Mostrar el registro sencillo del ítem

Aplicación de técnicas de inteligencia artificial para el diagnóstico temprano de cavitación en sistemas de bombeo

dc.contributor.authorEscobar Valencia, David
dc.contributor.authorRegino Ubarnes, Fernando Jesús
dc.coverage.spatialColombiaen_US
dc.date.accessioned2025-10-20T21:45:13Z
dc.date.available2025-10-20T21:45:13Z
dc.date.issued2025-08-11
dc.identifier.issn2011-642Xen_US
dc.identifier.urihttps://repositorioinstitucional.ufpso.edu.co/xmlui/handle/20.500.14167/5823
dc.description.abstractEste artículo presenta el diseño y entrenamiento de una red neuronal artificial para la detección temprana de cavitación en sistemas de bombeo. Se utilizaron datos generados por simulación hidráulica, considerando variables como presión atmosférica, altura estática, temperatura y pérdidas por fricción. El modelo fue entrenado y evaluado en MATLAB, alcanzando una precisión superior al 99%. Los resultados muestran que este enfoque puede ser una herramienta eficaz para diagnóstico predictivo, especialmente en entornos rurales con acceso limitado a instrumentación especializada.en_US
dc.language.isospaen_US
dc.relationhttps://revistas.ufps.edu.co/index.php/ingenio/article/view/5163en_US
dc.titleAplicación de técnicas de inteligencia artificial para el diagnóstico temprano de cavitación en sistemas de bombeoen_US
dc.title.translatedApplication of artificial intelligence techniques for early cavitation diagnosis in pumping systemsen_US
dc.contributor.cvlacDavid Escobar Valencia [0000154045]en_US
dc.contributor.cvlacFernando Jesús Regino Ubarnes [0001508915]en_US
dc.contributor.googlescholarFernando Jesús Regino Ubarnes [l6g9NY8AAAAJ]en_US
dc.contributor.orcidDavid Escobar Valencia [0000-0002-1076-1597]en_US
dc.contributor.orcidFernando Jesús Regino Ubarnes [0000-0003-0414-8654]en_US
dc.contributor.researchgateFernando Jesús Regino Ubarnes [Fernando-Regino]
dc.contributor.scopusFernando Jesús Regino Ubarnes [57212414222]en_US
dc.description.abstractenglishThis article presents the design and training of an artificial neural network for early cavitation detection in pumping systems. The model was trained using hydraulically simulated data, considering variables such as atmospheric pressure, static suction height, temperature, and friction losses. The network was developed and evaluated in MATLAB, achieving an accuracy above 99%. Results show that this approach can serve as an effective tool for predictive diagnosis, especially in rural environments with limited access to specialized instrumentation.en_US
dc.subject.proposalCavitaciónen_US
dc.subject.proposalRedes neuronales artificialesen_US
dc.subject.proposalNPSHaen_US
dc.subject.proposalBombeoen_US
dc.subject.proposalMantenimiento predictivoen_US
dc.subject.proposalSimulación hidráulicaen_US
dc.subject.proposalMATLABen_US
dc.subject.keywordsCavitationen_US
dc.subject.keywordsArtificial neural networksen_US
dc.subject.keywordsNPSHaen_US
dc.subject.keywordsPumpingen_US
dc.subject.keywordsPredictive maintenanceen_US
dc.subject.keywordsHydraulic simulationen_US
dc.subject.keywordsMATLABen_US
dc.publisher.facultyFacultad ingenieríasen_US
dc.type.redcolhttp://purl.org/redcol/resource_type/ARTen_US
dc.relation.referencesM.Rakibuzzaman,S.-H. Suh, H.-H. Kim, M.D.Islam, L Zhou, and M.A.El-Emmam,"Cavitation anderosion effects on hydraulic performances of a submersible drainage pump," Alexandria Eng.J.,vo.113,pp.431-450, Feb. 2025,doi: https://doi .org/10.1016/j. aej.2024.11.060 DOI: https://doi.org/10.1016/j.aej.2024.11.060en_US
dc.relation.referencesJ. Feng, B. Liu, X. Luo, G. Zhu, K. Li, and G. Wu, “Experimental investigation on characteristics of cavitation-induced vibration on the runner of a bulb turbine,” Mech. Syst. Signal Process., vol. 189, p. 110097, Apr. 2023, doi: https://doi.org/ 10.1016/j.ymssp.2023.110097 DOI: https://doi.org/10.1016/j.ymssp.2023.110097en_US
dc.relation.referencesW. Dong-wei, W. Wei-dong, H. Jia-jun, Z. Wei-guo, and L. Lai, “Experimental study of cavitation noise characteristics in a centrifugal pump based on power spectral density and wavelet transform,” Flow Meas. Instrum., vol. 94, p. 102481, Dec. 2023, doi: https://doi.org/10.1016/j.flowmeasinst.2023.102481 DOI: https://doi.org/10.1016/j.flowmeasinst.2023.102481en_US
dc.relation.referencesQ. Chao, Y. Hu, and C. Liu, “Physics informed neural networks for detecting the wear of friction pairs in axial piston pumps,” Reliab. Eng. Syst. Saf., vol. 261, p. 111144, Sep. 2025, doi: https:// doi.org/10.1016/j.ress.2025.111144 DOI: https://doi.org/10.1016/j.ress.2025.111144en_US
dc.relation.referencesW. Zhao, M. Egusquiza, C. Valero, D. Valentín, A. Presas, and E. Egusquiza, “On the use of artificial neural networks for condition monitoring of pumpturbines with extended operation,” Measurement, vol. 163, p. 107952, Oct. 2020, doi: https://doi.org/ 10.1016/j.measurement.2020.107952 DOI: https://doi.org/10.1016/j.measurement.2020.107952en_US
dc.relation.referencesL. Rajaoarisoa, R. Randrianandraina, G. J. Nalepa, and J. Gama, “Decision-making systems improvement based on explainable artificial intelligence approaches for predictive maintenance,” Eng. Appl. Artif. Intell., vol. 139, p. 109601, Jan. 2025, doi: https://doi.org/ 10.1016/j.engappai.2024.109601 DOI: https://doi.org/10.1016/j.engappai.2024.109601en_US
dc.relation.referencesL. Meitz et al., “A Literature Review Framework and Open Research Challenges for Predictive Maintenance in industry 4.0,” Comput. Ind. Eng., vol. 206, p. 111193, Aug. 2025, doi: https://doi.org /10.1016/j.cie.2025.111193 DOI: https://doi.org/10.1016/j.cie.2025.111193en_US
dc.relation.referencesL. Bachus and A. Custodio, “NPSH, net positive suction head,” in Know and Understand Centrifugal Pumps, Elsevier, 2003, pp. 12–23. doi: https://doi. org/10.1016/ B978-185617409-1/50003-7 DOI: https://doi.org/10.1016/B978-185617409-1/50003-7en_US
dc.relation.referencesA. R. Al-Obaidi, “Experimental novel investigation of diagnostics cavitation in axial pump using vibration and acoustic measurements based on CWT and FFT analyses approaches,” Appl. Acoust., vol. 236, p. 110758, Jun. 2025, doi: https://doi.org/ 10.1016/j.apacoust.2025.110758 DOI: https://doi.org/10.1016/j.apacoust.2025.110758en_US
dc.relation.referencesQ. Liu et al., “Investigation of cavitation characteristics in an aircraft centrifugal fuel pump,” Flow Meas. Instrum., vol. 96, p. 102521, Apr. 2024, doi: 10.1016/j.flowmeasinst.2024.102521 DOI: https://doi.org/10.1016/j.flowmeasinst.2024.102521en_US
dc.relation.referencesC. V. Prasshanth, S. Naveen Venkatesh, T. K. Mahanta, N. R. Sakthivel, and V. Sugumaran, “Fault diagnosis of monoblock centrifugal pumps using pre-trained deep learning models and scalogram images,” Eng. Appl. Artif. Intell., vol. 136, p. 109022, Oct. 2024, doi: 10.1016/j.engappai.2024.109022 DOI: https://doi.org/10.1016/j.engappai.2024.109022en_US
dc.relation.referencesR. Tiwari, D. J. Bordoloi, and A. Dewangan, “Blockage and cavitation detection in centrifugal pumps from dynamic pressure signal using deep learning algorithm,” Measurement, vol. 173, p. 108676, Mar. 2021, doi: 10.1016/j.measurement.2020.108676 DOI: https://doi.org/10.1016/j.measurement.2020.108676en_US
dc.relation.referencesJ. A. Gómez-Camperos, E. E. Espinel-Blanco, and F . J. Regino-Ubarnes, “Diagnosis of horizontal pipe leaks using neural networks,” J. Phys. Conf. Ser., vol. 1388, no. 1, p. 012032, Nov. 2019, doi: https:// doi.org/10.1088/1742-6596/1388/1/012032 DOI: https://doi.org/10.1088/1742-6596/1388/1/012032en_US
dc.relation.referencesC. E. Álvarez-Pacheco, C. M. Ruiz-Diaz, and O. M. Hernandez-Rodriguez, “Chordal measurement of phase fraction distribution in a static gas-liquid system using collimated gamma-ray densitometer and artificial neural networks,” Rev. Ingenio, vol. 21, no. 1, pp. 29–35, Jan. 2024, doi: https://doi.org/10. 22463/2011642X.4098 DOI: https://doi.org/10.22463/2011642X.4098en_US
dc.relation.referencesZ. J. Ibarra-Cuevas and F. E. Martínez-Pérez, “ Protocolo de comunicación inteligente para una arquitectura enfocada en internet de las cosas,” Rev. Ingenio, vol. 19, no. 1, pp. 24–30, Jan. 2022, doi: https://doi.org/10.22463/2011642X.2783 DOI: https://doi.org/10.22463/2011642X.2783en_US
dc.identifier.DOIhttps://doi.org/10.22463/2011642X.5163en_US


Ficheros en el ítem

Thumbnail
Nombre:
Aplicación de técnicas de ...
Tamaño:
1.005Mb
Formato:
PDF
Ver/

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

Mostrar el registro sencillo del ítem