Validación de modelos predictivos de analítica de datos de análisis de aceite usado para la toma de decisiones de mantenimiento en un turbogenerador de vapor.

dc.contributor.advisorGuevara Carazas, Fernando Jesús
dc.contributor.authorSierra Mejia, Juan Pablo
dc.contributor.researchgroupGestión, Operación y Mantenimiento de Activos - Gomacspa
dc.date.accessioned2022-03-01T16:23:20Z
dc.date.available2022-03-01T16:23:20Z
dc.date.issued2021-09-16
dc.descriptionilustraciones, diagramas, mapas, tablasspa
dc.description.abstractEn el presente trabajo se desarrollan modelos descriptivos, clasificatorios y predictivos de la analítica de datos, con el fin de generar una herramienta de toma de decisiones basadas en las observaciones capturadas de diferentes pruebas realizadas al aceite usado de un turbogenerador de vapor marca Siemens de una industria papelera. Se estructura una base de datos con la información recopilada en un periodo de seis años (81 registros).; allí se cuenta con mediciones de diferentes propiedades del lubricante, por lo que se seleccionan 4 variables principales para el análisis. Las variables seleccionadas son el Número acido total (TAN), el porcentaje de agua disuelta en el aceite, la concentración de fósforo en el aceite y la viscosidad a 40°c. Se implementan modelos de clusterización jerárquica, series de tiempo, aproximación por medias móviles y cartas de control. Por último, se presentan las conclusiones derivadas de la implementación de dichos modelos. (Texto tomado de la fuente)spa
dc.description.abstractIn this study, Data analytic models (descriptive, classificatory and predictive) are developed, in order to generate a decision-making tool based on observations obtained from different tests carried out on used oil of a Siemens brand steam turbogenerator from paper industry. A database is structured with information collected over a period of six years (81 records). There are measurements of different properties of lubricant, Then, 4 main variables are selected for analysis. Selected variables are Total Acid Number (TAN), percentage of water dissolved in oil, phosphorus concentration in oil and viscosity at 40 ° C. Hierarchical clustering models, time series, moving average approximation and control charts are implemented. Finally, Conclusions derived from the implementation of these models are presented.eng
dc.description.curricularareaÁrea Curricular de Ingeniería Mecánicaspa
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagíster en Ingeniería Mecánicaspa
dc.description.researchareaMachine Learning en gestión de mantenimientospa
dc.format.extentXII, 94 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/81094
dc.language.isospaspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Medellínspa
dc.publisher.departmentDepartamento de Ingeniería Mecánicaspa
dc.publisher.facultyFacultad de Minasspa
dc.publisher.placeMedellín, Colombiaspa
dc.publisher.programMedellín - Minas - Maestría en Ingeniería Mecánicaspa
dc.relation.referencesAhmad, R., & Kamaruddin, S. (2012). An overview of time-based and condition-based maintenance in industrial application. Computers & Industrial Engineering, 63(1), 135–149. https://doi.org/10.1016/j.cie.2012.02.002spa
dc.relation.referencesAlbarracín, P. R. (2015). Tribología y Lubricación (T. Ingeniería, Ed.). Medellín.spa
dc.relation.referencesAXA Risk Consulting. (2020). Steam Turbine Lubricating Oil Systems. 1–4.spa
dc.relation.referencesAyvaz, S., & Alpay, K. (2021). Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time. Expert Systems with Applications, 173, 114598. https://doi.org/10.1016/j.eswa.2021.114598spa
dc.relation.referencesBahari, A. (2017). Investigation into Tribological Performance of Vegetable Oils as Biolubricants at Severe Contact Conditions. (October), 292.spa
dc.relation.referencesBanaszkiewicz, M. (2014). Steam turbines start-ups. Transactions of the Institute of Fluid-Flow Machinery, 126(126), 169–198.spa
dc.relation.referencesBarrios, R. (2015). 3 Medidas De Tendencia Central Y De Dispersión. Slideshare, 59. Retrieved from https://es.slideshare.net/rbarriosm/3-medidas-de-tendencia-central-y-de-dispersion-49942466spa
dc.relation.referencesBergmeir, C., & Benítez, J. M. (2012). On the use of cross-validation for time series predictor evaluation. Information Sciences, 191, 192–213. https://doi.org/10.1016/j.ins.2011.12.028spa
dc.relation.referencesBergmeir, C., Hyndman, R. J., & Koo, B. (2018). A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics and Data Analysis, 120, 70–83. https://doi.org/10.1016/j.csda.2017.11.003spa
dc.relation.referencesBousdekis, A., Papageorgiou, N., Magoutas, B., Apostolou, D., & Mentzas, G. (2017). A Proactive Event-driven Decision Model for Joint Equipment Predictive Maintenance and Spare Parts Inventory Optimization. Procedia CIRP, 59(TESConf 2016), 184–189. https://doi.org/10.1016/j.procir.2016.09.015spa
dc.relation.referencesBrnabic, A., & Hess, L. M. (2021). Systematic literature review of machine learning methods used in the analysis of real-world data for patient-provider decision making. BMC Medical Informatics and Decision Making, 21(1), 54. https://doi.org/10.1186/s12911-021-01403-2spa
dc.relation.referencesBrown, P., & Sondalini, M. (n.d.). Asset Maintenance Management - The Path toward Defect Elimination. 1–10. Retrieved from www.lifetime-reliability.comspa
dc.relation.referencesCapuano, G., & Rimoli, J. J. (2019). Smart finite elements: A novel machine learning application. Computer Methods in Applied Mechanics and Engineering, 345, 363–381. https://doi.org/https://doi.org/10.1016/j.cma.2018.10.046spa
dc.relation.referencesCave, A. (2017). What Will We Do When The World’s Data Hits 163 Zettabytes In 2025? Retrieved March 8, 2019, from Forbes website: https://www.forbes.com/sites/andrewcave/2017/04/13/what-will-we-do-when-the-worlds-data-hits-163-zettabytes-in-2025/#694cc76c349aspa
dc.relation.referencesChiu, S., & Tavella, D. (2008). Introduction to Data Mining. Data Mining and Market Intelligence for Optimal Marketing Returns, 137–192. https://doi.org/10.1016/b978-0-7506-8234-3.00007-1spa
dc.relation.referencesColeman, W. (1981). Water Contamination of Steam Turbine Lube Oils - How to Avoid It. Journal of Chemical Information and Modeling, 53(9), 1689–1699.spa
dc.relation.referencesDeloitte Brazil. (2021). Strategic asset management. Retrieved April 30, 2021, from https://www2.deloitte.com/br/en/pages/finance/solutions/gestao-estrategica-ativos.htmlspa
dc.relation.referencesElshawi, R., Sakr, S., Talia, D., & Trunfio, P. (2018). Big Data Systems Meet Machine Learning Challenges: Towards Big Data Science as a Service. Big Data Research, 14, 1–11. https://doi.org/10.1016/j.bdr.2018.04.004spa
dc.relation.referencesEspino Timón, C., & Martínez Fontes, X. (2017). “Análisis predictivo: técnicas y modelos utilizados y aplicaciones del mismo - herramientas Open Source que permiten su uso. 26/27, I(Principio activo y prestación ortoprotésica), 67. Retrieved from http://openaccess.uoc.edu/webapps/o2/bitstream/10609/59565/6/caresptimTFG0117memòria.pdfspa
dc.relation.referencesExposito, C. (2020). Clustering jerarquico. Universidad de La Laguna.spa
dc.relation.referencesExxon Mobil. (2009). Turbine Oil System Care & Maintenance.spa
dc.relation.referencesExxon Mobil. (2020). Mobil SHC 825. Retrieved April 2, 2021, from https://www.mobil.com.mx/es-mx/lubricantes/industrial/lubricants/products/products/mobil-shc-825spa
dc.relation.referencesFaraldo, P. (2013). Estadística y metodología de la investigación. Universidad Santiago De Compostela, 15. Retrieved from http://eio.usc.es/eipc1/BASE/BASEMASTER/FORMULARIOS-PHP-DPTO/MATERIALES/Mat_G2021103104_EstadisticaTema1.pdfspa
dc.relation.referencesFernando, J., & Walters, T. (2021, February). Correlation Coefficient Definition. Retrieved May 1, 2021, from https://www.investopedia.com/terms/c/correlationcoefficient.aspspa
dc.relation.referencesFortune Business Insight. (2020). Lubricants Market Size, Share, Report. Retrieved April 30, 2021, from Market Research Report website: https://www.fortunebusinessinsights.com/industry-reports/lubricants-market-101771spa
dc.relation.referencesGuevara Carazas, F. J., & Martha daSouza, G. F. (2010). Risk-based decision making method for maintenance policy selection of thermal power plant equipment. Energy, 35(2), 964–975. https://doi.org/10.1016/j.energy.2009.06.054spa
dc.relation.referencesGupta, G., & Mishra, R. P. (2016). A SWOT analysis of reliability centered maintenance framework. Journal of Quality in Maintenance Engineering, 22(2), 130–145. https://doi.org/10.1108/JQME-01-2015-0002spa
dc.relation.referencesGutierrez Pulido, H., & De la Vara Salazar, R. (2009). Control Estadístico de la Calidad y Seis Sigma (M. Hill, Ed.). Guanajuato.spa
dc.relation.referencesHan, X., Wang, Z., Xie, M., He, Y., Li, Y., & Wang, W. (2021). Remaining useful life prediction and predictive maintenance strategies for multi-state manufacturing systems considering functional dependence. Reliability Engineering & System Safety, 210, 107560. https://doi.org/10.1016/j.ress.2021.107560spa
dc.relation.referencesHanke, J. E., & Wichern, D. W. (2010). Pronósticos en los negocios. In 9 Edición (Ed.), ممممم ممممم (Vol. 4). Retrieved from http://marefateadyan.nashriyat.ir/node/150spa
dc.relation.referencesHausermann, A. (1961). Particular Problems of Steam Turbine Lubrication. (Cv), 125–132.spa
dc.relation.referencesHejnowicz, Z., Burian, A., Dobrowolska, I., & Kolano, E. (2006). Orientational variability of parallel arrays of cortical microtubules under the outer cell wall of the Helianthus hypocotyl epidermis. Acta Societatis Botanicorum Poloniae, 75(3), 201–206. https://doi.org/10.5586/asbp.2006.023spa
dc.relation.referencesJiang, G., & Wang, W. (2017). Markov cross-validation for time series model evaluations. Information Sciences, 375, 219–233. https://doi.org/10.1016/j.ins.2016.09.061spa
dc.relation.referencesJiménez Rodríguez, C., & Arias Aguilar, D. (2004). Distribución de la biomasa y densidad de raíces finas en una gradiente sucesional de bosques en la Zona Norte de Costa Rica. Revista Forestal Mesoamerica Kurú, 1(2), pág. 44-63.spa
dc.relation.referencesJoseph Omosanya, A., Titilayo Akinlabi, E., & Olusegun Okeniyi, J. (2019). Overview for Improving Steam Turbine Power Generation Efficiency. Journal of Physics: Conference Series, 1378(3). https://doi.org/10.1088/1742-6596/1378/3/032040spa
dc.relation.referencesLahura, E. (2003). El Coeficiente De Correlación Y Correlaciones Espúreas. Universidad Catolica Del Perú, 1–64.spa
dc.relation.referencesLazovic, T., & Marinkovic, A. (2015). A case study of turbogenerator journal bearing failure. (February).spa
dc.relation.referencesLuo, J. (2013). Thin Film Lubrication. In Encyclopedia of Tribology (pp. 3663–3667). https://doi.org/10.1007/978-0-387-92897-5_682spa
dc.relation.referencesMacián, V., Tormos, B., Ruíz, S., & Ramírez, L. (2015). Potential of low viscosity oils to reduce CO2 emissions and fuel consumption of urban buses fleets. Transportation Research Part D: Transport and Environment, 39, 76–88. https://doi.org/10.1016/j.trd.2015.06.006spa
dc.relation.referencesMartha deSouza, G. F. (2012). Fundamentals of Maintenance. In Springer (Ed.), Thermal Power Plant Performance Analysis (pp. 123–146). Sao Paulo.spa
dc.relation.referencesMaxell, D. (1996). The History of the Steam Turbine. Pacific Turbines, (1629).spa
dc.relation.referencesMcCoy, J. T., & Auret, L. (2019). Machine learning applications in minerals processing: A review. Minerals Engineering, 132, 95–109. https://doi.org/https://doi.org/10.1016/j.mineng.2018.12.004spa
dc.relation.referencesMichalke, B., & Nischwitz, V. (2017). Speciation and element-specific detection. In Liquid Chromatography (pp. 753–767). https://doi.org/10.1016/B978-0-12-805392-8.00023-2spa
dc.relation.referencesMontoya-Restrepo, N. E., & Correa-Morales, J. C. (2009). Estadístico de Procesos en el Monitoreo de la Mortalidad Perinatal. Revista de Salud Publica, 11(1), 92–99.spa
dc.relation.referencesNeale, M. J. (1973). The Tribology Handbook. In Notes and Queries (Vol. s8-VI). https://doi.org/10.1093/nq/s8-VI.151.385-bspa
dc.relation.referencesNicholson, K. F., Richardson, R. T., van Roden, E. A. R., Quinton, R. G., Anzilotti, K. F., & Richards, J. G. (2019). Machine learning algorithms for predicting scapular kinematics. Medical Engineering & Physics, 65, 39–45. https://doi.org/https://doi.org/10.1016/j.medengphy.2019.01.005spa
dc.relation.referencesPalladino, A. C. (2011). Gráfico de caja. Atención Primaria de Salud, Epidemiología e Informatica II, 7–10.spa
dc.relation.referencesPatiño-Rodriguez, C. E., & Guevara Carazas, F. J. (2020). Maintenance and Asset Life Cycle for Reliability Systems. Reliability and Maintenance - An Overview of Cases. https://doi.org/10.5772/intechopen.85845spa
dc.relation.referencesPhillips 66. (2019). Next-Generation Turbine Oils Combat Oxidation , Thermal Degradation and Varnish.spa
dc.relation.referencesPintelon, L., & Parodi-Herz, A. (2008). Maintenance: An Evolutionary Perspective. Springer Series in Reliability Engineering, 8, 21–48. https://doi.org/10.1007/978-1-84800-011-7_2spa
dc.relation.referencesPourahmadi, M. (2002). A Course in Time Series Analysis. The American Statistician, 56(1), 77–77. https://doi.org/10.1198/tas.2002.s131spa
dc.relation.referencesR: The R Project for Statistical Computing. (n.d.). Retrieved April 15, 2021, from https://www.r-project.org/spa
dc.relation.referencesRaadnui, S., & Kleesuwan, S. (2005). Low-cost condition monitoring sensor for used oil analysis. Wear, 259(7–12), 1502–1506. https://doi.org/10.1016/j.wear.2004.11.009spa
dc.relation.referencesRaposo, H., Farinha, J. T., Fonseca, I., & Galar, D. (2019). Predicting condition based on oil analysis – A case study. Tribology International, 135(January), 65–74. https://doi.org/10.1016/j.triboint.2019.01.041spa
dc.relation.referencesReddy, a S., Ahmed, I., Kumar, T. S., Reddy, a V. K., & Bharathi, V. V. P. (2014). Analysis Of Steam Turbines. International Refereed Journal of Engineering and Science, 3(2), 32–48.spa
dc.relation.referencesSander, J. (2012). Steam Turbine Oil Challenges. LE White Paper, 1–10.spa
dc.relation.referencesScientific Spectro. (2000). Guide to Measuring TAN and TBN in Oil. Spectro Scientific, Spectro Sci. Retrieved from https://www.spectrosci.com/resource-center/lubrication-analysis/literature/e-guides/guide-to-measuring-tantbn/spa
dc.relation.referencesScopus. (2021a). Analyze search results for “lubricant” and “analytics.” Retrieved April 30, 2021, from https://www.scopus.com/term/analyzer.uri?sid=a091b7a8e94702c690c7bc7598eeaf06&origin=resultslist&src=s&s=TITLE-ABS-KEY%28%22lubricant%22+and+%22analytics%22%29&sort=plf-f&sdt=b&sot=b&sl=42&count=26&analyzeResults=Analyze+results&txGid=417060f79e9e194be4ae35a560a96415spa
dc.relation.referencesScopus. (2021b). Analyze search results for “Machine Learning” and “maintenance.” Retrieved April 30, 2021, from https://www.scopus.com/term/analyzer.uri?sid=de8fd338098c34bee445c5b4839b29cd&origin=resultslist&src=s&s=TITLE-ABS-KEY%28%22Machine+Learning%22+and+%22maintenance%22%29&sort=plf-f&sdt=b&sot=b&sl=51&count=3416&analyzeResults=Analyze+results&txGid=ed806beffspa
dc.relation.referencesScopus - Analyze search results. (n.d.). Retrieved March 19, 2019, from https://www-scopus-com.ezproxy.unal.edu.co/term/analyzer.uri?sid=6bce59022a605e33370d56242a5ba5fe&origin=resultslist&src=s&s=TITLE-ABS-KEY%28machine+learning%29&sort=plf-f&sdt=b&sot=b&sl=31&count=171267&analyzeResults=Analyze+results&txGid=da2bb524285aa00spa
dc.relation.referencesShahbazi, N., Bortoluzzi, B., Raghubar, C., An, A., Fok, R., & McArthur, J. J. (2018). Machine learning and BIM visualization for maintenance issue classification and enhanced data collection. Advanced Engineering Informatics, 38(October 2017), 101–112. https://doi.org/10.1016/j.aei.2018.06.007spa
dc.relation.referencesShimadzu. (2003). Elemental Analysis of Additives in Lubricant Oils Using ICPE-9820. Application News, J111.spa
dc.relation.referencesSibata. (2020). Viscosity Measurement Series. Sibata. Retrieved from https://www.sibata.co.jp/wpcms/wp-content/themes/sibata/en/pdf/viscosity_measurement_series.pdfspa
dc.relation.referencesSpakovszky, Z. (2007). Enhancements of Rankine Cycles. Retrieved March 28, 2021, from Unified: Thermodynamics and propulsion website: https://web.mit.edu/16.unified/www/FALL/thermodynamics/notes/node66.htmlspa
dc.relation.referencesSpectro Scientific. (2015). Guide to Measuring Water in Oil. Spectro Scientific, 5. Retrieved from https://www.spectrosci.com/resource-center/lubrication-analysis/literature/whitepapers/guide-to-measuring-water-in-oil/%5Cnhttp://www.spectrosci.com/resource-center/lubrication-analysis/literature/e-guides/guide-to-measuring-water-in-oil/spa
dc.relation.referencesSyan, C. S., Ramsoobag, G., Mahabir, K., & Rajnauth, V. (2020). A Case Study for Improving Maintenance Planning of Centrifugal Pumps Using Condition-Based Maintenance. 42(2), 17–24.spa
dc.relation.referencesTroyer, D., & Fitch, J. (2004). Oil Analysis Basics. León: Noria.spa
dc.relation.referencesUcci, D., Aniello, L., & Baldoni, R. (2019). Survey of machine learning techniques for malware analysis. Computers & Security, 81, 123–147. https://doi.org/https://doi.org/10.1016/j.cose.2018.11.001spa
dc.relation.referencesVališ, D., Žák, L., & Pokora, O. (2015). Failure prediction of diesel engine based on occurrence of selected wear particles in oil. Engineering Failure Analysis, 56, 501–511. https://doi.org/10.1016/j.engfailanal.2014.11.020spa
dc.relation.referencesVellido, A., Martín-Guerrero, J. D., & Lisboa, P. J. G. (2012). Making machine learning models interpretable. ESANN 2012 Proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, (April), 163–172.spa
dc.relation.referencesZhang, Z., & Sejdić, E. (2019). Radiological images and machine learning: Trends, perspectives, and prospects. Computers in Biology and Medicine. https://doi.org/https://doi.org/10.1016/j.compbiomed.2019.02.017spa
dc.relation.referencesZhao, Y. (2017). The Importance of Lubricant and Fluid Analysis in Predictive Maintenance. Spectro Scientific, (Figure 1), 1–6. Retrieved from https://www.spectrosci.com/blog/the-importance-of-lubricant-and-fluid-analysis-in-predictive-maintenance/spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-NoComercial-CompartirIgual 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/spa
dc.subject.ddc620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingenieríaspa
dc.subject.lembOil reclamation
dc.subject.lembRecuperación de aceites usados
dc.subject.proposalAnálisis de aceite usadospa
dc.subject.proposalMachine Learningeng
dc.subject.proposalTurbogenerador de vaporspa
dc.subject.proposalAnalítica de datosspa
dc.subject.proposalMantenimiento predictivospa
dc.subject.proposalUsed Oil Analysiseng
dc.subject.proposalSteam Turbogeneratorfra
dc.subject.proposalData Analyticseng
dc.subject.proposalPredictive Maintenanceeng
dc.titleValidación de modelos predictivos de analítica de datos de análisis de aceite usado para la toma de decisiones de mantenimiento en un turbogenerador de vapor.spa
dc.title.translatedValidation of predictive models on used oil analysis data for maintenance decision making in a steam turbo generator.eng
dc.typeTrabajo de grado - Maestríaspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TMspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentEstudiantesspa
dcterms.audience.professionaldevelopmentInvestigadoresspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
1037633177. 2021.pdf
Tamaño:
2.13 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería Mecánica

Bloque de licencias

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
license.txt
Tamaño:
3.98 KB
Formato:
Item-specific license agreed upon to submission
Descripción: