«Automation and Informatization of the fuel and energy complex»

Analysis of methods for predicting the reliability of electrical submersible centrifugal pumping units in the oil and gas industry

UDC: 622.276.054.23-004.83
DOI: -

Authors:

¹ Patrice Lumumba Peoples' Friendship University of Russia, Moscow, Russia

Keywords: reliability, electrical submersible centrifugal pumps, residual life of equipment, forecasting, mathematical methods, machine learning

Annotation:

The subject of the article is a review of methods for predicting the reliability and residual life of electric submersible centrifugal pumps (ESP). Mathematical methods used to solve this problem are considered. The laws of a random value distribution, which most accurately characterize the dependence of reliability on operating time for equipment elements and the unit as a whole, are described. Normative documents used for estimation of dynamic equipment reliability parameters are given. The software products used for these purposes are briefly indicated. The authors of the article, when revising technical literature that describes methods of ESP failure prediction, revealed that machine learning (ML) methods are universally used, capable of determining the residual operational lifetime like a classification for time periods or numerical values. The advantages and disadvantages of the considered techniques as well as accuracy obtained in practice are indicated. The conclusion about the relevance of the topic and the most effective methods is given as well as assumptions about possible improvements in solving the problem of ESP residual life prediction.

Bibliography:

1. Dunham C. 27th ESP Workshop: Summary of Presentations. Oilfield Automation Consulting. – 2013. – P. 1. – URL: https://www.spegcs.org/media/files/files/cebfcc3a/2013-ESP-Workshop-Summary-of-Presentations.pdf
2. ESP Data Analytics: Use of Deep Autoencoders for Intelligent Surveillance of Electric Submersible Pumps / O.A. Alamu, D.A. Pandya, O. Warner, I. Debacker // Offshore Technology Conf., Houston, Texas, USA, May 4–7, 2020. – DOI: 10.4043/30468-MS
3. Shchurin K.V. Nadezhnost' mashin. – SPb.: Lan', 2019. – 592 s.
4. Zubarev Yu.M. Osnovy nadezhnosti mashin i slozhnykh sistem. – SPb.: Lan', 2020. – 180 s.
5. GOST R ISO 13381-1-2016. Kontrol' sostoyaniya i diagnostika mashin. Prognozirovanie tekhnicheskogo sostoyaniya. Ch. 1. Obshchee rukovodstvo. – Vved. 2017–12–01. – M.: Standartinform, 2017. – IV, 20 s.
6. ISO 14224:2016. Petroleum, petrochemical and natural gas industries – Collection and exchange of reliability and maintenance data for equipment. – Third edition 2016-09-15; Corrected version 2016-10-01. – VI, 272 p.
7. Mustafina S.I., Zhilyakov S.A. Primenenie neyronnykh setey dlya diagnostiki i prognozirovaniya tekhnicheskogo sostoyaniya oborudovaniya // Avtomatizatsiya i informatizatsiya TEK. – 2023. – № 7(600). – S. 13–21. – DOI: 10.33285/2782-604X-2023-7(600)-13-21
8. Semi-supervised Failure Prediction for Oil Production Wells / Yintao Liu, Ke-Thia Yao, Shuping Liu [et al.] // 2011 IEEE 11th Int. Conf. on Data MiningWorkshops, Vancouver, BC, Canada, Dec. 11, 2011. – P. 434–441. – DOI: 10.1109/ICDMW.2011.151
9. Data Driven Approach to Failure Prediction for Electric Submersible Pump Systems / Dong Guo, C.S. Raghavendra, Ke-Thia Yao [et al.] // Western Regional Meeting, Garden Grove, California, USA, April 27–30, 2015. – DOI: 10.2118/174062-MS
10. ESP Health Monitoring KPI: A Real-Time Predictive Analytics Application / S. Gupta, M. Nikolaou, L. Saputelli, C. Bravo // SPE Intelligent Energy Int. Conf. and Exhibition, Aberdeen, Scotland, UK, Sept. 6–8, 2016. – DOI: 10.2118/181009-MS
11. Abdelaziz M., Lastra R., Xiao Jinjiang. ESP Data Analytics: Predicting Failures for Improved Production Performance // Abu Dhabi Int. Petroleum Exhibition & Conf., Abu Dhabi, UAE, Nov. 13–16, 2017. – DOI: 10.2118/188513-MS
12. Real-Time Monitoring and Predictive Failure Identification for Electrical Submersible Pumps / A.S. Bhardwaj, R. Saraf, G.G. Nair, S. Vallabhaneni // Abu Dhabi Int. Petroleum Exhibition & Conf., Abu Dhabi, UAE, Nov. 11–14, 2019. – DOI: 10.2118/197911-MS
13. ESP Well and Component Failure Prediction in Advance using Engineered Analytics – A Breakthrough in Minimizing Unscheduled Subsurface Deferments / A.A. Marin, S. Busaidy, M. Murad [et al.] // Abu Dhabi Int. Petroleum Exhibition & Conf., Abu Dhabi, UAE, Nov. 11–14, 2019. – DOI: 10.2118/197806-MS
14. Prediction of ESPs Failure Using ML at Western Siberia Oilfields with Large Number of Wells / R.A. Khabibullin, A.R. Shabonas, N.S. Gurbatov, A.V. Timonov // SPE Russian Petroleum Technology Conf., Oct. 26–29, 2020, Virtual. – DOI: 10.2118/201881-MS
15. Bailey W.J., Weir I.S., Couët B. How Data from Reuse of Electrical-Submersible-Pump Components Can Help in Predicting System Failure // SPE Production & Operation. – 2018. – Vol. 33, Issue 01. – P. 60–67. – DOI: 10.2118/171368-PA
16. Noui-Mehidi M.N., Bukhamseen A.Y. Advanced Signal Analysis of an Electrical-Submersible-Pump Failure Owing to Scaling // SPE Production & Operations. – 2019. – Vol. 34, Issue 02. – P. 394–399. – DOI: 10.2118/164320-PA
17. Lastra R.A., Jinjiang Xiao. Machine Learning Engine for Real-Time ESP Failure Detection and Diagnostics // SPE Middle East Artificial Lift Conf. and Exhibition, Manama, Bahrain, Oct. 25–26, 2022. – DOI: 10.2118/206935-MS
18. Dussi S., Octaviano R., Omrani P.Sh. Bayesian Networks Applied to ESP Performance Monitoring and Forecasting // SPE Annual Technical Conf. and Exhibition, Houston, Texas, USA, Oct. 3–5, 2022. – DOI: 10.2118/210495-MS
19. Silvia Sh., Prior M., Gilad Y. Case Study: Predicting Electrical Submersible Pump Failures Using Artificial Intelligence // Offshore Technology Conf., Houston, Texas, USA, May 2–5, 2022. – DOI: 10.4043/31852-MS