Mostrar el registro sencillo del ítem

dc.contributor.authorRuiz Diaz, Carlos Mauricio
dc.contributor.authorPerilla Plata, Erwing Eduardo
dc.contributor.authorGonzález Estrada, Octavio Andrés
dc.coverage.spatialColombiaen_US
dc.date.accessioned2026-05-08T12:40:22Z
dc.date.available2026-05-08T12:40:22Z
dc.date.issued2024-01-18
dc.identifier.issn2411-5134en_US
dc.identifier.urihttps://repositorioinstitucional.ufpso.edu.co/xmlui/handle/20.500.14167/6237
dc.description.abstractEl sector del petróleo y el gas adopta constantemente tecnologías innovadoras debido a los elevados costes asociados al transporte de hidrocarburos, a los problemas de corrosión de los oleoductos y a la necesidad de comprender mejor las características del flujo bifásico. Estas soluciones implican la implementación de modelos predictivos que utilizan redes neuronales. En este trabajo de investigación, se ha recopilado meticulosamente una base de datos exhaustiva que comprende 4864 puntos de datos, con información relativa a las propiedades del flujo bifásico de petróleo y agua en oleoductos verticales. Posteriormente, se empleó una red neuronal transformadora (TNN) de tipo «solo codificador» para identificar los patrones de flujo bifásico. Se propusieron diversas configuraciones para el modelo TNN, que implicaban ajustes de parámetros como el número de cabezales de atención, la función de activación, la tasa de abandono y la tasa de aprendizaje, con el objetivo de seleccionar la configuración que ofreciera resultados óptimos. Tras el entrenamiento de la red, se generaron predicciones utilizando un conjunto de datos reservado, lo que facilitó la creación de mapas de flujo que representaban los patrones previstos por el modelo. El modelo TNN desarrollado predijo con éxito 9 de los 10 patrones de flujo presentes en la base de datos, alcanzando una precisión máxima del 53,07 %. Además, los diversos patrones de flujo predichos mostraron una precisión media del 63,21 % y una exactitud media del 86,51 %.en_US
dc.language.isoengen_US
dc.relationhttps://www.mdpi.com/2411-5134/9/1/15en_US
dc.titleIdentificación de patrones de flujo bifásico en tuberías verticales mediante redes neuronales transformadorasen_US
dc.title.translatedTwo-phase flow pattern identification in vertical pipes using transformer neural networksen_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.researchgateCarlos Mauricio Ruiz Diaz [Carlos-Mauricio-Ruiz-Diaz]en_US
dc.contributor.researchgateOctavio Andrés González Estrada [Octavio-Gonzalez-Estrada]en_US
dc.contributor.scopusCarlos Mauricio Ruiz Diaz [57326268000]en_US
dc.contributor.scopusOctavio Andrés González Estrada [25927116600]en_US
dc.description.abstractenglishThe oil and gas industry consistently embraces innovative technologies due to the sig nificant expenses associated with hydrocarbon transportation, pipeline corrosion issues, and the necessity to gain a deeper understanding of two-phase flow characteristics. These solutions involve the implementation of predictive models utilizing neural networks. In this research paper, a compre hensive database comprising 4864 data points, encompassing information pertaining to oil–water two-phase flow properties within vertical pipelines, was meticulously curated. Subsequently, an encoder-only type transformer neural network (TNN) was employed to identify two-phase flow patterns. Various configurations for the TNN model were proposed, involving parameter adjustments such as the number of attention heads, activation function, dropout rate, and learning rate, with the aim of selecting the configuration yielding optimal outcomes. Following the training of the network, predictions were generated using a reserved dataset, thus facilitating the creation of flow maps depicting the patterns anticipated by the model. The developed TNN model successfully predicted 9 out of the 10 flow patterns present in the database, achieving a peak accuracy of 53.07%. Furthermore, the various predicted flow patterns exhibited an average precision of 63.21% and an average accuracy of 86.51%.en_US
dc.subject.proposalRed neuronal transformadoraen_US
dc.subject.proposalFlujo bifásicoen_US
dc.subject.proposalIdentificación de patrones de flujoen_US
dc.subject.proposalAprendizaje automáticoen_US
dc.subject.proposalTransporte de fluidosen_US
dc.subject.keywordsTransformer neural networken_US
dc.subject.keywordsTwo-phase flowen_US
dc.subject.keywordsFlow pattern identificationen_US
dc.subject.keywordsMachine learningen_US
dc.subject.keywordsFluid transporten_US
dc.publisher.facultyFacultad ingenieríasen_US
dc.type.redcolhttp://purl.org/redcol/resource_type/ARTen_US
dc.relation.referencesRosa, E.S. Escoamento Multifásico Isotérmico: Modelos de Multifluidos e de Mistura; Bookman: Porto Alegre, Brasil, 2012; ISBN 9788540700703en_US
dc.relation.referencesHernández-Cely, M.M.; Ruiz-Díaz, C. Estudio de los fluidos aceite-agua a través del sensor basado en la permitividad eléctrica del patrón de fluido. Rev. UIS Ing. 2020, 19, 177–186. [CrossRef]en_US
dc.relation.referencesSantos, D.S.; Faia, P.M.; Garcia, F.A.P.; Rasteiro, M.G. Oil/water stratified flow in a horizontal pipe: Simulated and experimental studies using EIT. J. Pet. Sci. Eng. 2019, 174, 1179–1193. [CrossRefen_US
dc.relation.referencesLiu, H.; Duan, J.; Li, J.; Gu, K.; Lin, K.;Wang, J.; Yan, H.; Guan, L.; Li, C. Numerical quasi-three dimensional modeling of stratified oil-water flow in horizontal circular pipe. Ocean Eng. 2022, 251, 111172. [CrossRef]en_US
dc.relation.referencesObaseki, M.; Elijah, P.T.; Alfred, P.B. Development of model to eliminate sand trapping in horizontal fluid pipelines. J. King Saud Univ.-Eng. Sci. 2022, 34, 425–434. [CrossRef]en_US
dc.relation.referencesGomez, C.; Ruiz, D.; Cely, M. Specialist system in flow pattern identification using artificial neural Networks. J. Appl. Eng. Sci. 2023, 21, 285–299. [CrossRef]en_US
dc.relation.referencesBazon, P.B.; Castro-Bolivar, J.E.; Ruiz-Diaz, C.M.; Hernández-Cely, M.M.; Rodriguez, O.M.H. Hybrid machine learning model applied to phase inversion prediction in liquid-liquid pipe flow. Multiph. Sci. Technol. 2023, 35, 35–53. [CrossRef]en_US
dc.relation.referencesde Almeida Coelho, N.M.; Taqueda, M.E.S.; Souza, N.M.O.; de Paiva, J.L.; Santos, A.R.; Lia, L.R.B.; de Moraes, M.S.; de Moraes Júnior, D. Energy savings on heavy oil transportation through core annular flow pattern: An experimental approach. Int. J. Multiph. Flow 2020, 122, 103127. [CrossRef]en_US
dc.relation.referencesSánchez, E.; Romero, C.; Zeppieri, S.; González-Mendizabal, D. Estudio experimental sobre patrones de flujo líquido-líquido en tuberias verticales. In Proceedings of the 8◦ Congreso Iberoamericano de Ingeniería Mecánica; Universidad Pontificia del Peru: Cusco, Mexico, 2007en_US
dc.relation.referencesRuiz-Díaz, C.; Hernández-Cely, M.M.; González-Estrada, O.A. 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. 2022, 21, 155–164. [CrossRef]en_US
dc.relation.referencesSanguino, V. Modelamiento en CFD de Flujo Bifásico (Aceite-Agua) en una Tubería Vertical. Bachelor’s Thesis, Universidad de los Andes, Bogotá, Colombia, 2014.en_US
dc.relation.referencesVasheghani Farahani, M.; Jahanpeyma, Y.; Taghikhani, V. Dynamic Modeling and Numerical Simulation of Gas Lift Performance in Deviated Oil Well Using the Two-Fluid Model. In Proceedings of the 80th EAGE Conference and Exhibition 2018, Copenhagen, Denmark, 11–14 June 2018; European Association of Geoscientists & Engineers: Utrecht, The Netherlands, 2018. [CrossRef]en_US
dc.relation.referencesHassanpouryouzband, A.; Yang, J.; Tohidi, B.; Chuvilin, E.; Istomin, V.; Bukhanov, B. Geological CO2 Capture and Storage with Flue Gas Hydrate Formation in Frozen and Unfrozen Sediments: Method Development, Real Time-Scale Kinetic Characteristics, Efficiency, and Clathrate Structural Transition. ACS Sustain. Chem. Eng. 2019, 7, 5338–5345. [CrossRef]en_US
dc.relation.referencesHassanpouryouzband, A.; Joonaki, E.; Taghikhani, V.; Bozorgmehry Boozarjomehry, R.; Chapoy, A.; Tohidi, B. New Two- Dimensional Particle-Scale Model To Simulate Asphaltene Deposition inWellbores and Pipelines. Energy Fuels 2018, 32, 2661–2672. [CrossRef]en_US
dc.relation.referencesNorouzi, S.; Nazari, M.; VasheghaniFarahani, M. A Novel Hybrid Particle Swarm Optimization-Simulated Annealing Approach for CO2-Oil Minimum Miscibility Pressure (MMP) Prediction. In Proceedings of the 81st EAGE Conference and Exhibition 2019, London, UK, 3–6 June 2019; European Association of Geoscientists & Engineers: Utrecht, The Netherlands, 2019; pp. 1–5. [CrossRef]en_US
dc.relation.referencesSossa, J. El papel de la inteligencia artificial en la Industria 4.0. In Inteligencia Artificial y Datos Masivos en Archivos Digitales Sonoros y Audiovisuales; Rodríguez Reséndiz, P.O., Ed.; Univ. Nacional Autónoma de México: Mexico City, Mexico, 2020.en_US
dc.relation.referencesValle Tamayo, G.A.; Romero Consuegra, F.; Cabarcas Simancas, M.E. Predicción de flujo multifásico en sistemas de recolección de crudo: Descripción de requerimientos. Rev. Fuentes Reventón Energético 2017, 15, 87–99. [CrossRef]en_US
dc.relation.referencesRuiz-Diaz, C.M.; Hernández-Cely, M.M.; González-Estrada, O.A. A Predictive Model for the Identification of the Volume Fraction in Two-Phase Flow. Cienc. Desarro. 2021, 12, 49–55en_US
dc.relation.referencesJahanandish, I.; Salimifard, B.; Jalalifar, H. Predicting bottomhole pressure in vertical multiphase flowing wells using artificial neural networks. J. Pet. Sci. Eng. 2011, 75, 336–342. [CrossRef]en_US
dc.relation.referencesSemeraro, F.; Griffiths, A.; Cangelosi, A. Human–robot collaboration and machine learning: A systematic review of recent research. Robot. Comput. Integr. Manuf. 2022, 79, 102432. [CrossRef]en_US
dc.relation.referencesVaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, L.; Polosukhin, I. Attention is All you Need. In Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA, 4–9 December 2017; Guyon, I., von Luxburg, U., Bengio, S., Wallach, H.M., Fergus, R., Vishwanathan, S.V.N., Garnett, R., Eds.; Curran Associates, Inc.: Red Hook, NY, USA, 2017; pp. 5998–6008.en_US
dc.relation.referencesLakew, S.M.; Cettolo, M.; Federico, M. A comparison of transformer and recurrent neural networks on multilingual neural machine translation. In Proceedings of the COLING 2018—27th International Conference on Computational Linguistics, Santa Fe, NM, USA, 20–26 August 2018; pp. 641–652.en_US
dc.relation.referencesBrown, T.B.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; et al. Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 2020, 2020, 1154–1156.en_US
dc.relation.referencesSafi Samghabadi, N.; Patwa, P.; Pykl, S.; Mukherjee, P.; Das, A.; Solorio, T. Aggression and Misogyny Detection using BERT: A Multi-Task Approach. In Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying; European Language Resources Association (ELRA): Marseille, France, 2020; pp. 126–131.en_US
dc.relation.referencesLe, N.Q.K.; Ho, Q.T. Deep transformers and convolutional neural network in identifying DNA N6-methyladenine sites in cross-species genomes. Methods 2022, 204, 199–206. [CrossRef] [PubMed]en_US
dc.relation.referencesSharma, A.; Jain, P.; Mahgoub, A.; Zhou, Z.; Mahadik, K.; Chaterji, S. Lerna: Transformer architectures for configuring error correction tools for short- and long-read genome sequencing. BMC Bioinform. 2022, 23, 25. [CrossRef]en_US
dc.relation.referencesBehjati, A.; Zare-Mirakabad, F.; Arab, S.S.; Nowzari-Dalini, A. Protein sequence profile prediction using ProtAlbert transformer. Comput. Biol. Chem. 2022, 99, 107717. [CrossRef]en_US
dc.relation.referencesQu, K.; Si, G.; Shan, Z.; Kong, X.G.; Yang, X. Short-term forecasting for multiple wind farms based on transformer model. Energy Rep. 2022, 8, 483–490. [CrossRef]en_US
dc.relation.referencesWang, L.; He, Y.; Li, L.; Liu, X.; Zhao, Y. A novel approach to ultra-short-term multi-step wind power predictions based on encoder–decoder architecture in natural language processing. J. Clean. Prod. 2022, 354, 131723. [CrossRef]en_US
dc.relation.referencesGomaa, I.; Gowida, A.; Elkatatny, S.; Abdulraheem, A. The prediction of wellhead pressure for multiphase flow of vertical wells using artificial neural networks. J. Geosci. 2021, 14, 1–10. [CrossRef]en_US
dc.relation.referencesTunstall, L.; Von Werra, L.; Wolf, T. Natural Language Processing with Transformers: Building Language Applications with Hugging Face; O’Reilly: Sebastopol, CA, USA, 2022; ISBN 978-1-098-10324-8.en_US
dc.relation.referencesBannwart, A.C.; Rodriguez, O.M.H.; de Carvalho, C.H.M.; Wang, I.S.; Vara, R.M.O. Flow Patterns in Heavy Crude Oil-Water Flow. J. Energy Resour. Technol. 2004, 126, 184–189. [CrossRef]en_US
dc.relation.referencesAbduvayt, P.; Manabe, R.;Watanabe, T.; Arihara, N. Analisis of Oil-Water Flow Tests in Horizontal, Hilly-Terrain, and Vertical Pipes. In Proceedings of the SPE Annual Technical Conference and Exhibition; Society of Petroleum Engineers: London, UK, 2004; pp. 1335–1347. [CrossRef]en_US
dc.relation.referencesDu, M.; Jin, N.-D.; Gao, Z.-K.; Wang, Z.-Y.; Zhai, L.-S. Flow pattern and water holdup measurements of vertical upward oil–water two-phase flow in small diameter pipes. Int. J. Multiph. Flow 2012, 41, 91–105. [CrossRef]en_US
dc.relation.referencesFlores, J.; Chen, X.; Brill, J. Characterization of Oil-Water Flow Patterns in Vertical and DeviatedWells. In Proceedings of the SPE Annual Technical Conference and Exhibition; Society of Petroleum Engineers: London, UK, 1997; Volume 1, pp. 55–64. [CrossRef]en_US
dc.relation.referencesGanat, T.; Ridha, S.; Hairir, M.; Arisa, J.; Gholami, R. Experimental investigation of high-viscosity oil–water flow in vertical pipes: Flow patterns and pressure gradient. J. Pet. Explor. Prod. Technol. 2019, 9, 2911–2918. [CrossRef]en_US
dc.relation.referencesGovier, G.W.; Sullivan, G.A.; Wood, R.K. The upward vertical flow of oil-water mixtures. Can. J. Chem. Eng. 1961, 39, 67–75. [CrossRef]en_US
dc.relation.referencesHan, Y.F.; Jin, N.D.; Zhai, L.S.; Zhang, H.X.; Ren, Y.Y. Flow pattern and holdup phenomena of low velocity oil-water flows in a vertical upward small diameter pipe. J. Pet. Sci. Eng. 2017, 159, 387–408. [CrossRef]en_US
dc.relation.referencesHasan, A.R.; Kabir, C.S. A New Model for Two-Phase Oil/Water Flow: Production Log Interpretation nd Tubular Calculations. SPE Prod. Eng. 1990, 5, 193–199. [CrossRef]en_US
dc.relation.referencesHasan, A.R.; Kabir, C.S. A simplified model for oil/water flow in vertical and deviated wellbores. SPE Prod. Facil. 1999, 14, 56–62. [CrossRef]en_US
dc.relation.referencesJana, A.K.; Das, G.; Das, P.K. Flow regime identification of two-phase liquid–liquid upflow through vertical pipe. Chem. Eng. Sci. 2006, 61, 1500–1515. [CrossRef]en_US
dc.relation.referencesJana, A.K.; Ghoshal, P.; Das, G.; Das, P.K. An Analysis of Pressure Drop and Holdup for Liquid-Liquid Upflow through Vertical Pipes. Chem. Eng. Technol. 2007, 30, 920–925. [CrossRef]en_US
dc.relation.referencesGuo, J.; Yang, Y.; Zhang, S.; Zhang, D.; Cao, C.; Ren, B.; Liu, L.; Xing, Y.; Xiong, R. Heavy oil-water flow patterns in a small diameter vertical pipe under high temperature/pressure conditions. J. Pet. Sci. Eng. 2018, 171, 1350–1365. [CrossRef]en_US
dc.relation.referencesMazza, R.A.; Suguimoto, F.K. Experimental investigations of kerosene-water two-phase flow in vertical pipe. J. Pet. Sci. Eng. 2020, 184, 106580. [CrossRef]en_US
dc.relation.referencesMydlarz-Gabryk, K.; Pietrzak, M.; Troniewski, L. Study on oil–water two-phase upflow in vertical pipes. J. Pet. Sci. Eng. 2014, 117, 28–36. [CrossRef]en_US
dc.relation.referencesRodriguez, O.M.H.; Bannwart, A.C. Experimental study on interfacial waves in vertical core flow. J. Pet. Sci. Eng. 2006, 54, 140–148. [CrossRef]en_US
dc.relation.referencesXu, J.; Li, D.; Guo, J.; Wu, Y. Investigations of phase inversion and frictional pressure gradients in upward and downward oil–water flow in vertical pipes. Int. J. Multiph. Flow 2010, 36, 930–939. [CrossRefen_US
dc.relation.referencesYang, Y.; Guo, J.; Ren, B.; Zhang, S.; Xiong, R.; Zhang, D.; Cao, C.; Liao, Z.; Zhang, S.; Fu, S. Oil-Water flow patterns, holdups and frictional pressure gradients in a vertical pipe under high temperature/pressure conditions. Exp. Therm. Fluid Sci. 2019, 100, 271–291. [CrossRef]en_US
dc.relation.referencesZhao, D.; Guo, L.; Hu, X.; Zhang, X.; Wang, X. Experimental study on local characteristics of oil-water dispersed flow in a vertical pipe. Int. J. Multiph. Flow 2006, 32, 1254–1268. [CrossRef]en_US
dc.identifier.DOIhttps://doi.org/10.3390/inventions9010015en_US


Ficheros en el ítem

Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem