Show simple item record

dc.contributor.authorUribe Tarazona, Daniel Yesid
dc.contributor.authorRuiz Diaz, Carlos Mauricio
dc.contributor.authorGonzález Estrada, Octavio Andrés
dc.coverage.spatialColombiaen_US
dc.date.accessioned2026-04-23T15:03:37Z
dc.date.available2026-04-23T15:03:37Z
dc.date.issued2025-07-09
dc.identifier.issn2297-3079en_US
dc.identifier.urihttps://repositorioinstitucional.ufpso.edu.co/xmlui/handle/20.500.14167/6233
dc.description.abstractEste estudio desarrolla un modelo robusto de aprendizaje automático basado en redes neuronales artificiales para clasificar seis patrones de flujo en el flujo bifásico de petróleo y agua dentro de tuberías horizontales, un aspecto clave para garantizar la eficiencia operativa, la integridad y un diseño rentable en la industria del petróleo y el gas. Se recopiló una base de datos compuesta por 1.846 puntos de datos experimentales a partir de la bibliografía, que abarcaba diversas condiciones de funcionamiento, incluidas las propiedades de los fluidos, las velocidades superficiales y los diámetros de las tuberías. Tras evaluar 104 configuraciones de red, se seleccionó el modelo óptimo, que alcanzó una precisión global del 95,4 %, con precisiones de entrenamiento, validación y prueba del 97,1 %, 92,8 % y 90,3 %, respectivamente, y un error de entropía cruzada de 0,024. El modelo demostró una rápida convergencia con un tiempo de entrenamiento de solo 2 s, lo que lo convierte en una herramienta fiable y computacionalmente eficiente para el reconocimiento de patrones de flujo. Los resultados de este estudio aportan un valor significativo para mejorar el diseño de tuberías, optimizar las estrategias de garantía de flujo, mejorar el control de la corrosión y respaldar la toma de decisiones operativas en tiempo real en sistemas de transporte multifásico en la industria del petróleo y el gas.en_US
dc.language.isoengen_US
dc.relationhttps://www.frontiersin.org/journals/mechanical-engineering/articles/10.3389/fmech.2025.1522120/fullen_US
dc.titleTécnica de aprendizaje automático para la identificación de patrones de flujo bifásico (aceite-agua) en tuberíasen_US
dc.title.translatedMachine learning technique for the identification of two-phase (oil-water) flow patterns through pipelinesen_US
dc.contributor.cvlacDaniel Yesid Uribe Tarazona [0001824646]en_US
dc.contributor.cvlacCarlos Mauricio Ruiz Diaz [0001772117]en_US
dc.contributor.cvlacOctavio Andrés González Estrada [0001406575]en_US
dc.contributor.googlescholarCarlos Mauricio Ruiz Diaz [x10qI0UAAAAJ]en_US
dc.contributor.googlescholarOctavio Andrés González Estrada [Z4YyFpgAAAAJ]en_US
dc.contributor.orcidCarlos Mauricio Ruiz Diaz [0000-0003-3836-9332]en_US
dc.contributor.orcidOctavio Andrés González Estrada [0000-0002-2778-3389]en_US
dc.contributor.researchgateDaniel Yesid Uribe Tarazona [Daniel-Yesid-Uribe-Tarazona]en_US
dc.contributor.scopusCarlos Mauricio Ruiz Diaz [57326268000]en_US
dc.contributor.scopusOctavio Andrés González Estrada [25927116600]en_US
dc.description.abstractenglishThis study develops a robust machine learning model based on artificial neural networks to classify six flow patterns in oil-water two-phase flow within horizontal pipelines, a key aspect for ensuring operational efficiency, integrity, and cost-effective design in the oil and gas industry. A database comprising 1,846 experimental data points was assembled from the literature, encompassing various operating conditions, including fluid properties, superficial velocities, and pipe diameters. After evaluating 104 network configurations, the optimal model was selected, achieving an overall accuracy of 95.4%, with training, validation, and testing accuracies of 97.1%, 92.8%, and 90.3%, respectively, and a cross-entropy error of 0.024. The model demonstrated rapid convergence with a training time of only 2 s, making it a reliable and computationally efficient tool for flow pattern recognition. The outcomes of this study provide significant value for improving pipeline design, optimizing flow assurance strategies, enhancing corrosion control, and supporting real-time operational decision-making in multiphase transport systems in the oil and gas industry.en_US
dc.subject.proposalRed neuronal artificialen_US
dc.subject.proposalReconocimiento de patrones de flujoen_US
dc.subject.proposalAprendizaje automáticoen_US
dc.subject.proposalFlujo bifásicoen_US
dc.subject.proposalTransporte de fluidosen_US
dc.subject.keywordsArtificial neural networken_US
dc.subject.keywordsFlow pattern recognitionen_US
dc.subject.keywordsMachine learningen_US
dc.subject.keywordsTwo-phase flowen_US
dc.subject.keywordsFluid transporten_US
dc.publisher.facultyFacultad ingenieríasen_US
dc.type.redcolhttp://purl.org/redcol/resource_type/ARTen_US
dc.relation.referencesAl-Wahaibi, T., Al-Wahaibi, Y., Al-Ajmi, A., Al-Hajri, R., Yusuf, N., Olawale, A., et al. (2014). Experimental investigation on flow patterns and pressure gradient through two pipe diameters in horizontal oil-water flows. J. Pet. Sci. Eng. 122, 266–273. doi:10.1016/j. petrol.2014.07.019en_US
dc.relation.referencesAbba, S. I., Usman, A. G., and Işik, S. (2020). Simulation for response surface in the HPLC optimization method development using artificial intelligence models: a datadriven approach. Chemom. Intell. Lab. Syst. 201 (November 2019), 104007. doi:10.1016/ j.chemolab.2020.104007en_US
dc.relation.referencesAbdel Azim, R. (2020). Prediction of multiphase flow rate for artificially flowing wells using rigorous artificial neural network technique. Flow.Meas. Instrum. 76 (September), 101835. doi:10.1016/j.flowmeasinst.2020.101835en_US
dc.relation.referencesAbduvayt, P., Manabe, R.,Watanabe, T., and Arihara, N. (2004). Analisis of oil-water flow tests in horizontal, hilly-terrain, and vertical pipes. Proc. - SPE Annu. Tech. Conf. Exhib., 1335–1347. doi:10.2523/90096-msen_US
dc.relation.referencesAlhashem, M. (2020). “Machine learning classification model for multiphase flow regimes in horizontal pipes,” in Int. Pet. Technol. Conf. 2020, IPTC 2020. doi:10.2523/ iptc-20058-abstracten_US
dc.relation.referencesAl-Naser, M., Elshafei, M., and Al-Sarkhi, A. (2016). Artificial neural network application for multiphase flow patterns detection: a new approach. J. Pet. Sci. Eng. 145, 548–564. doi:10.1016/j.petrol.2016.06.029en_US
dc.relation.referencesAl-Sarkhi, A., Pereyra, E., Mantilla, I., and Avila, C. (2017). Dimensionless oil-water stratified to non-stratified flow pattern transition. J. Pet. Sci. Eng. 151, 284–291. doi:10. 1016/j.petrol.2017.01.016en_US
dc.relation.referencesArgatov, I. (2019). Artificial neural networks (ANNs) as a novel modeling technique in tribology. Front. Mech. Eng. 5. doi:10.3389/fmech.2019.00030en_US
dc.relation.referencesBahrami, B.,Mohsenpour, S., Shamshiri Noghabi, H. R., Hemmati, N., and Tabzar, A. (2019). Estimation of flow rates of individual phases in an oil-gas-water multiphase flow system using neural network approach and pressure signal analysis. Flow. Meas. Instrum. 66, 28–36. doi:10.1016/j.flowmeasinst.2019.01.018en_US
dc.relation.referencesCai, J., Li, C., Tang, X., Ayello, F., Richter, S., and Nesic, S. (2012). Experimental study of water wetting in oil-water two phase flow-Horizontal flow of model oil. Chem. Eng. Sci. 73, 334–344. doi:10.1016/j.ces.2012.01.014en_US
dc.relation.referencesChauvin, Y., and Rumelhart, D. E. (1995). Backpropagation: theory, architectures, and applications. Lawrence Erlbaum Associates, Inc.en_US
dc.relation.referencesChimeno-Trinchet, C., Murru, C., Díaz-García, M. E., Fernández-González, A., and Badía-Laíño, R. (2020). Artificial Intelligence and fourier-transform infrared spectroscopy for evaluating water-mediated degradation of lubricant oils. Talanta 219, 121312. doi:10.1016/j.talanta.2020.121312en_US
dc.relation.referencesCohen, J. (1988). Statistical power analysis for the behavioral sciences. Second Edition, 2nd edn. New York: Lawrence Erlbaum Associatesen_US
dc.relation.referencesÇolak, A. B. (2025). Investigating a machine learning algorithm’s applicability for simulating the apparent viscosity of waxy crude oil in a pipeline. Int. J. Oil, Gas. Coal Technol. 37 (3), 321–337. doi:10.1504/IJOGCT.2025.145438en_US
dc.relation.referencesDasari, A., Desamala, A. B., Dasmahapatra, A. K., and Mandal, T. K. (2013). Experimental studies and probabilistic neural network prediction on flow pattern of viscous oil-water flow through a circular horizontal pipe. Ind. Eng. Chem. Res. 52 (23), 7975–7985. doi:10.1021/ie301430men_US
dc.relation.referencesDíaz, C., González-Estrada, O., and Cely, M. (2021). “Predictive modeling of holdup in horizontal wateroil flow using a neural network approach,” in 14th WCCMECCOMAS congress (CIMNE), 11–15. doi:10.23967/wccm-eccomas.2020.283en_US
dc.relation.referencesDu, M., Yin, H., Chen, X., and Wang, X. (2019). Oil-in-Water two-phase flow pattern identification from experimental snapshots using convolutional neural network. IEEE Access 7, 6219–6225. doi:10.1109/ACCESS.2018.2888733en_US
dc.relation.referencesEl-Sebakhy, E. A. (2010). Flow regimes identification and liquid-holdup prediction in horizontal multiphase flow based on neuro-fuzzy inference systems. Math. Comput. Simul. 80 (9), 1854–1866. doi:10.1016/j.matcom.2010.01.002en_US
dc.relation.referencesFigueiredo,M.M. F.,Goncalves, J.L.,Nakashima, A.M. V.,Fileti, A.M. F., andCarvalho,R. D. M. (2016). The use of an ultrasonic technique and neural networks for identification of the flow pattern and measurement of the gas volume fraction in multiphase flows. Exp. Therm. Fluid Sci. 70, 29–50. doi:10.1016/j.expthermflusci.2015.08.010en_US
dc.relation.referencesGómez, G., Henao, J., and Salazar, H. (2004). Entrenamiento de una red neuronal artificial usando el algoritmo simulated annealing. Scientia Et Technica 1 (24), 13–18. Available online at: https://revistas.utp.edu.co/index.php/revistaciencia/article/view/7307.en_US
dc.relation.referencesGoodfellow, I., Bengio, Y., and Coutville, A. (2016). Deep learning.Massachusetts: The MIT Press.en_US
dc.relation.referencesGrassi, B., Strazza, D., and Poesio, P. (2008). Experimental validation of theoretical models in two-phase high-viscosity ratio liquid-liquid flows in horizontal and slightly inclined pipes. Int. J. Multiph. Flow. 34 (10), 950–965. doi:10.1016/j.ijmultiphaseflow. 2008.03.006en_US
dc.relation.referencesGuyon, I., and De, A. M. (2003). An introduction to variable and feature selection andré elisseeff. J. Mac. Learn. 3, 1157–1182.en_US
dc.relation.referencesGuyon, I., and De, A. M. (2003). An introduction to variable and feature selection andré elisseeff. J. Mac. Learn. 3, 1157–1182.en_US
dc.relation.referencesHernández-Cely, M. M., Ruiz-Díaz, C. M., and González-Estrada, O. A. (2022). Modelo predictivo para el cálculo de la fracción volumétrica de un flujo bifásico aguaaceite en la horizontal utilizando una red neuronal artificial. Rev. UIS Ing. 21 (2), 155–164. doi:10.18273/revuin.v21n2-2022013en_US
dc.relation.referencesHernández-Salazar, C. A., Carreño-Verdugo, A., and González-Estrada, O. A. (2024). Prediction of the volume fraction of liquid-liquid two-phase flow in horizontal pipesen_US
dc.relation.referencesusing Long-Short Term Memory Networks. Rev. UIS Ing. 23 (3). doi:10.18273/revuin. v23n3-2024002en_US
dc.relation.referencesHuang, Z., Duo, Y., and Xu, H. (2024). Prediction of two-phase flow patterns based on machine learning. Nucl. Eng. Des. 421, 113107. doi:10.1016/j.nucengdes.2024.113107en_US
dc.relation.referencesIbarra, R., Zadrazil, I., Markides, C. N., and Matar, O. K. (2015). Towards a universal dimensionless map of flow regime transitions in horizontal liquid-liquid flows. 11th International Conference on Heat Transfer, Fluid Mechanics and Thermodynamics, Kruger National Park 1-6. Available online at: https://www.imperial.ac.uk/cleanenergy- processes/publications/conferences/.en_US
dc.relation.referencesJorjani, E., Chehreh Chelgani, S., and Mesroghli, S. (2008). Application of artificial neural networks to predict chemical desulfurization of Tabas coal. Fuel 87 (12), 2727–2734. doi:10.1016/j.fuel.2008.01.029en_US
dc.relation.referencesLiu, X., Tang, H., Ding, Y., and Yan, D. (2022). Investigating the performance of machine learning models combined with different feature selection methods to estimate the energy consumption of buildings. Energy Build. 273 (Oct), 112408. doi:10.1016/j. enbuild.2022.112408en_US
dc.relation.referencesLum, J. Y. L., Al-Wahaibi, T., and Angeli, P. (2006). Upward and downward inclination oil–water flows. Int. J. Multiph. Flow. 32 (4), 413–435. doi:10.1016/J. IJMULTIPHASEFLOW.2006.01.001en_US
dc.relation.referencesMontoya, G., Garcia, K., Valencillos, M., Garcia, J., Romero, C., and Gonzalez- Mendizabal, D. (2009). “Determinación de altura de fase y hold up para flujo bifásico líquido-líquido en tuberías horizontales por medio de procesamiento de imágenes,” in Conference: American society of mechanical engineers (ASME) congress “ideas Practicas. . .Soluciones eficientes, 1–10.en_US
dc.relation.referencesNädler, M., and Mewes, D. (1997). Flow induced emulsification in the flow of two immiscible liquids in horizontal pipes. Int. J. Multiph. Flow. 23 (1), 55–68. doi:10.1016/ s0301-9322(96)00055-9en_US
dc.relation.referencesOsundare, O. S., Falcone, G., Lao, L., and Elliott, A. (2020). Liquid-liquid flow pattern prediction using relevant dimensionless parameter groups. Energies 13 (17), 4355. doi:10.3390/en13174355en_US
dc.relation.referencesPerera, K., Pradeep, C., Mylvaganam, S., and Time, R. W. (2017). Imaging of oil-water flow patterns by electrical capacitance tomography. Flow. Meas. Instrum. 56, 23–34. doi:10.1016/J.FLOWMEASINST.2017.07.002en_US
dc.relation.referencesPowers, D. M. W. (2011). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. J. Mach. Learn. Technol., 37–63. doi:10. 48550/arXiv.2010.16061en_US
dc.relation.referencesQin, J., Fan, C., Li, Z., and Zhang, C. (2021). “Flow pattern identification of oil-water two-phase flow based on multi-feature convolutional neural network,” in 2021 China automation congress (CAC) (IEEE), 7447–7451. doi:10.1109/CAC53003.2021.9727531en_US
dc.relation.referencesRazavi, M. A., Mortazavi, A., and Mousavi, M. (2003). Dynamic modelling of milk ultrafiltration by artificial neural network. J. Memb. Sci. 220 (1–2), 47–58. doi:10.1016/ S0376-7388(03)00211-4en_US
dc.relation.referencesRodriguez, O. M. H., and Oliemans, R. V. A. (2006). Experimental study on oil-water flow in horizontal and slightly inclined pipes. Int. J. Multiph. Flow. 32 (3), 323–343. doi:10.1016/j.ijmultiphaseflow.2005.11.001en_US
dc.relation.referencesRoshani, G. H., Feghhi, S. A. H., Mahmoudi-Aznaveh, A., Nazemi, E., and Adineh-Vand, A. (2014). Precise volume fraction prediction in oil-water-gas multiphase flows by means of gamma-ray attenuation and artificial neural networks using one detector. Meas. J. Int. Meas. Confed. 51 (1), 34–41. doi:10. 1016/j.measurement.2014.01.030en_US
dc.relation.referencesRoshani, M., Phan, G. T., JammalMuhammad Ali, P., Hossein Roshani, G.,Hanus, R., Duong, T., et al. (2021). Evaluation of flow pattern recognition and void fraction measurement in two phase flow independent of oil pipeline’s scale layer thickness. Alex. Eng. J. 60 (1), 1955–1966. doi:10.1016/J.AEJ.2020.11.043en_US
dc.relation.referencesRuiz-Díaz, C. M., Perilla-Plata, E. E., and González-Estrada, O. A. (2024a). Two-phase flow pattern identification in vertical pipes using transformer neural networks. Inventions 9 (1), 15. doi:10.3390/inventions9010015en_US
dc.relation.referencesRuiz-Díaz, C. M., Quispe-Suarez, B., and González-Estrada, O. A. (2024b). Twophase oil and water flow pattern identification in vertical pipes applying long shortterm memory networks. Emergent Mater, 0123456789. doi:10.1007/s42247-024- 00631-2en_US
dc.relation.referencesSalgado, C. M., Pereira, C. M. N. A., Schirru, R., and Brandão, L. E. B. (2010). Flow regime identification and volume fraction prediction in multiphase flows by means of gamma-ray attenuation and artificial neural networks. Prog. Nucl. Energy 52 (6), 555–562. doi:10.1016/j.pnucene.2010.02.001en_US
dc.relation.referencesShi, J., Lao, L., and Yeung, H. (2017). Water-lubricated transport of high-viscosity oil in horizontal pipes: the water holdup and pressure gradient. Int. J. Multiph. Flow. 96, 70–85. doi:10.1016/j.ijmultiphaseflow.2017.07.005en_US
dc.relation.referencesShi, J., and Yeung, H. (2017). Characterization of liquid-liquid flows in horizontal pipes. AIChE J. 63 (3), 1132–1143. doi:10.1002/aic.15452en_US
dc.relation.referencesShirley, R., Chakrabarti, D. P., and Das, G. (2012). Artificial neural networks in liquidliquid two-phase flow. Chem. Eng. Commun. 199 (12), 1520–1542. doi:10.1080/ 00986445.2012.682323en_US
dc.relation.referencesShoham, O. (2005). Mechanistic modeling of gas-liquid two-phase flow in pipes. 1st edn. Richardson, Texas: Society of Petroleum Engineers.en_US
dc.relation.referencesSoot, P. M. (1970). “A study of two-phase liquid-liquid flow in pipes,” in Thesis in partial fulfillment of the requirements for the degree of Doctor of Philosophy. Oregon State University. Available online at: https://ir.library.oregonstate.edu/downloads/ wp988n23x.en_US
dc.relation.referencesSu, Q., Bai, F., Fang, W., Li, J., and Liu, Z. (2024). “Ultrasonic identification method of oil-gas-water multiphase flow pattern based on K-means clustering algorithm,” in 2024 43rd Chinese control conference (CCC) (IEEE), 2100–2105. doi:10.23919/CCC63176. 2024.10661823en_US
dc.relation.referencesSun, J., Zheng, Y., Jiang, L., Yang, C., Huang, C., Sun, N., et al. (2025). Investigation on flow characteristics of highly viscous oil-water core-annular flow in horizontal pipes based on machine learning. Int. J. Multiph. Flow. 189, 105265. doi:10.1016/j. ijmultiphaseflow.2025.105265en_US
dc.relation.referencesWang, Y., Luo, F., Zhu, Z., Li, R., and Sina, M. (2024). Optimization of entrainment and interfacial flow patterns in countercurrent air-water two-phase flow in vertical pipes. Front. Mater. 11. doi:10.3389/fmats.2024.1454922en_US
dc.relation.referencesXie, J., Sage, M., and Zhao, Y. F. (2023). Feature selection and feature learning in machine learning applications for gas turbines: a review. Eng. Appl. Artif. Intell. 117, 105591. doi:10.1016/J.ENGAPPAI.2022.105591en_US
dc.relation.referencesXu, Z., Wu, F., Yang, Y., and Li, Y. (2021). ECT Attention Reverse Mapping algorithm: visualization of flow pattern heatmap based on convolutional neural network and its impact on ECT image reconstruction. Meas. Sci. Technol. 32 (3), 035403. doi:10.1088/1361-6501/abc1aden_US
dc.relation.referencesZhao, T., Zheng, Y., and Wu, Z. (2023). Feature selection-based machine learning modeling for distributed model predictive control of nonlinear processes. Comput. Chem. Eng. 169, 108074. doi:10.1016/j.compchemeng.2022.108074en_US
dc.identifier.DOI10.3389/fmech.2025.1522120en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record