Factibilidad técnico-económica de implementación de un sensor virtual de producción en pozos de un campo del Valle Medio del Magdalena colombiano
Publicado 2023-12-12
Palabras clave
- Sensor virtual,
- Red neuronal artificial,
- Pozo de producción de crudo,
- Valle Medio del Magdalena,
- Librería Neuralnet
- CAPEX ...Más
Cómo citar
Derechos de autor 2023 Giovanni Vizcaya-Cedeño , Fernando Enrique Calvete González, Giovanni Morales Medina
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Resumen
En la consecución de las metas corporativas, los profesionales de producción requieren datos actualizados de los desempeños de los pozos petroleros, identificando aquellos que demandan mantenimientos correctivos. Sin embargo, los costos de implementación de sensores físicos restringen el acceso a la información en tiempo real. Alternativamente, los sensores virtuales (SV) se presentan como una opción de bajo costo, que pueden predecir datos de producción, con base en los procedimientos inmersos en una red neuronal artificial (RNA). El presente documento desarrolla un análisis de viabilidad técnicoeconómico de la implementación de un SV de producción en pozos con sistema de levantamiento por Cavidades Progresivas (PCP) de un campo del Valle Medio del Magdalena colombiano (VMM). Para esto, datos históricos con 15 variables fueron utilizados en el entrenamiento y la validación de diferentes arquitecturas de RNA, por medio de los códigos de la librería Neuralnet del programa de uso libre R. Posteriormente, el documento desarrolla una evaluación del impacto económico que tendría la implementación del SV de flujo en pozos del campo del VMM. Según los resultados, la RNA con capa interna de 23 neuronas y función de activación logística sigmoidal reportó los mejores desempeños de predicción, con errores de predicción de ± 9,6 al 95 % de confianza. Por otra parte, la aplicación de un SV basado en la RNA para los pozos con PCP para el campo del VMM, conllevaría a un beneficio económico favorable, con un valor presente neto de $ 25,6 MMusd, para un flujo de caja de 10 años.
Descargas
Referencias
- Doğan B, Erol D. The Future of Fossil and Alternative Fuels Used in Automotive Industry. En: 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT); 2019 October 11-13; Ankara, Turkey; IEEE; 2019. doi.org/10.1109/ISMSIT.2019.8932925
- Kreps BH. The Rising Costs of Fossil-Fuel Extraction: An Energy Crisis That Will Not Go Away. Am. J. Econ. Sociol. 2020;79(3):695–717. doi.org/10.1111/ajes.12336
- Kremieniewski M. Improving the Efficiency of Oil Recovery in Research and Development. Energies. 2022;15(2):4488. doi.org/10.3390/en15124488
- Soares FDV, Secchi AR, de Souza MBJr. Development of a nonlinear model predictive control for stabilization of a gas-lift oil well. Ind. Eng. Chem. Res. 2022;61(24):8411–8421. doi.org/10.1021/acs. iecr.1c04728
- García A, Almeida I, Singh G, Purwar S, Monteiro M, Carbone L, et al. An Implementation of On-line Well Virtual Metering of Oil Production. En: SPE Intelligent Energy Conference and Exhibition; 2010 March 23-25; Utrecht, The Netherlands; OnePetro; 2010. doi.org/10.2118/127520-ms
- Amin A. Evaluation of Commercially Available Virtual Flow Meters (VFMs). En: Offshore Technology Conference; 2015 May 4-7; Houston, Texas; OnePetro; 2015. doi.org/10.4043/25764-ms
- Bravo CE, Saputelli L, Rivas F, Pérez AG, Nickolaou M, Zangl G, et al. State of the Art of Artificial Intelligence and Predictive Analytics in the E&P Industry: A Technology Survey. SPE J. 2014;19(04):547–563. doi.org/10.2118/150314-pa
- Varyan R, Haug RK, Fonnes DG. Investigation on the Suitability of Virtual Flow Metering System as an Alternative to the Conventional Physical Flow Meter. En: SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition; 2015 October 20-22; Nusa Dua, Bali, Indonesia; OnePetro; 2015. doi.org/10.2118/176432-ms
- Varyan R. Cost Saving of Implementing Virtual Flow Metering at Various Fields and Engineering Phases - A Case Study. En: Offshore Technology Conference Asia; 2016 March 22-25; Kuala Lumpur, Malaysia; OnePetro; 2016. doi.org/10.4043/26637-ms
- Bikmukhametov T, Jäschke J. First principles and machine learning Virtual Flow Metering: A literature review. J. Pet. Sci. Eng. 2020;184:106487. doi.org/10.1016/j.petrol.2019.106487
- Hansen LS, Pedersen S, Durdevic P. MultiPhase Flow Metering in Offshore Oil and Gas Transportation Pipelines: Trends and Perspectives. Sensors. 2019;19(9):2184. doi.org/10.3390/s19092184
- Ursini F, Rossi R, Castelnuovo L, Perrone A, Bendari A, Pollero M. The Benefits of Virtual Meter Applications on Production Monitoring and Reservoir Management. En: SPE Reservoir Characterisation and Simulation Conference and Exhibition; 2019 September 17-19; Abu Dhabi, UAE; OnePetro; 2019. doi.org/10.2118/196654-ms
- George A. Predicting Oil Production Flow Rate Using Artificial Neural Networks - The Volve Field Case. En: SPE Nigeria Annual International Conference and Exhibition; 2021 August 2-4; Lagos, Nigeria; OnePetro; 2021. doi.org/10.2118/208258-MS
- Bello O, Ade-Jacob S, Yuan K. Development of Hybrid Intelligent System for Virtual Flow Metering in Production Wells. En: SPE Intelligent Energy Conference & Exhibition; 2014 April 1-3; Utrecht, The Netherlands; OnePetro; 2014. doi.org/10.2118/167880-MS
- Cai S, Toral H, Sinta D, Tajak M. Experience in field tuning and operation of a multiphase meter based on neural net characterization of flow conditions FLOMEKO. En: Proc. 12th Int. Conf. on Flow Measurement; 2004 September 14-17; Guilin, China; 2004.
- Mirzaei-Paiaman A, Salavati S. The Application of Artificial Neural Networks for the Prediction of Oil Production Flow Rate. Energ. Source Part A. 2010;34(19):1834-1843. doi.org/10.1080/15567036.2010.492386
- Al-Jasmi AK, Goel HK, Nasr H, Querales M, Rebeschini J, Villamizar MA, et al. ShortTerm Production Prediction in Real Time Using Intelligent Techniques. En: EAGE Annual Conference & Exhibition Incorporating SPE Europ; 2013 June 10-13; London, UK; OnePetro; 2013. doi.org/10.2118/164813-ms
- Ahmadi MA, Ebadi M, Shokrollahi A, Majidi SMJ. Evolving artificial neural network and imperialist competitive algorithm for prediction oil flow rate of the reservoir. Appl. Soft Comput. 2013;13(2):1085-1098. doi.org/10.1016/j.asoc. 2012.10.009
- Liu G, Wang L, Qu H, Shen H, Zhang X, Zhang S, et al. Artificial neural network approaches on composition–property relationships of jet fuels based on GC–MS. Fuel. 2007;86(16):2551-2559. doi.org/10.1016/j.fuel.2007.02.023
- Berry MJA, Linoff G. Data mining techniques. Nueva York: John Wiley & Sons; 1987.
- Swingler K. Applying Neural Networks, A Practical Guide. London: Press Limited Oval Road; 1996.
- Zhang Z. Neural Networks: further insights into error function, generalized weights and others. Ann Transl Med. 2016;4(16):300. doi.org/10.21037/atm.2016.05.37
- Thorn R, Johansen GA, Hjertarek BT. Threephase flow measurement in the petroleum industry. Meas. Sci. Technol. 2013;24:012003. doi.org/10.1088/0957-0233/24/1/012003
- Carvajal G, Maucec M, Cullick S. Intelligent digital oil and gas fields. Concepts, collaboration, and Right-Time Decisions. USA: Gulf Professional Publishing, Elsevier; 2018.
- Kluth ELE, Varnham MP, Clowes JR, Kutlik RL, Crawley CM, Heming RF. Advanced Sensor Infrastructure for Real Time Reservoir Monitoring. En: SPE European Petroleum Conference; 2000 October 24-25; Paris, France; OnePetro; 2000. doi.org/10.2118/65152-MS
- Kemp CE, Ravikumar AP, Brandt AR. Comparing Natural Gas Leakage Detection Technologies Using an Open-Source “Virtual Gas Field” Simulator. Environ. Sci. Technol. 2016;50(8):4546−4553. doi.org/10.1021/acs.est.5b06068
- Khan MY. Theory & Problems in Financial Management. Boston: McGraw Hill Higher Education; 1999.
- Carmalt SW. The Economics of Oil. A primer Including Geology, Energy, Economics, Politics. Switzerland: Springer; 2017.
- Brealey R, Myers S. Principles of Corporate Finance. New York: McGraw-Hill; 2000.
- Isasi P, Galvan I. Redes neuronales artificiales: enfoque práctico. Madrid: Pearson; 2004.
- Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning. New York: Springer Inc; 2009.
- Sadri M, Shariatipour S, Hunt A, Ahmadinia M. Effect of systematic and random flow measurement errors on history matching: a case study on oil and wet gas reservoirs. J Petrol Explor Prod Technol 2019;9:2853–2862. doi.org/10.1007/s13202-019-0665-2
- Falcone G, Hewitt GF, Alimonti C, Harrison B. Multiphase Flow Metering: Current Trends and Future Developments. J. Pet. Technol. 2002;54(04):77–84. doi.org/10.2118/74689-jpt
- Andrade GMP, de Menezes DQF, Soares RM, Lemos TSM, Teixeira AF, Ribeiro LD, et al. Virtual flow metering of production flow rates of individual wells in oil and gas platforms through data reconciliation, J. Pet. Sci. Eng. 2022;208(Part E):109772. doi.org/10.1016/j.petrol.2021.109772
- Gevrey M, Dimopoulus I, Lek S. Review and comparison of methods to study to contribution of variables in artificial neural network models. Ecol. Modell. 2003;160(3):349-264. doi.org/10.1016/S0304-3800(02)00257-0
- Luíza da Costa N, Dias de Lima M, Barbosa R. Evaluation of feature selection methods based on artificial neural network weights. Expert Syst. Appl. 2021;168:114312. doi.org/10.1016/j.eswa.2020.114312
- Zuluaga-Álvarez W.J. Evaluación económica de la actualización del sistema de monitoreo remoto en los pozos con inyección de agua, bloques I y II, del campo Casabe (Tesis de maestría). Bucaramanga, Colombia: Universidad Industrial de Santander; 2020.