Revista UIS Ingenierías

Vol. 23 Núm. 3 (2024): Revista UIS Ingenierías
Artículos

Predicción de la fracción volumétrica del flujo bifásico líquido-líquido en tuberías horizontales mediante redes de memoria a largo plazo

PDF (English)
  • Cristian A. Hernández-Salazar ,
  • Alejandro Carreño-Verdugo ,
  • Octavio Andrés González-Estrada
Cristian A. Hernández-Salazar
Universidad Industrial de Santander
Alejandro Carreño-Verdugo
Universidad Industrial de Santander
Octavio Andrés González-Estrada
Universidad Industrial de Santander
DOI: https://doi.org/10.18273/revuin.v23n3-2024002

Publicado 2024-08-15

Palabras clave

  • redes neuronales artificiales,
  • LSTM,
  • aprendizaje de m´áquina,
  • flujo bifásico,
  • fracción de volumen

Cómo citar

Hernández-Salazar , C. A. ., Carreño-Verdugo , A. ., & González-Estrada, O. A. (2024). Predicción de la fracción volumétrica del flujo bifásico líquido-líquido en tuberías horizontales mediante redes de memoria a largo plazo. Revista UIS Ingenierías, 23(3), 19–32. https://doi.org/10.18273/revuin.v23n3-2024002

Derechos de autor 2024 Revista UIS Ingenierías

Creative Commons License

Esta obra está bajo una licencia internacional Creative Commons Atribución-SinDerivadas 4.0.

Resumen

Este artículo presenta el desarrollo de una red neuronal de memoria a corto plazo diseñada para predecir la fracción volumétrica de flujos bifásicos líquido-líquido que circulan por tuberías horizontales. Para ello, se compiló una base de datos exhaustiva con información procedente de investigaciones existentes, que comprende 2156 puntos de datos experimentales utilizados para la construcción del modelo. La entrada del algoritmo consiste en un vector que contiene las velocidades superficiales de las sustancias (aceite y agua), la velocidad de la mezcla, el diámetro interno de la tubería y la viscosidad del aceite, mientras que la salida es la fracción volumétrica de aceite. Los procedimientos de entrenamiento y validación consistieron en preparar y segmentar los datos, utilizando el 80% de la información total para el entrenamiento y el 20% restante para la validación. La selección del modelo, basada en la evaluación del rendimiento, se llevó a cabo mediante 216 experimentos. El modelo predictivo con mejor rendimiento tuvo un Error Cuadrático Medio (ECM) de 3,5651E-05, un Error Medio Absoluto (EMA) de 0,0045 y un Error Medio Porcentual Absoluto (EPAA) de 3,0250%. Este rendimiento se obtuvo estructurando el modelo con una función de transferencia ReLu, 20 épocas, una tasa de aprendizaje de 0,1, una función de transferencia sigmoide, un tamaño de lote de 1, un optimizador ADAM y 150 neuronas en la capa oculta.

PDF (English)

Descargas

Los datos de descargas todavía no están disponibles.

Referencias

  1. T. Bikmukhametov, J. Jäschke, “First Principles and Machine Learning Virtual Flow Metering: A Literature Review,” Journal of Petroleum Science and Engineering, vol. 184, 2020, doi: https://doi.org/10.1016/j.petrol.2019.106487
  2. Y. Taitel, A. E. Dukler, “A model for predicting flow regime transitions in horizontal and near horizontal gas-liquid flow,” AIChE J., vol. 22, no. 1, pp. 47–55, 1976, doi: https://doi.org/10.1002/aic.690220105
  3. D. Barnea, O. Shoham, Y. Taitel, “Flow pattern transition for downward inclined two phase flow; horizontal to vertical,” Chem. Eng. Sci., vol. 37, no. 5, pp. 735–740, 1982, doi: https://doi.org/10.1016/0009-2509(82)85033-1
  4. G. A. Valle Tamayo, F. Romero Consuegra, M. E. Cabarcas Simancas, “Predicción de flujo multifásico en sistemas de recolección de crudo: descripción de requerimientos,” Rev. Fuentes el Reventón Energético, vol. 15, no. 1, pp. 87–99, 2017, doi: https://doi.org/10.18273/revfue.v15n1-2017008
  5. O. S. Osundare, G. Falcone, L. Lao, A. Elliott, “Liquid-liquid flow pattern prediction using relevant dimensionless parameter groups,” Energies, vol. 13, no. 17, 2020, doi: https://doi.org/10.3390/en13174355
  6. C. R. K. García, J. García, G. Montoya, M. T. Valecillos, “Determinación de altura de fase y Hold Up para flujo bifásico líquido-líquido en tuberías horizontales por medio de procesamiento de imágenes,” in VIII Congreso anual de ingeniería ASME, Caracas, Venezuela, 2009, pp. 1–10.
  7. N. Varotsis, “Prediction of gas phase volumetric variations in diphasic reservoir oils,” J. Can. Pet. Technol., vol. 36, no. 8, pp. 56–60, 1997, doi: https://doi.org/10.2118/97-08-05
  8. M. R. Malayeri, H. Müller-Steinhagen, J. M. Smith, “Neural network analysis of void fraction in air/water two-phase flows at elevated temperatures,” Chem. Eng. Process. Process Intensif., vol. 42, no. 8–9, pp. 587–597, 2003, doi: https://doi.org/10.1016/S0255-2701(02)00208-8
  9. M. Abdelhafidh, M. Fourati, L. C. Fourati, A. Abidi, “Remote water pipeline monitoring system IoT-based architecture for new industrial era 4.0,” Proc. IEEE/ACS Int. Conf. Comput. Syst. Appl. AICCSA, vol. 2017-Octob, pp. 1184–1191, 2018, doi: https://doi.org/10.1109/AICCSA.2017.158
  10. V. Slaný, A. Lučanský, P. Koudelka, J. Mareček, E. Krčálová, R. Martínek, “An integrated iot architecture for smart metering using next generation sensor for water management based on lorawan technology: A pilot study,” Sensors, vol. 20, no. 17, pp. 1–23, 2020, doi: https://doi.org/10.3390/s20174712
  11. C. M. Ruiz-Díaz, B. Quispe-Suarez, O. A. González-Estrada, “Two-phase oil and water flow pattern identification in vertical pipes applying long short-term memory networks,” Emergent Mater., pp. 1–13, 2024, doi: https://doi.org/10.1007/s42247-024-00631-2
  12. A. Ibrahim, B. Hewakandamby, Z. Yang, B. Azzopardi, “Effect of liquid viscosity on two-phase flow development in a vertical large diameter pipe,” Am. Soc. Mech. Eng. Fluids Eng. Div. FEDSM, vol. 3, pp. 1–10, 2018, doi: https://doi.org/10.1115/FEDSM2018-83466
  13. K. R. Sai, P. J. Nayak, K. V. A. Kumar, A. D. Dutta, “Oil Spill Management System Based on Internet of Things,” Proc. 2020 IEEE-HYDCON Int. Conf. Eng. 4th Ind. Revolution, HYDCON 2020, 2020, doi: https://doi.org/10.1109/HYDCON48903.2020.9242823
  14. C. Gomez, D. Ruiz, M. Cely, “Specialist system in flow pattern identification using artificial neural Networks,” J. Appl. Eng. Sci., vol. 21, no. 2, pp. 285–299, Jan. 2023, doi: https://doi.org/10.5937/jaes0-40309
  15. C. Ruiz-Díaz, M. M. Hernández-Cely, O. A. González-Estrada, “Modelo predictivo para el cálculo de la fracción volumétrica de un flujo bifásico agua- aceite en la horizontal utilizando una red neuronal artificial,” Rev. UIS Ing., vol. 21, no. 2, pp. 155–164, 2022, doi: https://doi.org/10.18273/revuin.v21n2-2022013
  16. V. Ganeshmoorthy, M. Muthukannan, M. Thirugnanasambandam, “Comparison of Linear Regression and ANN of Fish Oil Biodiesel Properties Prediction,” J. Phys. Conf. Ser., vol. 1276, no. 1, 2019, doi: https://doi.org/10.1088/1742-6596/1276/1/012074
  17. S. Chaki, A. K. Verma, A. Routray, W. K. Mohanty, M. Jenamani, “Well tops guided prediction of reservoir properties using modular neural network concept: A case study from western onshore, India,” J. Pet. Sci. Eng., vol. 123, pp. 155–163, 2014, doi: https://doi.org/10.1016/j.petrol.2014.06.019
  18. C. M. Ruiz-Diaz, M. M. Hernández-Cely, O. A. González-Estrada, “A Predictive Model for the Identification of the Volume Fraction in Two-Phase Flow,” Cienc. en Desarro., vol. 12, no. 2, pp. 49–55, 2021.
  19. Q. Cao, R. Banerjee, S. Gupta, J. Li, W. Zhou, B. Jeyachandra, “Data driven production forecasting using machine learning,” SPE Argentina Exploration and Production of Unconventional Resources Symposium, 2016. doi: https://doi.org/10.2118/180984-MS
  20. G. Luo, Y. Tian, M. Bychina, C. Ehlig-Economides, “Production optimization using machine learning in bakken shale,” SPE/AAPG/SEG Unconv. Resour. Technol. Conf. 2018, URTC 2018, no. 2011, 2018, doi: https://doi.org/10.15530/urtec-2018-2902505
  21. A. U. Osarogiagbon, F. Khan, R. Venkatesan, P. Gillard, “Review and analysis of supervised machine learning algorithms for hazardous events in drilling operations,” Process Saf. Environ. Prot., vol. 147, pp. 367–384, 2021, doi: https://doi.org/10.1016/j.psep.2020.09.038
  22. Z. Zhong, T. R. Carr, X. Wu, G. Wang, “Application of a convolutional neural network in permeability prediction: A case study in the Jacksonburg-Stringtown oil field, West Virginia, USA,” Geophysics, vol. 84, no. 6, pp. B363–B373, 2019, doi: https://doi.org/10.1190/geo2018-0588.1
  23. C. M. Salgado, R. S. F. Dam, W. L. Salgado, M. C. Santos, and R. Schirru, “Development of a deep rectifier neural network for fluid volume fraction prediction in multiphase flows by gamma-ray densitometry,” Radiat. Phys. Chem., vol. 189, no. July, p. 109708, 2021, doi: https://doi.org/10.1016/j.radphyschem.2021.109708
  24. P. Temirchev et al., “Deep neural networks predicting oil movement in a development unit,” J. Pet. Sci. Eng., vol. 184, no. August 2019, p. 106513, 2020, doi: https://doi.org/10.1016/j.petrol.2019.106513
  25. D. Biswas, “Adapting shallow and deep learning algorithms to examine production performance – Data analytics and forecasting,” Soc. Pet. Eng. - SPE/IATMI Asia Pacific Oil Gas Conf. Exhib. 2019, APOG 2019, 2019, doi: https://doi.org/10.2118/196404-ms
  26. S. Madasu, K. P. Rangarajan, “Deep recurrent neural network DrNN model for real-time step-down analysis,” Soc. Pet. Eng. - SPE Reserv. Characterisation Simul. Conf. Exhib. 2019, RCSC 2019, 2019, doi: https://doi.org/10.2118/196621-ms
  27. H. Li, S. Misra, J. He, “Neural network modeling of in situ fluid-filled pore size distributions in subsurface shale reservoirs under data constraints,” Neural Comput. Appl., vol. 32, no. 8, pp. 3873–3885, Apr. 2020, doi: https://doi.org/10.1007/s00521-019-04124-w
  28. A. Sagheer, M. Kotb, “Time series forecasting of petroleum production using deep LSTM recurrent networks,” Neurocomputing, vol. 323, pp. 203–213, 2019, doi: https://doi.org/10.1016/j.neucom.2018.09.082
  29. H. D. Pasinato, N. F. M. Reh, “Modeling Turbulent Flows with LSTM Neural Network,” arXiv.org, Jul. 2023, doi: https://doi.org/10.48550/arxiv.2307.13784
  30. R. Vinuesa, S. L. Brunton, “Enhancing computational fluid dynamics with machine learning,” Nat. Comput. Sci., vol. 2, no. 6, pp. 358–366, Jun. 2022, doi: https://doi.org/10.1038/s43588-022-00264-7
  31. P. A. Costa Rocha, S. J. Johnston, V. Oliveira Santos, A. A. Aliabadi, J. V. G. Thé, B. Gharabaghi, “Deep Neural Network Modeling for CFD Simulations: Benchmarking the Fourier Neural Operator on the Lid-Driven Cavity Case,” Appl. Sci., vol. 13, no. 5, p. 3165, 2023, doi: https://doi.org/10.3390/app13053165
  32. A. F. Casas-Pulido, M. M. Hernández-Cely, O. M. Rodríguez-Hernández, “Análisis experimental de flujo líquido-líquido en un tubo horizontal usando redes neuronales artificiales,” Rev. UIS Ing., vol. 22, no. 1, pp. 49–56, Jan. 2023, doi: https://doi.org/10.18273/revuin.v22n1-2023005
  33. C. M. Ruiz-Díaz, E. E. Perilla-Plata, O. A. González-Estrada, “Two-Phase Flow Pattern Identification in Vertical Pipes Using Transformer Neural Networks,” Inventions, vol. 9, no. 1, p. 15, Jan. 2024, doi: https://doi.org/10.3390/inventions9010015
  34. J. Shi, L. Lao, H. Yeung, “Water-lubricated transport of high-viscosity oil in horizontal pipes: The water holdup and pressure gradient,” Int. J. Multiph. Flow, vol. 96, no. July, pp. 70–85, Nov. 2017, doi: https://doi.org/10.1016/j.ijmultiphaseflow.2017.07.005
  35. P. Abduvayt, R. Manabe, T. Watanabe, N. Arihara, “Analisis of Oil-Water Flow Tests in Horizontal, Hilly-Terrain, and Vertical Pipes,” in Proceedings of SPE Annual Technical Conference and Exhibition, Sep. 2004, pp. 1335–1347. doi: https://doi.org/10.2523/90096-MS
  36. J. Cai, C. Li, X. Tang, F. Ayello, S. Richter, S. Nesic, “Experimental study of water wetting in oil–water two phase flow—Horizontal flow of model oil,” Chem. Eng. Sci., vol. 73, pp. 334–344, May 2012, doi: https://doi.org/10.1016/j.ces.2012.01.014
  37. A. Al-Sarkhi, E. Pereyra, I. Mantilla, C. Avila, “Dimensionless oil-water stratified to non-stratified flow pattern transition,” J. Pet. Sci. Eng., vol. 151, no. September 2016, pp. 284–291, 2017, doi: https://doi.org/10.1016/j.petrol.2017.01.016
  38. J. Shi, L. Lao, H. Yeung, “Water-lubricated transport of high-viscosity oil in horizontal pipes: The water holdup and pressure gradient,” Int. J. Multiph. Flow, vol. 96, pp. 70–85, 2017, doi: https://doi.org/10.1016/j.ijmultiphaseflow.2017.07.005
  39. T. Al-Wahaibi et al., “Experimental investigation on flow patterns and pressure gradient through two pipe diameters in horizontal oil-water flows,” J. Pet. Sci. Eng., vol. 122, pp. 266–273, 2014, doi: https://doi.org/10.1016/j.petrol.2014.07.019
  40. A. Dasari, A. B. Desamala, A. K. Dasmahapatra, T. K. Mandal, “Experimental studies and probabilistic neural network prediction on flow pattern of viscous oil-water flow through a circular horizontal pipe,” Ind. Eng. Chem. Res., vol. 52, no. 23, pp. 7975–7985, 2013, doi: https://doi.org/10.1021/ie301430m
  41. R. Ibarra, I. Zadrazil, C. N. Markides, O. K. Matar, “Towards a universal dimensionless map of flow regime transitions in horizontal liquid-liquid flows,” in 11th International Conference on Heat Transfer, Fluid Mechanics and Thermodynamics, 2015, no. July, pp. 20–23.
  42. M. Nädler, D. Mewes, “Flow induced emulsification in the flow of two immiscible liquids in horizontal pipes,” Int. J. Multiph. Flow, vol. 23, no. 1, pp. 55–68, 1997, doi: https://doi.org/10.1016/S0301-9322(96)00055-9
  43. O. M. H. Rodriguez, R. V. A. Oliemans, “Experimental study on oil-water flow in horizontal and slightly inclined pipes,” Int. J. Multiph. Flow, vol. 32, no. 3, pp. 323–343, 2006, doi: https://doi.org/10.1016/j.ijmultiphaseflow.2005.11.001
  44. Z. Qiao, Z. Wang, C. Zhang, S. Yuan, Y. Zhu, J. Wang, “PVAm–PIP/PS composite membrane with high performance for CO2/N2 separation,” AIChE J., vol. 59, no. 4, pp. 215–228, 2012, doi: https://doi.org/10.1002/aic
  45. A. Wegmann, P. Rudolf von Rohr, “Two phase liquid-liquid flows in pipes of small diameters,” Int. J. Multiph. Flow, vol. 32, no. 8, pp. 1017–1028, 2006, doi: https://doi.org/10.1016/j.ijmultiphaseflow.2006.04.001
  46. W. McKinney, “Data Structures for Statistical Computing in Python,” Proceedings of the 9th Python in Science Conference, 2010, pp. 56–61, doi: https://doi.org/10.25080/majora-92bf1922-00a
  47. S. Hochreiter, J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: https://doi.org/10.1162/neco.1997.9.8.1735
  48. K. Greff, R. K. Srivastava, J. Koutnik, B. R. Steunebrink, J. Schmidhuber, “LSTM: A Search Space Odyssey,” IEEE Trans. Neural Networks Learn. Syst., vol. 28, no. 10, pp. 2222–2232, Oct. 2017, doi: https://doi.org/10.1109/TNNLS.2016.2582924

Artículos más leídos del mismo autor/a

1 2 > >>