«Oilfield engineering»

ELECTRIC SUBMERSIBLE PUMP OPERATION MODE OPTIMIZATION TO INCREASE THE RUN-TO-FAILURE TIME

UDC: 622.276.054.23:621.671:004.896
DOI: 10.33285/0207-2351-2021-8(632)-30-36

Authors:

¹ National University of Oil and Gas "Gubkin University", Moscow, Russian Federation

Keywords: Electric submersible pump (ESP), ESP failure prediction, ESP predictive analytics, ESP predictive maintenance, ESP operation mode optimization, ESP operation mode sensitivity analysis

Annotation:

Electric submersible pump (ESP) are widely used for oil production in Russia and worldwide. ESP failure requires costly repairs and leads to well downtime, while the technical limit of ESP technology is higher than current mean time between failures (MTBF). This work uses machine learning methods to create the model of ESP systems failure prediction. Today the industry knows that such models are necessary for solving logistical management tasks of routine maintenance team movement and stocking required number of ESP equipment for future repairs, which will minimize well downtime and, thus, maximize production. This paper describes a new approach to the application of the ESP failure prediction model created by machine learning methods to select the optimal ESP unit operation mode. Calculation results analysis shows that the approach studied in this work can be used for targeted ESP operation modes optimization in order to increase their MTBF.

Bibliography:

1. Abdelaziz M., Lastra R., Xiao J. ESP Data Analytics: Predicting Failures for Improved Production Performance / SPE-188513-MS International Petroleum Exhibition & Conference, Abu Dhabi, 2017.
2. ESP Well and Component Failure Prediction in Advance using Engineered Analytics - A Breakthrough in Minimizing Unscheduled Subsurface Deferments / Andrade Marin [et al.] // SPE-197806-MS International Petroleum Exhibition & Conference, Abu Dhabi, 2019.
3. ESP Well Surveillance using Pattern Recognition Analysis, Oil Wells, Petroleum Development Oman / A. Awaid [et al.] // IPTC-17413-MS International Petroleum Technology Conference, Doha, Qatar, January 2014.
4. Real-Time Monitoring and Predictive Failure Identification for Electrical Submersible Pumps / A.S. Bhardwaj, R. Saraf, G.G. Nair, S. Vallabhaneni // SPE-197911-MS International Petroleum Exhibition & Conference, Abu Dhabi, 2019.
5. Data Driven Approach to Failure Prediction for Electrical Submersible Pump Systems / Guo D. [et al.] // SPE-174062 SPE Western Regional Meeting held in Garden Grove, California, USA, 27-30 April 2015.
6. Gupta S., Saputelli L., Nikolaou M. Applying Big Data Analytics to Detect, Diagnose, and Prevent Impending Failures in Electric Submersible Pumps // SPE-181510-MS SPE Annual Technical Conference and Exhibition, Dubai, UAE, September 2016.
7. Предиктивная аналитика отказов УЭЦН на большом фонде скважин Западной Сибири с использованием методов машинного обучения / Р.А. Хабибуллин, А.Р. Шабонас, Н.С. Губаров, А.В. Тимонов // SPE-201881 SPE Russian Petroleum Technology Conference, Virtual, October 2020.
8. Electric submersible pump broken shaft fault diagnosis based on principal component analysis / Long Peng, Guoqing Han, Arnold Landjobo Pagou, Jin Shu // J. of Petroleum Science and Engineering. - 2020. - Vol. 191.
9. Слепченко С.Д. Оценка надежности УЭЦН и их отдельных узлов по результатам промысловой эксплуатации: дис. … канд. техн. наук. - М.: РГУ нефти и газа имени И.М. Губкина, 2011.
10. Sneed Jessamyn. Predicting ESP Lifespan With Machine Learning // URTEC-2017-2669988 SPE Unconventional Resources Technology Conference, Austin, Texas, USA, July 2017.