Intelligent automation and neural networks for enhanced energy efficiency in ESPs systems: Optimizing chemical injection in Nantu 31
DOI:
https://doi.org/10.18686/cest823Keywords:
energy; oil; variability; artificial neural networks; chemical dosageAbstract
Discontinuities in chemical injection and dosing in conventional artificial oil lift systems generate technical problems and significant energy losses, which can be mitigated through intelligent automation. This project began with the design and development of the first automated chemical injection and dosing system with closed-loop control that integrates an Artificial Neural Network with Backpropagation implemented in a Siemens S7-1200 PLC, remotely supervised via satellite SCADA through Baker Hughes’ Production Link Expert platform, using a producing well and the transient current signals of variable frequency drives as indirect sensors of fluid rheology. A predictive model was then trained using historical data from the Nantu 31 well, owned by Andes Petroleum Ecuador Ltd. and operated by Baker Hughes, to dynamically adjust dosing based on operational variables. The validation process was conducted through both simulation and 30 days of field testing, entailing a comparative analysis between the automated system and the manual method to ascertain advancements in efficiency, accuracy, and stability. The findings suggest that the Intelligent Chemical Injection and Dosing System may mitigate human error from 40% to 8% through the application of Artificial Neural Networks with a Backpropagation (BP) algorithm. Production demonstrated an increase from 755 barrels of oil per day (BOPD) to 765.8 BOPD. Furthermore, a cost reduction of USD 21,900 per annum was observed in multifunctional chemical additives, concomitant with a notable diminution in energy consumption from 6.47 kWh/BOPD to 6.20 kWh/BOPD.
References
1. Rebello CM, Costa EA, Fontana M, et al. Interpretable Scientific Machine Learning Approach for Correcting Phenomenological Models: Methodology Validation on an ESP Prototype. Industrial & Engineering Chemistry Research. 2024; 63(44): 19030–19050. doi: 10.1021/acs.iecr.4c02104
2. Sui X, Lu X, Ji Y, et al. Intelligent Oil Production Management System Based on Artificial Intelligence Technology. Processes. 2025; 13(1): 133. doi: 10.3390/pr13010133
3. Terneus-Páez CF, Viteri-Salazar O. Energy Security in Ecuador: An Analysis Considering the Interrelationships of the WEF Nexus. Energies. 2023; 16(20): 7166. doi: 10.3390/en16207166
4. Gautam S, Guria C, Rajak VK. A state of the art review on the performance of high-pressure and high-temperature drilling fluids: Towards understanding the structure-property relationship of drilling fluid additives. Journal of Petroleum Science and Engineering. 2022; 213: 110318. doi: 10.1016/j.petrol.2022.110318
5. Tsirulnikova NV, Bolt YV, Dernovaya ES, et al. Creation and study of formulations as inhibitors of metal corrosion and scaling for stabilization water treatment in water utilization systems (a review). International Journal of Corrosion and Scale Inhibition. 2016; 5(1): 66–86. doi: 10.17675/2305-6894-2016-5-1-6
6. Sayani JKS, Lal B, Pedapati SR. Comprehensive Review on Various Gas Hydrate Modelling Techniques: Prospects and Challenges. Archives of Computational Methods in Engineering. 2022; 29(4): 2171–2207. doi: 10.1007/s11831-021-09651-1
7. Egbumokei PI, Dienagha IN, Digitemie WN, et al. The role of digital transformation in enhancing sustainability in oil and gas business operations. International Journal of Multidisciplinary Research and Growth Evaluation. 2024; 5(5): 1029–1041. doi: 10.54660/.IJMRGE.2024.5.5.1029-1041
8. Joseph A, Adeoti AO. Impact of Fluid Properties on Electric Submersible Pumps (ESP) Performance and Run Life in a Well. Journal of Applied Sciences and Environmental Management. 2021; 25(2): 139–143. doi: 10.4314/jasem.v25i2.1
9. Sabaa A, Abu El Ela M, El-Banbi AH, et al. Artificial Neural Network Model to Predict Production Rate of Electrical Submersible Pump Wells. SPE Production & Operations. 2023; 38(01): 63–72. doi: 10.2118/212284-PA
10. Agwu OE, Alkouh A, Alatefi S, et al. Utilization of machine learning for the estimation of production rates in wells operated by electrical submersible pumps. Journal of Petroleum Exploration and Production Technology. 2024; 14(5): 1205–1233. doi: 10.1007/s13202-024-01761-3
11. Wibawa RA, Rahmanto BA, Jha B, et al. Enhancing Energy Efficiency in Oilfield Operations: A Novel Approach Using Artificial Neural Network-Based Predictive Modeling for Electrical Submersible Pump Power Consumption. In: Proceedings of the SPE Western Regional Meeting; 27 April–1 May 2025; Garden Grove, CA, USA. doi: 10.2118/224135-MS
12. Liu T, Shi M. Research on Intelligent Energy-saving Algorithm of Oil Pumping Based on BP Neural Network. Journal of Physics: Conference Series. 2019; 1237(4): 042023. doi: 10.1088/1742-6596/1237/4/042023
13. Luo X, Wang SJ, Lv XR, et al. Speed Prediction of ESPCP System Based on Neural Network. Applied Mechanics and Materials. 2010; 44–47: 3569–3573. doi: 10.4028/www.scientific.net/AMM.44-47.3569
14. Jin B, Xu X. Late and early indica rice’s price forecasts through neural networks. International Journal of Big Data Mining for Global Warming. 2025; 07(02): 2550005. doi: 10.1142/S2630534825500056
15. Jin B, Xu X. Machine learning-driven forecasting of composite wholesale price indices for agricultural commodities in the Vegetable Basket Project. Quality & Quantity. 2026; 60(3): 10307–10357. doi: 10.1007/s11135-026-02650-z
16. Jin B, Xu X. Regional steel price index predictions for the southwest Chinese market through machine learning. Ironmaking & Steelmaking: Processes, Products and Applications. 2024; 03019233241297720. doi: 10.1177/03019233241297720
17. Jin B, Xu X. Inter-city housing price causality in Fujian: contemporaneous analysis via vector error-correction and directed acyclic graph models. Quality & Quantity. 2026. doi: 10.1007/s11135-026-02740-y
18. Xu X, Zhang Y. Individual time series and composite forecasting of the Chinese stock index. Machine Learning with Applications. 2021; 5: 100035. doi: 10.1016/j.mlwa.2021.100035
19. Zhang Y, Xu X. Disordered MgB2 superconductor critical temperature modeling through regression trees. Physica C: Superconductivity and its Applications. 2022; 597: 1354062. doi: 10.1016/j.physc.2022.1354062
20. Zhang Y, Xu X. Predictions of the Total Crack Length in Solidification Cracking Through LSBoost. Metallurgical and Materials Transactions A. 2021; 52(3): 985–1005. doi: 10.1007/s11661-020-06130-3
21. Wang T, Wei Q, Xiong W, et al. Current Status and Prospects of Artificial Intelligence Technology Application in Oil and Gas Field Development. ACS Omega. 2024; 9(3). doi: 10.1021/acsomega.3c09229
22. Esbai R, Khalifa M. Automating Continuous Demulsifier Injection (CDI) for Oil Well Treatment. KnE Engineering. 2018; 3(7): 150. doi: 10.18502/keg.v3i7.3079
23. Jia G, Gao Q, Pan G, et al. Test System Based on PLC Control for Intelligent Water Injection Tool. DEStech Transactions on Computer Science and Engineering. 2019; 30024. doi: 10.12783/dtcse/cscbd2019/30024
24. Liang X, Lu X, Han G, et al. Lifespan Prediction and Multiobjective Optimization of Electrical Submersible Pump Wells Using Machine Learning. SPE Journal. 2026; 31(03): 1802–1821. doi: 10.2118/221041-PA
25. Pan S, Ni X. Design of Automatic Drilling Fluid Configuration System Based on PLC. Academic Journal of Science and Technology. 2024; 13(2): 173–181. doi: 10.54097/g5a90m96
26. Shaik NB, Jongkittinarukorn K, Benjapolakul W, et al. A novel neural network-based framework to estimate oil and gas pipelines life with missing input parameters. Scientific Reports. 2024; 14(1): 4511. doi: 10.1038/s41598-024-54964-3
27. Yao C, Aher P, Villarreal A, et al. Closed-Loop ESP Optimization to Maximize Asset Value. In: Proceedings of the SPE Gulf Coast Section Electric Submersible Pumps Symposium; 25–29 August 2025; Galveston, TX, USA. doi: 10.2118/225261-MS
28. Saeed MA, El-Kenawy ESM, Ibrahim A, et al. Electrical power output prediction of combined cycle power plants using a recurrent neural network optimized by waterwheel plant algorithm. Frontiers in Energy Research. 2023; 11: 1234624. doi: 10.3389/fenrg.2023.1234624
29. Rahmanifard H, Gates I. A Comprehensive review of data-driven approaches for forecasting production from unconventional reservoirs: best practices and future directions. Artificial Intelligence Review. 2024; 57(8): 213. doi: 10.1007/s10462-024-10865-5
30. Alkhawaher A, Al Jishi H, Al-Aseef S. Advanced ESP Monitoring System for Performance and Production Optimization. In: Proceedings of the SPE Middle East Artificial Lift Conference and Exhibition; 29–30 October 2024; Manama, Bahrain. doi: 10.2118/221543-MS
31. Chen J, Farhadian A, Rizi ZT, et al. Kinetic inhibition of gas hydrates for efficient development of sour gas reservoirs. Results in Engineering. 2026; 29: 109088. doi: 10.1016/j.rineng.2026.109088
32. Iravani D, Farhadian A, Sharifi R, et al. Fabrication of novel Arabic gum-grafted-polyurethanes as eco-friendly corrosion inhibitors for carbon steel in sour environments: Surface analysis and inhibition mechanism. Corrosion Science. 2025; 246: 112712. doi: 10.1016/j.corsci.2025.112712
33. El Sherbeny WI, Denver L, Rameraize S, et al. An Artificial Intelligent Cutting-Edge Technology for Automated Field Production Optimization & ESP Failures Prediction. In: Proceedings of the SPE Middle East Artificial Lift Conference and Exhibition; 29–30 October 2024; Manama, Bahrain. doi: 10.2118/221571-MS
34. Ruiz YL, Carrera JM, Tagarot GN, et al. Transforming Legacy Production Operations into Smart Asset Operations in Ecuador. In: Proceedings of the ADIPEC; 31 October–3 November 2022; Abu Dhabi, UAE. doi: 10.2118/211844-MS
35. Mejía S, Nuñez G, Zamora P, et al. Revolutionizing Reservoir Management Chemical Tracer Technology Integrated with Advanced Monitoring and Data-Driven Strategies for Enhanced Production in Block 61. In: Proceedings of the OTC Brasil; 28–30 October 2025; Rio de Janeiro, Brazil. doi: 10.4043/36080-MS
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Manolo Córdova, Juan Córdova, Segundo Espín, Juan Paredes, Alex Mayorga
This work is licensed under a Creative Commons Attribution 4.0 International License.
.jpg)
.jpg)
