To date computer technologies are being actively introduced into the industry. One of the urgent issues at the moment is a proactive approach to the prevention of equipment failures. The purpose of this paper is a review of existing approaches to diagnostics and failures prediction of electric submersible pumps (ESP) units. A literature review was conducted in the domain of diagnostics and forecasting of ESP malfunctions. There are 4 main approaches observed: deterministic, expert-based, data-based, and hybrid. A deterministic approach uses functional or analytical dependencies, an expert approach is based on the available knowledge base, which is used in the form of patterns interpreted by specialists, a data-based approach identifies existing patterns based on the historical archive of data, and hybrid approach may include various options for combining main approaches. For each group examples, features and results are provided where possible. Applicability and limitations of each category are given. As a result of literature analysis, the advantages and disadvantages of existing approaches are established. Main advantages of deterministic approaches are interpretability and non-dependence on historical data. Expert rules are mainly used in the diagnosis of the current state without forecasting, unlike fuzzy logic approaches. The effectiveness of this approach depends on the quality of the applied rules and data. The main advantage of the data-based approach is the absence of detailed physical modeling of systems or processes. The main disadvantage is the dependence on the volume and quality of historical data. A promising direction is combined approaches that include several models, thereby adopting the advantages of each one of them.
References
1. Abdelaziz M., Lastra R., Xiao J.J., ESP Data Analytics: Predicting failures for improved production performance, SPE-188513-MS, 2017, DOI: https://doi.org/10.2118/188513-MS
2. Carvalho T.P., Soares F.A.A.M.N., Vita R. et al., A systematic literature review of machine learning methods applied to predictive maintenance, Computers & Industrial Engineering, 2019, V. 131, Article No. 106024, DOI: https://doi.org/10.1016/j.cie.2019.106024
3. Bruijnen P.M., Nodal analysis by use of ESP intake and discharge pressure gauges, SPE-178433-PA, 2016, DOI: https://doi.org/10.2118/178433-PA
4. Iranzi J., Son H., Lee Y., Wang J.A., Nodal analysis based monitoring of an electric submersible pump operation in multiphase flow, Applied Sciences, 2022, V. 12(6), Article No. 2825, DOI: https://doi.org/10.3390/app12062825
5. Grassian D., Bahatem M., Scott T., Olsen D., Application of a fuzzy expert system to analyze and anticipate ESP failure modes, SPE-188305-MS, 2017, DOI: https://doi.org/10.2118/188305-MS
6. Awaid A., Al-Muqbali H., Al-Bimani A. et al., ESP well surveillance using pattern recognition analysis, oil wells, petroleum development Oman, IPTC-17413-MS, 2014, DOI: https://doi.org/10.2523/IPTC-17413-MS
7. Li L., Hua C., Xu X., Condition monitoring and fault diagnosis of electric submersible pump based on wellhead electrical parameters and production parameters, Systems Science & Control Engineering, 2018, V. 6, no. 3, pp. 253–261, DOI: https://doi.org/10.1080/21642583.2018.1548983
8. Bermudez F., Carvajal G.A., Moricca G. et al., Fuzzy logic application to monitor and predict unexpected behavior in electric submersible pumps (Part of KwIDF Project), SPE-167820-MS, 2014, DOI: https://doi.org/10.2118/167820-MS
9. Stone P., Introducing predictive analytics: Opportunities, SPE-106865-MS, 2007, DOI: https://doi.org/10.2118/106865-MS
10. R.A. Khabibullin, A.R. Shabonas, N.S. Gurbatov, Timonov A.V., Prediction of ESPs failure using ML at Western Siberia oilfields with large number of wells, SPE-201881-MS, 2020, DOI: https://doi.org/10.2118/201881-MS
11. Solomatine D., See L.M., Abrahart R.J., Data-driven modelling: Concepts, approaches and experiences, In: Water Science and Technology Library, V. 68, Berlin: Springer, 2008, DOI: https://doi.org/10.1007/978-3-540-79881-1_2
12. Abdalla R., Samara H., Perozo N. et al., Machine learning approach for predictive maintenance of the electrical submersible pumps (ESPs), ACS omega, 2022, V. 7(21), pp. 17641–17651, DOI: https://doi.org/10.1021/acsomega.1c05881
13. Sherif S., Adenike O., Obehi E. et al., Predictive data analytics for effective electric submersible pump management, SPE-198759-MS, 2019, DOI: https://doi.org/10.2118/198759-MS
14. Pilipenko O.G., Povyshenie vremeni prokata ustanovok elektrotsentrobezhnykh nasosov metodami mashinnogo obucheniya (Improving the production of electric centrifugal pump by machine learning methods), Collected papers “Nauchnyy forum: tekhnicheskie i fiziko-matematicheskie nauki” (Scientific forum: technical and physical and mathematical sciences), Proceedings of XXV international scientific and practical conference, Moscow: Publ. of OOO “Mezhdunarodnyy tsentr nauki i obrazovaniya”, 2019, V. 6(25), pp. 14-18.
15. Marin A.A., Busaidy S., Murad M. et al., ESP well and component failure prediction in advance using engineered analytics – A breakthrough in minimizing unscheduled subsurface deferments, SPE-197806-MS, 2019, DOI: https://doi.org/10.2118/197806-MS
16. Peng L., Han G., Sui X. et al., Predictive approach to perform fault detection in electrical submersible pump systems, ACS Omega, 2021, V. 6(12), pp. 8104–8111, DOI: https://doi.org/10.1021/acsomega.0c05808
17. Peng L., Han G., Landjobo P.A., Shu J., Electric submersible pump broken shaft fault diagnosis based on principal component analysis, Journal of Petroleum Science and Engineering, 2020, V. 191, Article No. 107154, DOI: https://doi.org/10.1016/j.petrol.2020.107154
18. Peng L., Han G., Pagou A.L., A predictive model to detect the impending electric submersible pump trips and failures, SPE-206150-MS, 2021, DOI: https://doi.org/10.2118/206150-MS
19. Gupta S., Saputelli L., Nikolaou M., Applying big data analytics to detect, diagnose, and prevent impending failures in electric submersible pumps, SPE-181510-MS, 2016, DOI: https://doi.org/10.2118/181510-MS
20. Bhardwaj A.S., Saraf R., Nair G.G., Vallabhaneni S., Real-time monitoring and predictive failure identification for electrical submersible pumps, SPE-197911-MS, 2019, DOI: https://doi.org/10.2118/197911-MS
21. Gupta S., Nikolaou M., Saputelli L., Bravo C., ESP health monitoring KPI: A real-time predictive analytics application, SPE-181009-MS, 2016, DOI: https://doi.org/10.2118/181009-MS
22. Al-Hajri N.M., Al-Ghamdi A., Tariq Z., Mahmoud M., Scale-prediction/inhibition design using machine-learning techniques and probabilistic approach, SPE-198646-PA, 2020, DOI: https://doi.org/10.2118/198646-PA
23. Adesanwo M., Bello O., Olorode O. et al., Advanced analytics for data-driven decision making in electrical submersible pump operations management, SPE-189119-MS, 2017, DOI: https://doi.org/10.2118/189119-MS
24. Antonic M., Solesa M., Thonhauser G. et al., Implementing the autonomous adaptive algorithm to manage ESP operation in harsh reservoir conditions, IOP Conference Series: Materials Science and Engineering, 2021, V. 1201(1), Article No. 012083, DOI: https://doi.org/10.1088/1757-899x/1201/1/012083
25. Turpin J.L., Lea J.F., Bearden J.L., Gas-liquid flow through centrifugal pumps – correlation of data, Proceedings of the 3rd International Pump Symposium, Texas A&M University, 1986, pp. 13-20, URL: https://www.911metallurgist.com/blog/wp-content/uploads/2016/01/Gas-Liquid-Flow-Through-Centrifugal-Pumps-Correlation-of-Data.pdf
