En 6 día(s), 16 hora(s) y 17 minuto(s): El Repositorio Institucional UNAL informa a la comunidad universitaria que, con motivo del periodo de vacaciones colectivas, el servicio de publicación estará suspendido: Periodo de cierre: Del 20 de diciembre al 18 de enero de 2026. Sobre los depósitos: Durante este tiempo, los usuarios podrán continuar realizando el depósito respectivo de sus trabajos en la plataforma. Reanudación: Una vez reiniciadas las actividades administrativas, los documentos serán revisados y publicados en orden de llegada.

Prueba piloto de software industrial de analítica de datos aplicado al modelado de un activo de una planta industrial colombiana de Oil and Gas

Vista sencilla de ítem
dc.contributor.advisorGrisales Palacio, Victor Hugo
dc.contributor.authorCaballero Colina, Jesús Daniel
dc.contributor.cvlacCaballero C, Jesús [0002039433]
dc.contributor.educationalvalidatorMedina González, Juan David
dc.contributor.orcidCaballero Colina, Jesús D [0000000261913562]
dc.coverage.countryColombia
dc.date.accessioned2025-12-18T13:17:59Z
dc.date.available2025-12-18T13:17:59Z
dc.date.issued2025
dc.descriptionilustraciones a color, diagramas, fotografíasspa
dc.description.abstractEste trabajo presenta el desarrollo e implementación de una solución analítica predictiva aplicada a un compresor reciprocante de una planta de compresión de gas natural en Colombia. El objetivo principal fue diseñar y validar una herramienta de modelado predictivo como piloto de aplicación del software ThingWorx en entornos industriales reales. Se adoptó una metodología híbrida basada en marcos de ciencia de datos y metodologías nativas de la plataforma, adaptada al contexto técnico y operativo del activo. La solución integra modelos de detección de anomalías —basados en control estadístico de procesos (SPC)— para 12 variables críticas, y modelos de pronóstico multivariable para predecir 18 variables en ventanas de hasta 24 horas. Se emplearon datos históricos reales de dos años remuestreada a 30 y 60 minutos. La validación incluyó pruebas retroactivas con datos no vistos y análisis comparativo con eventos de falla documentados. La herramienta fue desplegada en la plataforma ThingWorx, con interfaces HMI diseñadas para el operario, y una estrategia de transferencia de conocimiento mediante curso estructurado en Moodle. Los resultados demuestran la viabilidad técnica y operativa de soluciones analíticas en activos críticos del sector Oil & Gas, y su potencial para anticipar fallas, apoyar decisiones operativas y facilitar la transición hacia modelos de mantenimiento predictivo digital (Texto tomado de la fuente).spa
dc.description.abstractThis work presents the development and implementation of a predictive analytics solution applied to a reciprocating compressor in a natural gas compression plant in Colombia. The main objective was to design and validate a predictive modeling tool as a pilot application of the ThingWorx software in real industrial environments. A hybrid methodology was adopted, based on data science frameworks and native platform methodologies, adapted to the technical and operational context of the asset. The solution integrates anomaly detection models —based on Statistical Process Control (SPC)— for 12 critical variables, and multivariable forecasting models to predict 18 variables with forecast windows of up to 24 hours. Two years of real historical data were used, resampled at 30 and 60 minutes. Validation included retrospective testing with unseen data and comparative analysis with documented failure events. The tool was deployed on the ThingWorx platform, featuring HMI interfaces designed for operators, and a knowledge transfer strategy implemented through a structured Moodle course. The results demonstrate the technical and operational feasibility of analytical solutions in critical assets of the Oil & Gas sector, and their potential to anticipate failures, support operational decisions, and facilitate the transition toward digital predictive maintenance models.eng
dc.description.degreelevelMaestría
dc.description.degreenameMagister en Automatización Industrial
dc.description.methodsSe adoptó una metodología híbrida basada en marcos de ciencia de datos y metodologías nativas de la plataforma, adaptada al contexto técnico y operativo del activo.
dc.description.notesContiene figura y tablasspa
dc.description.notesIt contains figures and tables.eng
dc.description.researchareaIndustria 4.0 en Automatización
dc.description.technicalinfoSistema desarrollado en software ThingWorxspa
dc.description.technicalinfoSystem developed in ThingWorx softwareeng
dc.format.extentxvii, 150 páginas
dc.format.mimetypeapplication/pdf
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/89228
dc.language.isospa
dc.publisherUniversidad Nacional de Colombia
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotá
dc.publisher.facultyFacultad de Ingeniería
dc.publisher.placeBogotá, Colombia
dc.publisher.programBogotá - Ingeniería - Maestría en Ingeniería - Automatización Industrial
dc.relation.referencesR. Teichert, «Digital Transformation Maturity: A Systematic Review of Literature,» Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis, vol. 67, no 6, pp. 1673-1687, 2019.
dc.relation.referencesK. Dörner y D. Edelman, «McKinsey & Company,» 1 Julio 2015. [En línea]. Available: https://www.mckinsey.com/industries/technology-media-and- telecommunications/our-insights/what-digital-really-means#/.
dc.relation.referencesISA, «Digital Transformation and Industry 4.0,» International Society of Automation, [En línea]. Available: https://www.isa.org/digital-transformation-and-industry-4-0.
dc.relation.referencesC. Angevine, J. Keomany, J. Thomsen y R. Zemmel, «McKinsey & Company,» 27 Mayo 2021. [En línea]. Available: https://www.mckinsey.com/industries/industrials- and-electronics/our-insights/implementing-a-digital-transformation-at-industrial- companies#/.
dc.relation.referencesGrand View Research, «Grand View Research Web Site,» 2024. [En línea]. Available: https://www.grandviewresearch.com/industry-analysis/digital-transformation-market.
dc.relation.referencesJ. Berge, «Digital Transformation and IIoT for Oil & Gas Production,» de Offshore Technology Conference, 2018.
dc.relation.referencesP. McLaughlin y R. McAdam, «Process Technology Web Site,» Honeywell Process Solutions, 14 Junio 2017. [En línea]. Available: https://www.processonline.com.au/content/industrial-networks-buses/article/the- undiscovered-country-the-future-of-industrial-automation-part-1-1214533017.
dc.relation.referencesO. A. Bascur y J. O'Rourke, Digital Transformation for the Process Industries: A roadmap, CRC Press, 2021.
dc.relation.referencesYokogawa, Digital Transformation in Process Industries: A Journey Towards Autonomous Operations, 2020.
dc.relation.referencesS. Varan Nath, A. Dunkin, M. Chowdhary y N. Patel, Industrial Digital Transformation: Accelerate digital transformation with business optimization, AI, and Industry 4.0, Mumbai: Packt, 2020.
dc.relation.referencesR. Wolf y R. Lepratti, Smart Digital Manufacturing: A guide for Digital Transformation with Real Case Studies across industries, Wiley-VCH, 2021.
dc.relation.referencesG. Schuh, R. Anderl, R. Dumitrescu, A. Krüger y M. ten Hompel, «Industrie 4.0 Maturity Index: Managing the Digital Transformation of Companies,» acatech STUDY, 2020.
dc.relation.referencesD. Ifenthaler y M. Egloffstein, «Development and Implementation of a Maturity Model of Digital Transformation,» TechTrends, vol. 64, pp. 302-309, 2019.
dc.relation.referencesSmart Industry Readiness Index, «INCIT Web Site,» Febrero 2022. [En línea]. Available: https://www3.weforum.org/docs/WEF_The_Global_Smart_Industry_Readiness_Ind ex_Initiative_2022.pdf.
dc.relation.referencesIDC Marketplace, IDC MarketScape Worldwide Industrial IoT Platforms and Applications in Manufacturing Vendor Assessment, IDC, 2021.
dc.relation.referencesGatner, Gartner Magic Quadrant for Industrial IoT Platforms, Gatner, 2020.
dc.relation.referencesFrost & Sullivan, Frost Radar: Digital Industrial Platforms, Global Industrial Automation & Process Control Research Team at Frost & Sullivan, 2022.
dc.relation.referencesForrester, The Forrester WaveTM: Industrial IoT Software Platforms - Q4 2019, 2019.
dc.relation.referencesABB ltd, «ABB Web Site,» 2018. [En línea]. Available: https://new.abb.com/process- automation/genix/abb-ability-genix-modules.
dc.relation.referencesHitachi, «Hitachi Group Global Site Web Site,» 2017. [En línea]. Available: https://www.hitachihyoron.com/rev/archive/2017/r2017_04/eC_EDGE_5/index.html.
dc.relation.referencesLitmus, «Litmus Web Site,» 2023. [En línea]. Available: https://litmus.io/blog/sneak- peak-into-whats-next-at-litmus-edge.
dc.relation.referencesPTC Thingworx, «PTC Web Site,» 2019. [En línea]. Available: https://medium.com/globant/how-do-iot-platforms-fit-in-e94d1c2eee2c.
dc.relation.referencesSiemens, «Siemens Digital Industries Software Web Site,» 2024. [En línea]. Available: https://documentation.mindsphere.io/MindSphere/concepts/concept- architecture.html.
dc.relation.referencesYokogawa, «Yokogawa Corporation of America Web Site,» Enero 2025. [En línea]. Available: https://www.yokogawa.com/us/news/press-releases/2025/2025-01-24/.
dc.relation.referencesABB ltd, «ABB Web Site,» 2019. [En línea]. Available: https://search.abb.com/library/Download.aspx?DocumentID=9AKK107780&Langua geCode=en&DocumentPartId=&Action=Launch.
dc.relation.referencesABB ltd, «ABB Web Site,» Agosto 2021. [En línea]. Available: https://search.abb.com/library/Download.aspx?DocumentID=9AKK108466A0155&L anguageCode=en&DocumentPartId=&Action=Launch.
dc.relation.referencesCognite AS, «Cognite Web Site,» 2020. [En línea]. Available: https://www.cognite.com/en/resources/customer-stories/omv-uses-data-from- cognite-data-fusion-to-reduce-inspection-time-and-deferments.
dc.relation.referencesCognite AS, «Cognite Web Site,» 2021. [En línea]. Available: https://www.cognite.com/en/resources/customer-stories/dataops-renewables- arbaflame-data-foundation.
dc.relation.referencesIIoTNext, «IIoTNet Web Site,» 2019. [En línea]. Available: https://iiotnext.com/iiotnext-serves-up-a-condition-based-maintenance-system-for- bpcl/.
dc.relation.referencesDayra, «Dayra Web Site,» 2020. [En línea]. Available: https://www.davra.com/iiot- platform.html.
dc.relation.referencesJ. Montague, «Controlglobal Web Site,» 19 Mayo 2020. [En línea]. Available: https://www.controlglobal.com/home/article/11296712/celanese-zooms-out-to-hi- level-avoids-potential-shutdown.
dc.relation.referencesGE Vernova, «GE Web Site,» 2021. [En línea]. Available: https://www.gevernova.com/software/customer-stories/total-ep-reach-zero- unanticipated-failures.
dc.relation.referencesHitachi, «Hitachi Web Site,» 31 Marzo 2022. [En línea]. Available: https://www.hitachi.com/products/it/lumada/global/en/spcon/uc_01765s/index.html.
dc.relation.referencesHoneywell Forge, «Honeywell Forge Web Site,» 2021. [En línea]. Available: https://www.honeywellforge.ai/us/en/campaigns/an-alarming-success-in-argentina.
dc.relation.referencesHoneywell Forge, «Honeywell Forge Web Site,» 2020. [En línea]. Available: https://www.honeywellforge.ai/us/en/case-studies/suncor-forthills.
dc.relation.referencesLitmus, «Litmus Web Site,» 2021. [En línea]. Available: https://litmus.io/customers/mining-company-augments-scada-with-iot-platform-to- enable-predictive.
dc.relation.referencesLitmus, «Litmus Web Site,» 2022. [En línea]. Available: https://litmus.io/customers/food-manufacturer-achieves-complete-digital- transformation-with-litmus.
dc.relation.referencesPTC, «PTC Web Site,» 2020. [En línea]. Available: https://www.ptc.com/en/case- studies/smartplant-innovation-skenergy.
dc.relation.referencesPTC, «PTC Web Site,» 2021. [En línea]. Available: https://www.ptc.com/en/case- studies/texmark-leverages-iot-ar.
dc.relation.referencesUptake Technologies Inc, «Uptake Web Site,» 2022. [En línea]. Available: https://static1.squarespace.com/static/63a1c6a2415f98749634e9ea/t/63b706feb639 631a6f5c0ceb/1672939262867/Uptake-case-studies- Chevron+%281%29+%281%29.pdf.
dc.relation.referencesF. Martínez-Plumed, L. Contreras-Ochando, C. Ferri, J. Hernández-Orallo, M. Kull, N. Lachiche, M. J. Ramírez-Quintana y P. Flach, «CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories,» IEEE Transactions on Knowledge and Data Engineering, vol. 33, no 8, pp. 3048-3061, 2021.
dc.relation.referencesS. Yadav y R. Chandra Joshi, «Trustworthy Machine Learning for Cloud-Based Internet of Things (IoT),» de Transforming Management with AI, Big-Data, and IoT , Springer, 2022, pp. 157-167.
dc.relation.referencesL. Breiman, «Random Forest,» Machine Learning, vol. 45, pp. 5-32, 2001.
dc.relation.referencesJ. H. Friedman, «Greddy Function Approximation: A Gradient Boosting Machine,» The Annals of Statistics, vol. 29, no 5, pp. 1189-1232, 2001.
dc.relation.referencesC. Cortes y V. Vapnik, «Support-Vector Networks,» Machine Learning, vol. 20, pp. 273-297, 1995.
dc.relation.referencesK. Arnold y M. Stewart, «The Production Facility,» de Surface Production Operations: Design of Oil-Handling System and Facilities, Houston, Gulf Publishing Company, 1998, pp. 1-25.
dc.relation.referencesK. Hoopes, T. C. Allison y R. Kurz, «Oil & Gas Compressor Basics,» de Compression Machinery for Oil and Gas, Elsevier, 2019, pp. 3-11.
dc.relation.referencesB. White, T. Kreuz y G. Talabisco, «Equipment Overview,» de Compression Machinery for Oil and Gas, Elsevier, 2019, pp. 13-27.
dc.relation.referencesK. Brun y R. Kurz, «Preface,» de Compressor Machinery for Oil and Gas, Elsevier, 2019, pp. xix-xx.
dc.relation.referencesK. Arnold y M. Stewart, «Choosing a Process,» de Surface Production Operations: Design of Oil-Handling Systems and Facilities, Houston, Gulf Publishing Company, 1998, pp. 26-57.
dc.relation.referencesZ. Wang, X. Wang, W. G. Duan, F. J. Li y F. Chen, «Well Production Real-Time Intelligent Monitoring Based on Convolutional Neural Network,» de Proceedings of the International Field Exploration and Development Conference, 2019.
dc.relation.referencesJ. Hollingsworth, G. Phillippi, M. Hinchliff, C. Kulhanek, A. Rimpel y F. Maywald, «Reciprocating Compressors,» de Compression Machinery of Oil and Gas, Elsevier, 2019, pp. 167-252.
dc.relation.referencesJ. Wilkes, B. Pettinato, R. Kurz, J. Hollingsworth, D. Zhang, M. Taher, C. Kulhanek, F. Werdecker, D. Büche y G. Talabisco, «Centrifugal Compressors,» de Compression Machinery for Oil and Gas, Elsevier, 2019, pp. 31-133.
dc.relation.referencesV. N. Mironov, «Some operational problems of Gas-Lift Compressor Plants with Centrifugal Compressor,» Chemical and Petroleum Engineering, vol. 34, pp. 586- 591, 1998.
dc.relation.referencesE. V. Krinitskii, S. D. Medvedev y A. G. Ovsienko, «Determination of optimal requirements for compressor reliability from standpoint of operating costs,» Chemical and Petroleum Engineering, vol. 30, pp. 98-101, 1994.
dc.relation.referencesH. Jeong, B. Oh, D. Kim, K. Lee, H. Kim, J. Kim y G. Choi, «Development of reduced order model for performance prediction of reciprocating compressor,» de 13th International Conference on Compressors and Their System, 2024.
dc.relation.referencesF. Safiyullah, S. A. Sulaiman, M. Y. Naz, M. S. Jasmani y S. M. Ghazali, «Prediction of performance degradation and maintenance of centrifugal gas compressors using genetic programming,» Enegy, vol. 158, pp. 485-494, 2018.
dc.relation.referencesO. V. Kryukov y A. V. Serebryakov, «Artificial Neural Networks of Technical State Prediction of Gas Compressor Units Electric Motors,» J. Loss Prev. Process Ind, vol. 43, pp. 148-157, 2016.
dc.relation.referencesA. N. Krasnov y M. Y. Prakhova, «Predictive State Analytics of Gas Pumping Units,» Journal of Physics: Conference Series, vol. 115, pp. 88-102, 2022.
dc.relation.referencesF. Schulze Spüntrup, J. G. Londoño, C. Skourup, N. F. Thornhill y L. Imsland, «Reliability Improvement of Compressors Based on Asset Fleet Reliability Data,» de IFAC Conference, 2018.
dc.relation.referencesY. Weichao, Z. Xianbin, H. Weihe, C. Quingwen, G. Jie, X. Jili, L. Yang, G. Jing y Y. Hong, «A Data-Driven Methodology for the Reliability Analysis of the Natural Gas Compressor Unit Considering Multiple Failure Modes,» Energies, vol. 13, no 3, 2022.
dc.relation.referencesD. Pandya, A. Srivastava, A. Doherty, S. Sundareshwar, C. Needham, A. Chaudry y S. Krishnalyer, «Increasing Production Efficiency via Compressor Failure Predictive Analytics Using Machine Learning,» de Offshore Technology, 2018.
dc.relation.referencesV. A. Vladimirov, S. V. Porshnev y I. S. Fridman, «Technological Data Analysis for Pre-Emergency Situations at Gas Compressor Units,» Automation and Remote Control, vol. 72, no 4, 2011.
dc.relation.referencesG. Akbar y A. Dhimi, «Fault Detection Model of Rotating Machinery Using Machine Learning: Case Study of Oil and Gas Company,» de 25th International Conference on Software, 2023.
dc.relation.referencesK. Brun y M. G. Nored, «Guideline for field testing of gas turbine and centrifugal compressor performance,» Gas Machinery Research Council, 2006.
dc.relation.referencesPTC, «ThingWorx IIoT Platform,» PTC, 2025. [En línea]. Available: https://www.ptc.com/en/products/thingworx.
dc.relation.referencesValerus, Compressor Package ISO View, Houston, Texas.
dc.relation.referencesJ. D. Caballero Colina, V. H. Grisales Palacio y J. D. Medina Gonzalez, «Desarrollo y prueba piloto de una solución de análisis de datos para monitoreo activo compresor en tiempo real en la industria de Oil&Gas,» de XII Congreso Internacional de Ingeniería Mecánica, Mecatrónica y Automatización, Montería, 2025.
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess
dc.rights.licenseAtribución-NoComercial-CompartirIgual 4.0 Internacional
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/
dc.subject.ddc000 - Ciencias de la computación, información y obras generales::004 - Procesamiento de datos Ciencia de los computadores
dc.subject.ddc000 - Ciencias de la computación, información y obras generales::006 - Métodos especiales de computación
dc.subject.ddc620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingeniería
dc.subject.lembAUTOMATIZACIONspa
dc.subject.lembAutomationeng
dc.subject.lembSISTEMAS DE RECOLECCION AUTOMATICA DE DATOSspa
dc.subject.lembAutomatic data collection systemseng
dc.subject.lembFABRICAS-AUTOMATIZACIONspa
dc.subject.lembFactory automationeng
dc.subject.lembCAMBIO TECNOLOGICOspa
dc.subject.lembTechnological changeeng
dc.subject.lembCONTROL AUTOMATICOspa
dc.subject.lembAutomatic controleng
dc.subject.lembADMINISTRACION DE PROYECTOS INDUSTRIALES-PROCESAMIENTO DE DATOSspa
dc.subject.lembIndustrial project management - data processingeng
dc.subject.lembANALISIS DE INFORMACIONspa
dc.subject.lembInformation analysiseng
dc.subject.proposalTransformación digital Industrialspa
dc.subject.proposalAnalítica industrial de datosspa
dc.subject.proposalMantenimiento predictivospa
dc.subject.proposalThingWorxspa
dc.subject.proposalCompresores reciprocantesspa
dc.subject.proposalOil & Gaseng
dc.subject.proposalIndustrial digital transformationeng
dc.subject.proposalIndustrial data analyticseng
dc.subject.proposalPredictive maintenanceeng
dc.subject.proposalReciprocating compressorseng
dc.titlePrueba piloto de software industrial de analítica de datos aplicado al modelado de un activo de una planta industrial colombiana de Oil and Gasspa
dc.title.translatedPilot test of industrial data analytics software applied to the modeling of an asset in a Colombian Oil and Gas planteng
dc.typeTrabajo de grado - Maestría
dc.type.coarhttp://purl.org/coar/resource_type/c_bdcc
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.contentText
dc.type.driverinfo:eu-repo/semantics/masterThesis
dc.type.redcolhttp://purl.org/redcol/resource_type/TM
dc.type.versioninfo:eu-repo/semantics/acceptedVersion
dcterms.audience.professionaldevelopmentAdministradores
dcterms.audience.professionaldevelopmentBibliotecarios
dcterms.audience.professionaldevelopmentConsejeros
dcterms.audience.professionaldevelopmentEstudiantes
dcterms.audience.professionaldevelopmentGrupos comunitarios
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2

Archivos

Bloque original

Mostrando 1 - 1 de 1
Miniatura
Nombre:
Documento final Trabajo de Grado [sin anexos].pdf
Tamaño:
8.64 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería - Automatización Industrial
Descargar

Bloque de licencias

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

Colecciones

Maestría en Ingeniería - Automatización Industrial