مناسب و دقیق در جهت بهبود دقت پیش‌بینی‌ها مطرح شده است. از این‌رو مهندسان بهره‌بردار نیز از الگوریتم‌های یادگیری ماشین، برای تحلیل داده‌های مرتبط با تولید ماسه استفاده کردند. در این مطالعه، مروری بر تحقیقات پیشین، در زمینه‌ی استفاده از یادگیری ماشین در مدیریت تولید ماسه ارائه شده است. همچنین به‌منظور فهم بهتر، مطالعات ذکرشده براساس موضوع به دسته‌های مناسب‌ تفکیک و سازماندهی شده‌اند؛ به‌علاوه، الگوریتم‌ها و روش‌های اعتبارسنجی در هر مطالعه‌ ذکر شده است تا به‌عنوان راهنما مورد استفاده قرارگیرد؛ بنابراین مطالعه‌ی حاضر می‌تواند همچون مرجعی برای مطالعات آینده در این زمینه عمل کند.

کلیدواژه‌ها

موضوعات

عنوان مقاله English

Machine Learning Applications in the Prediction and Management of Sand Production in Oil and Gas Wells-a Review Study

نویسندگان English

Mohammadelyas Khodashenas 1
Meysam Mohammadzadeh Shirazi 2
Behnam Shahsavani 2
1 M.Sc. student, Department of Petroleum Engineering, School of Chemical Engineering, Oil and Gas, Shiraz University, Shiraz, Iran
2 Assistant Professor, Department of Petroleum Engineering, School of Chemical Engineering, Oil and Gas, Shiraz University, Shiraz, Iran
چکیده English

Sand production in oil and gas wells leads to numerous issues, including reduced well productivity and equipment damage. To mitigate the challenges and consequences of sand production, implementing sand prediction and control processes in wells is recommended. These processes involve evaluating multiple factors, such as well depth, formation failure gradient, and other geological parameters. Due to the vast volume of data and the complexity of analysis, conventional traditional methods are time-consuming and prone to significant uncertainties and errors. Consequently, the adoption of more efficient methods has gained considerable importance. In recent years, the application of machine learning techniques for analyzing large and complex datasets has emerged as an effective and accurate approach to improving prediction accuracy. As a result, production engineers have utilized machine learning algorithms to analyze data related to sand production. This study provides a review of previous research on the application of machine learning in managing sand production. To facilitate better understanding, the referenced studies have been categorized and organized based on their focus. Furthermore, the algorithms and validation methods used in each study are specified to serve as a guide. Therefore, this study can serve as a reference for future research in this field.

کلیدواژه‌ها English

Sand Production Prediction
Production and Productivity
Oil Production
Artificial Intelligence
Machine Learning
  1. Cui, L., et al., A survey on application of machine learning for Internet of Things. International Journal of Machine Learning and Cybernetics, 2018. 9: p. 1399-1417.
  2. Zhu, M., et al., A review of the application of machine learning in water quality Eco-Environment & Health, 2022. 1(2): p. 107-116.
  3. Pandey, R.K., A.K. Dahiya, and A. Mandal, Identifying applications of machine learning and data analytics based approaches for optimization of upstream petroleum operations. Energy Technology, 2021. 9(1): p. 2000749.
  4. Otchere, D.A., et al., Application of supervised machine learning paradigms in the prediction of petroleum reservoir properties: Comparative analysis of ANN and SVM models. Journal of Petroleum Science and Engineering, 2021. 200: 108182.
  5. Anifowose, F.A., J. Labadin, and A. Abdulraheem, Ensemble machine learning: An untapped modeling paradigm for petroleum reservoir characterization. Journal of Petroleum Science and Engineering, 2017. 151: p. 480-487.
  6. Salem, A.M., M.S. Yakoot, and O. Mahmoud, Addressing diverse petroleum industry problems using machine learning techniques: literary methodology─ spotlight on predicting well integrity failures. ACS omega, 2022. 7(3): p. 2504-2519.
  7. Anifowose, F., A. Abdulraheem, and A. Al-Shuhail, A parametric study of machine learning techniques in petroleum reservoir permeability prediction by integrating seismic attributes and wireline data. Journal of Petroleum Science and Engineering, 2019. 176: p. 762-774.
  8. Zhang, G., et al., Pattern visualization and understanding of machine learning models for permeability prediction in tight sandstone reservoirs. Journal of Petroleum Science and Engineering, 2021. 200: p. 108142.
  9. Laalam, A., et al. Application of Machine Learning for Mineralogy Prediction from Well Logs in the Bakken Petroleum System. in SPE Annual Technical Conference and Exhibition? SPE.
  10. Xie, C., et al., Intelligent modeling with physics-informed machine learning for petroleum engineering problems. Advances in Geo-Energy Research, 2023. 8(2).
  11. Mai-Cao, L. and H. Truong-Khac, A comparative study on different machine learning algorithms for petroleum production forecasting. Improved Oil and Gas Recovery, 2022. 6.
  12. Ojedapo, B., S.S. Ikiensikimama, and V.U. Wachikwu-Elechi. Petroleum Production Forecasting Using Machine Learning Algorithms. in SPE Nigeria Annual International Conference and Exhibition. 2022. SPE.
  13. Sabah, M., et al., A machine learning approach to predict drilling rate using petrophysical and mud logging data. Earth Science Informatics, 2019. 12: p. 319-339.
  14. Hopgood, A.A., The state of artificial intelligence. Advances in computers, 2005. 65: p. 1-75.
  15. Krithiga, G., V. Mohan, and S. Senthilkumar, A BRIEF REVIEW OF THE DEVELOPMENT PATH OF ARTIFICIAL INTELLIGENCE AND ITS SUBFIELDS. 2023.
  16. Chaudhary, S., et al., A brief review of machine learning and its applications. SAMRIDDHI: A Journal of Physical Sciences, Engineering and Technology, 2020. 12(SUP 1): p. 218-223.
  17. Liu, W., W.D. Liu, and J. Gu. Petroleum production forecasting based on machine learning. in Proceedings of the 2019 3rd International Conference on Advances in Image Processing. 2019.
  18. Azad, M., et al., A new approach to sand production onset prediction using artificial neural networks. Petroleum science and technology, 2011. 29(19): p. 1975-1983.
  19. Gharagheizi, F., et al., Prediction of sand production onset in petroleum reservoirs using a reliable classification approach. Petroleum, 2017. 3(2): p. 280-285.
  20. Olatunji, O.O. and Micheal. Prediction of sand production from oil and gas reservoirs in the Niger Delta using support vector machines SVMs: A binary classification approach. in SPE Nigeria Annual International Conference and Exhibition. 2017. SPE.
  21. Ngwashi, A.R., D.O. Ogbe, and D.O. Udebhulu. Evaluation of machine-learning tools for predicting sand production. in SPE Nigeria Annual International Conference and Exhibition. 2021. SPE.
  22. Song, J., et al., Comparison of Machine Learning Algorithms for Sand Production Prediction: An Example for a Gas-Hydrate-Bearing Sand Case. Energies, 2022. 15(18): p. 6509.
  23. Jing, H., et al. Sand Production Prediction Based on Deep Learning and BP Neural Network. in ARMA US Rock Mechanics/Geomechanics Symposium. 2023. ARMA.
  24. Abuh, F.A., J.U. Akpabio, and A.N. Okon, Machine Learning-Based Models for Basic Sediment & Water and Sand-Cut Prediction in Matured Niger Delta Fields. Journal of Energy Research and Reviews, 2023. 15(2): p. 70-93.
  25. Abdelghany, W.K., M. Hammed, and A.E. Radwan, Implications of machine learning on geomechanical characterization and sand management: a case study from Hilal field, Gulf of Suez, Egypt. Journal of Petroleum Exploration and Production Technology, 2023. 13(1): p. 297-312.
  26. Ngochindo, G.N. and A. Joseph, Predicting Onset of Sand Production in Oil Wells using Machine Learning. Journal of Engineering Research and Reports, 2024. 26(4): p. 165-176.
  27. Shabdirova, A., et al., Sand Production Prediction with Machine Learning using Input Variables from Geological and Operational Conditions in the Karazhanbas Oilfield, Kazakhstan. Natural Resources Research, 2024: p. 1-17.
  28. Asfha, D.T., et al., Mechanisms of sand production, prediction–a review and the potential for fiber optic technology and machine learning in monitoring. Journal of Petroleum Exploration and Production Technology, 2024: p. 1-40.
  29. Kolla, S.S., et al. Utilizing artificial intelligence for determining threshold sand rates from acoustic monitors. in SPE Annual Technical Conference and Exhibition? SPE.
  30. Vieira, R.E., B. Xu, and S.A. Shirazi. Prediction of Sand Transport in Horizontal and Inclined Flow Based on Machine Learning Algorithms. in PSIG Annual Meeting. 2021. PSIG.
  31. Shabdirova, A., et al. A Novel Approach to Sand Volume Prediction Using Machine Learning Algorithms. in International Petroleum Technology Conference. 2023. IPTC.
  32. Chikwe, A.O., et al., A Response Surface Model for Predicting Sand Production Rate for Oil Wells in the Niger Delta. Petroleum & Coal, 2024. 66(1).
  33. Khamehchi, E., I.R. Kivi, and M. Akbari, A novel approach to sand production prediction using artificial intelligence. Journal of Petroleum Science and Engineering, 2014. 123: p. 147-154.
  34. Alakbari, F.S., et al., Prediction of critical total drawdown in sand production from gas wells: Machine learning approach. The Canadian Journal of Chemical Engineering, 2023. 101(5): p. 2493-2509.
  35. Ketmalee, T. and P. Bandyopadhyay. Application of neural network in formation failure model to predict sand production. in Offshore Technology Conference Asia. 2018. OTC.
  36. Laoufi, H., et al. Selection of sand control completion techniques using machine learning. in ARMA/DGS/SEG International Geomechanics Symposium. 2022. ARMA.
  37. Abdul Hamid, Z., et al. A Use Case of Production and Sand Control Benchmarking Through Unstructured Data and Machine Learning Analysis. in SPE Asia Pacific Oil and Gas Conference and Exhibition. 2023. SPE.
  38. Liu, S., A Grain Size Profile Prediction Method Based on Combined Model of Extreme Gradient Boosting and Artificial Neural Network and Its Application in Sand Control Design. SPE Journal, 2024: p. 1-15.
  39. Daud, M.S.H., S.M. Tabatabai, and F.K. Wong. Cascaded Machine Learning in NMR: Unveiling a Continuous Grain Size Distribution Approach for Tackling Sand Production Challenges. in SPWLA Annual Logging Symposium. 2024. SPWLA.

  • تاریخ دریافت 30 بهمن 1403
  • تاریخ بازنگری 30 اردیبهشت 1404
  • تاریخ پذیرش 17 خرداد 1404