«Automation and Informatization of the fuel and energy complex»

Determination of the maximum allowable weight on bit for accident-free drilling

UDC: 681.5:622.24
DOI: 10.33285/2782-604X-2022-10(591)-52-59

Authors:

¹ National University of Oil and Gas "Gubkin University", Moscow, Russia
² Gazprom EP International B.V, St. Petersburg, Russia

Keywords: accident-free drilling, rate of penetration, technical limit, drilling regime, optimization

Annotation:

The article presents a methodology for calculation of the allowable weight on bit upper during drilling. The developed model is based on the application of machine learning techniques coupled with numerical optimization algorithms of mathematical functions. Testing is fulfilled on drilling rig sensor data received from the Sillimanite field in the North Sea by means of visual comparison of modeled dependences with the actual ones as well as computation of the corresponding statistical indicators. Results of the research have confirmed high applicability of the described approach.

Bibliography:

1. Marshall D.W. The Technical Limit – Illusion and Reality // SPE/IADC Drilling Conf., Amsterdam, Netherlands, Feb. 27 – March 1. – 2001. – DOI: 10.2118/67819-MS
2. Xuyue Chen, Jin Yang, Deli Gao. Drilling Performance Optimization Based on Mechanical Specific Energy Technologies // Drilling. – London, 2018. – P. 133–161. – DOI: 10.5772/intechopen.75827
3. Akgun F. Drilling Variables At Technical Limit Of Drilling Rate // Canadian Int. Petroleum Conf., Calgary, Alberta, June 11–13. – 2002. – DOI: 10.2118/2002-051
4. Monitoring and Mitigating Downhole Vibration with MSE in Xinjiang Oil Filed of China / Fei Zhao, Haige Wang, Meng Cui [et al.] // 51st U.S. Rock Mechanics/Geomechanics Symposium, San Francisco, California, June 25–28. – 2017. – Paper No. ARMA-2017-0694. – P. 2555–2559.
5. WellPlan Software / Halliburton. – URL: https://www.landmark.solutions/WellPlan-Well-Engineering-Software
6. Ofitsial'nyy sayt Bursoftproekt. – URL: http://www.burproject.ru/
7. Dzhafarov R.F., Dadashev M.N. Kombinirovanie algoritmov mashinnogo obucheniya i metoda Monte-Karlo pri planirovanii srokov stroitel'stva skvazhin // Vestn. Assotsiatsii burovykh podryadchikov. – 2021. – № 4. – S. 17–22.
8. Dadashev M.N., Dzhafarov R.F., Kuropatkin G.Yu. Perspektivy vnedreniya elementov mashinnogo obucheniya dlya uvelicheniya mekhanicheskoy skorosti prokhodki // Oboronnyy kompleks – nauchno-tekhnicheskomu progressu Rossii. – 2021. – № 3(151). – S. 21–25. – DOI: 10.52190/1729-6552_2021_3_21
9. Elistratova E., Gubko P. Random Forest // Uchebnik po ML ot ShAD. – URL: https://ml-handbook.ru/chapters/ensembles/intro#random-forest
10. Bourgoyne Jr A.T., Young Jr F.S. A Multiple Regression Approach to Optimal Drilling and Abnormal Pressure Detection // SPE J. – 1974. – Vol. 14, Issue 04. – P. 371–384. – DOI: 10.2118/4238-PA
11. R2 score, the coefficient of determination // Scikit-learn. Machine Learning in Python. – URL: https://scikit-learn.org/stable/modules/model_evaluation.html#r2-score
12. Mean absolute error // Scikit-learn. Machine Learning in Python. – URL: https://scikit-learn.org/stable/modules/model_evaluation.html#mean-absolute-error
13. Mean absolute percentage error // Scikit-learn. Machine Learning in Python. – URL: https://scikit-learn.org/stable/modules/model_evaluation.html#mean-absolute-percentage-error
14. Savitzky A., Golay M.J.E. Smoothing and Differentiation of Data by Simplified Least Squares Procedures // Analytical Chemistry. – 1964. – Vol. 36, No. 8. – P. 1627–1639. – DOI: 10.1021/ac60214a047