Modelo de mantenimiento predictivo basado en machine learning y datos telemáticos para optimización logística en el servicio posventa de vehículos pesados

dc.contributor.advisorGuevara Carazas, Fernando Jesus
dc.contributor.authorUrrea Pérez, Julián
dc.contributor.orcidGuevara Carazas, Fernando Jesús [0000000185294383]
dc.contributor.researchgroupGestión, Operación y Mantenimiento de Activos - Gomac
dc.date.accessioned2025-11-25T17:04:54Z
dc.date.available2025-11-25T17:04:54Z
dc.date.issued2025-11-19
dc.description.abstractEn Colombia, donde alrededor del 80 % de la carga se moviliza mediante vehículos pesados, garantizar su disponibilidad y confiabilidad es esencial para la eficiencia logística. No obstante, los concesionarios encargados de la posventa enfrentan desafíos operativos debido a retrasos en las intervenciones de mantenimiento, causados por la baja disponibilidad de repuestos, la escasez de personal técnico calificado y la limitada capacidad instalada en talleres. Este estudio propone un modelo de mantenimiento predictivo basado en técnicas de aprendizaje automático y datos telemáticos, con el objetivo de detectar fallas en componentes críticos y optimizar la planificación de recursos. Se analizó una flota de 117 vehículos bajo un esquema de gestión de flotas de una comercializadora de vehículos pesados, identificando al sensor de nivel de Fluido de Escape Diésel como uno de los componentes con mayor recurrencia de fallas. Se utilizaron registros históricos de mantenimiento y datos telemáticos segmentados en intervalos de 15 minutos para entrenar y evaluar tres modelos de clasificación: Árbol de Clasificación, Random Forest y Gradient Boosting. Este último obtuvo el mejor desempeño (exactitud: 99,97%; sensibilidad: 99,40%; AUC: 0,9997). A partir de este resultado, se diseñó un sistema predictivo capaz de procesar datos en tiempo real, emitir alertas tempranas y coordinar la logística de repuestos e intervención técnica. Esta estrategia reduce los tiempos de inactividad, mitiga daños colaterales y mejora la eficiencia operativa de los talleres, impactando positivamente la satisfacción del cliente y el cumplimiento normativo. La metodología es escalable y replicable en otros componentes o flotas, representando una herramienta estratégica para la transformación digital del servicio posventa. (Texto tomado de la fuente)spa
dc.description.abstractIn Colombia, where approximately 80% of freight is transported by heavy-duty vehicles, ensuring their availability and reliability is critical for logistics efficiency. However, dealerships responsible for after-sales service face operational challenges due to delays in maintenance interventions, primarily driven by limited spare parts availability, shortages of qualified technicians, and restricted workshop capacity. This study proposes a predictive maintenance model that leverages machine learning techniques and telematics data to detect failures in critical components and optimize resource planning. A fleet of 117 vehicles managed by a heavy-duty vehicle distributor under a centralized fleet management scheme was analyzed, identifying the Diesel Exhaust Fluid level sensor as one of the most failure-prone components. Historical maintenance records and telematics data were segmented into 15-minute intervals and used to train and evaluate three classification models: Classification Tree, Random Forest, and Gradient Boosting. The latter achieved the best performance (accuracy: 99.97%; sensitivity: 99.40%; AUC: 0.9997). Based on this, a predictive system was developed to process real-time vehicle data, trigger early alerts, and support proactive coordination of part supply and technician availability. This approach reduces downtime, repair costs, and collateral damage to surrounding systems, while enhancing workshop efficiency and customer satisfaction. Additionally, it supports compliance with emission standards by preventing unnoticed sensor failures. The proposed methodology is scalable, adaptable to other components, and replicable across multiple fleets, positioning itself as a strategic tool for the digital transformation of after-sales service logistics in the heavy-duty vehicle sector.eng
dc.description.curricularareaIngeniería Mecánica.Sede Medellín
dc.description.degreelevelMaestría
dc.description.degreenameMagister en Ingeniería Mecánica
dc.format.extent1 recurso en línea (109 páginas)
dc.format.mimetypeapplication/pdf
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.repoRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/89147
dc.language.isospa
dc.publisherUniversidad Nacional de Colombia
dc.publisher.branchUniversidad Nacional de Colombia - Sede Medellín
dc.publisher.facultyFacultad de Minas
dc.publisher.placeMedellín, Colombia
dc.publisher.programMedellín - Minas - Maestría en Ingeniería Mecánica
dc.relation.referencesAmat, J. (2017, February). Árboles de decisión, random forest, gradient boosting y C5.0. https://cienciadedatos.net/documentos/33_arboles_de_prediccion_bagging_random_forest_boosting#
dc.relation.referencesAsmai, S. A., Hussin, B., & Mohd Yusof, M. (2010). A framework of an intelligent maintenance prognosis tool. 2nd International Conference on Computer Research and Development, ICCRD 2010, 241–245. https://doi.org/10.1109/ICCRD.2010.69
dc.relation.referencesBalinado, J. R., Prasetyo, Y., Young, M., Persada, S., Miraja, B., & Redi, A. A. N. P. (2021). The Effect of Service Quality on Customer Satisfaction in an Automotive After-Sales Service. Journal of Open Innovation: Technology, Market, and Complexity, 7, 116. https://doi.org/10.3390/joitmc7020116
dc.relation.referencesCangas Ortega, H. E. (2021). Gestión del mantenimiento vehicular a base del aprendizaje autónomo en motores de tractores agrícolas [Tesis de pregrado]. Universidad Técnica del Norte.
dc.relation.referencesChen, C., Liu, Y., Wang, S., Sun, X., Di Cairano-Gilfedder, C., Titmus, S., & Syntetos, A. A. (2020). Predictive maintenance using cox proportional hazard deep learning. Advanced Engineering Informatics, 44, 101054. https://doi.org/https://doi.org/10.1016/j.aei.2020.101054
dc.relation.referencesCrespo Márquez, A. (2007). The Maintenance Management Framework: Models and Methods for Complex Systems Maintenance. Springer London. https://books.google.com.co/books?id=L-rA9yccgpEC
dc.relation.referencesDhillon, B. S. (2006). Maintainability, maintenance, and reliability for engineers. CRC/Taylor & Francis. https://doi.org/https://doi.org/10.1201/9781420006780
dc.relation.referencesDong, M., & He, D. (2007). Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis. European Journal of Operational Research, 178(3), 858–878. https://doi.org/https://doi.org/10.1016/j.ejor.2006.01.041
dc.relation.referencesDuan, Y., Edwards, J. S., & Dwivedi, Y. K. (2019). Artificial intelligence for decision making in the era of Big Data – evolution, challenges and research agenda. International Journal of Information Management, 48, 63–71. https://doi.org/https://doi.org/10.1016/j.ijinfomgt.2019.01.021
dc.relation.referencesFan, Y., Nowaczyk, S., & Rögnvaldsson, T. (2015). Evaluation of Self-Organized Approach for Predicting Compressor Faults in a City Bus Fleet. Procedia Computer Science, 53, 447–456. https://doi.org/https://doi.org/10.1016/j.procs.2015.07.322
dc.relation.referencesFathulloh, M., & Purnama, N. (2024). Assessing Customer Satisfaction in Automotive After-sales Service: A SERVQUAL Analysis. Asian Journal of Economics, Business and Accounting, 24, 98–110. https://doi.org/10.9734/ajeba/2024/v24i91479
dc.relation.referencesGoodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
dc.relation.referencesHarris, L. (2024). Customer-Centric Data Strategies: Enhancing Automotive After-Sales Services.
dc.relation.referencesHosseini, S. A., Fathi, A., Shafaat, A., & Niknam, M. (2023). A computationally inexpensive method to outsource facility maintenance services through the internet in real-time. Journal of Building Engineering, 76, 107424. https://doi.org/https://doi.org/10.1016/j.jobe.2023.107424
dc.relation.referencesIndustrial Internet Consortium (IIC). (2019). The Industrial Internet of Things Volume G1: Reference Architecture. Industrial Internet Consortium. https://www.iiconsortium.org
dc.relation.referencesInternational Organization for Standardization. (2003). ISO 13374: Condition monitoring and diagnostics of machines — Data processing, communication and presentation. ISO.
dc.relation.referencesInternational Organization for Standardization. (2014). ISO 55000: Asset management — Overview, principles and terminology. ISO.
dc.relation.referencesInternational Organization for Standarization. (2016). ISO 14224:2016 Petroleum, petrochemical and natural gas industries — Collection and exchange of reliability and maintenance data for equipment. ISO.
dc.relation.referencesJardine, A. K. S., Lin, D., & Banjevic, D. (2006). A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing, 20(7), 1483–1510. https://doi.org/https://doi.org/10.1016/j.ymssp.2005.09.012
dc.relation.referencesKaplan, A., & Haenlein, M. (2019). Siri, Siri, in my hand: Who’s the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence. Business Horizons, 62(1), 15–25. https://doi.org/https://doi.org/10.1016/j.bushor.2018.08.004
dc.relation.referencesKilleen, P., Ding, B., Kiringa, I., & Yeap, T. (2019). IoT-based predictive maintenance for fleet management. Procedia Computer Science, 151, 607–613. https://doi.org/https://doi.org/10.1016/j.procs.2019.04.184
dc.relation.referencesKumar, U., Galar, D., Parida, A., Stenström, C., & Berges, L. (2013). Maintenance performance metrics: A state-of-the-art review. In Journal of Quality in Maintenance Engineering (Vol. 19, Issue 3, pp. 233–277). https://doi.org/10.1108/JQME-05-2013-0029
dc.relation.referencesKushiro, N., Oniduka, Y., & Sakurai, Y. (2017). Initial Practice of Telematics-Based Prognostics for Commercial Vehicles: Analysis Tool for Building Faults Progress Model for Trucks on Telematics Data. Procedia Computer Science, 112, 2155–2164. https://doi.org/10.1016/j.procs.2017.08.244
dc.relation.referencesLast, M., Sinaiski, A., & Siva SUBRAMANIA, H. (2011). Condition-based Maintenance with Multi-Target Classification Models. In New Generation Computing (Vol. 29). Ohmsha, Ltd. and Springer.
dc.relation.referencesLee, J., Ni, J., Djurdjanovic, D., Qiu, H., & Liao, H. (2006). Intelligent prognostics tools and e-maintenance. Computers in Industry, 57(6), 476–489. https://doi.org/https://doi.org/10.1016/j.compind.2006.02.014
dc.relation.referencesLee, J., Qiu, H., Ni, J., & Djurdjanovic, D. (2004). Infotronics Technologies and Predictive Tools for Next-Generation Maintenance Systems. IFAC Proceedings Volumes, 37(4), 291–302. https://doi.org/https://doi.org/10.1016/S1474-6670(17)36133-5
dc.relation.referencesLee, J., Wu, F., Zhao, W., Ghaffari, M., Liao, L., & Siegel, D. (2014). Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications. Mechanical Systems and Signal Processing, 42, 314–334. https://doi.org/10.1016/j.ymssp.2013.06.004
dc.relation.referencesLoyola-González, O. (2019). Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View. IEEE Access, 7, 154096–154113. https://doi.org/10.1109/ACCESS.2019.2949286
dc.relation.referencesLozada, J., Cruz, S., Lara, O., Macías, D., & Mañay, E. (2025). Desarrollo de un sistema de telemetría para la supervisión de parámetros operativos en un Go Kart homologado por la CIK-FIA. Ciencia Latina Revista Científica Multidisciplinar, 9, 11328–11343. https://doi.org/10.37811/cl_rcm.v9i1.16702
dc.relation.referencesMachinery Information Management Open System Alliance (MIMOSA). (2001). OSA-CBM: Open System Architecture for Condition-Based Maintenance. MIMOSA. https://www.mimosa.org
dc.relation.referencesMasaquiza, J., Mora, L., & Mancheno, M. (2023). Calidad del servicio y satisfacción del cliente. El caso del mantenimiento vehicular liviano. Religación. Revista de Ciencias Sociales y Humanidades, 8, e2301019. https://doi.org/10.46652/rgn.v8i35.1019
dc.relation.referencesMejías Acosta, A., Godoy Durán, E., & Piña Padilla, R. (2018). Impacto de la calidad de los servicios sobre la satisfacción de los clientes en una empresa de mantenimiento. Revista Científica Compendium, 21(40). https://revistas.uclave.org/index.php/Compendium/article/view/1656
dc.relation.referencesMesgarpour, M., Landa-Silva, D., & Dickinson, I. (2013). Overview of Telematics-Based Prognostics and Health Management Systems for Commercial Vehicles. In CCIS (Vol. 395).
dc.relation.referencesMinisterio de Transporte. (2004). Resolución 4100 de 2004, por la cual se establecen pesos y dimensiones de los vehículos de carga en Colombia. In Diario Oficial No. 45.764.
dc.relation.referencesMitchell, T. (1997). Machine Learning. McGraw-Hill.
dc.relation.referencesMohri, M., Rostamizadeh, A., & Talwalkar, A. (2018). Foundations of Machine Learning (2nd ed.). The MIT Press.
dc.relation.referencesMondragón, G. C. (2009). Development and characterization of NOx-reductive catalytic coating systems for lean-burn engines.
dc.relation.referencesMoubray, J. (1997). Reliability-centered Maintenance. Industrial Press.
dc.relation.referencesOliveira, M. F. B. G., & Lüders, R. (2016). Combining Multiple Diagnostic Trouble Codes into a Single Decision Tree. IFAC-PapersOnLine, 49(11), 555–561. https://doi.org/https://doi.org/10.1016/j.ifacol.2016.08.081
dc.relation.referencesPanda, C., & Singh, T. R. (2023). ML-based vehicle downtime reduction: A case of air compressor failure detection. Engineering Applications of Artificial Intelligence, 122. https://doi.org/10.1016/j.engappai.2023.106031
dc.relation.referencesPatiño, C. E., & Guevara Carazas, F. J. (2019). Maintenance and Asset Life Cycle for Reliability Systems. In Reliability and Maintenance-An Overview of Cases. https://doi.org/10.5772/intechopen.85845
dc.relation.referencesPrapas, I., Derakhshan, B., Mahdiraji, A. R., & Markl, V. (2021). Continuous Training and Deployment of Deep Learning Models. Datenbank-Spektrum, 21(3), 203–212. https://doi.org/10.1007/s13222-021-00386-8
dc.relation.referencesRögnvaldsson, T., Nowaczyk, S., Byttner, S., Prytz, R., & Svensson, M. (2018). Self-monitoring for maintenance of vehicle fleets. Data Mining and Knowledge Discovery, 32(2), 344–384. https://doi.org/10.1007/s10618-017-0538-6
dc.relation.referencesRussell, S., & Norvig, P. (2021). Artificial Intelligence: A Modern Approach (4th ed.). Pearson.
dc.relation.referencesSchwabacher, M. (2005). A Survey of Data Driven Prognostics. 2. https://doi.org/10.2514/6.2005-7002
dc.relation.referencesShafi, U., Safi, A., Shahid, A. R., Ziauddin, S., & Saleem, M. Q. (2018). Vehicle Remote Health Monitoring and Prognostic Maintenance System. Journal of Advanced Transportation, 2018, 8061514. https://doi.org/10.1155/2018/8061514
dc.relation.referencesSoltani, S., Sobhani, F., & Najafi, E. (2021). Determining the increased numerical value of customer satisfaction, which has been impacted by latent and observed factors in after-sales service in the automotive industry, based on System Dynamics Method. (A Case study in car manufacturer). Journal of Engineering Research. https://doi.org/10.36909/jer.12121
dc.relation.referencesSutton, R., & Barto, A. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.
dc.relation.referencesTechnical Association of the Pulp and Paper Industry. (2008). ANSI TAPPI TIP 0305-34: Checklists for preventive maintenance. TAPPI Press.
dc.relation.referencesTran, V. T., Yang, B.-S., Oh, M.-S., & Tan, A. C. C. (2008). Machine condition prognosis based on regression trees and one-step-ahead prediction. Mechanical Systems and Signal Processing, 22(5), 1179–1193. https://doi.org/https://doi.org/10.1016/j.ymssp.2007.11.012
dc.relation.referencesWang, W. (2007). A two-stage prognosis model in condition based maintenance. European Journal of Operational Research, 182(3), 1177–1187. https://doi.org/https://doi.org/10.1016/j.ejor.2006.08.047
dc.relation.referencesYapa, S., & Fernando, R. (2023). An Assessment of Service Quality in the Automobile Service Industry: A Study of a Developing Country. Proceedings on Engineering Sciences, 5, 85–96. https://doi.org/10.24874/PES05.01.008
dc.relation.referencesYilmaz, V., & Sürmeli̇oğlu, Y. (2025). Measuring automobile service quality with the European customer satisfaction index model (ECSI): the moderating effect of trust. The TQM Journal, 37(4), 1176–1200. https://doi.org/10.1108/TQM-10-2023-0315
dc.relation.referencesZygiaris, S., Hameed, Z., Ayidh Alsubaie, M., & Ur Rehman, S. (2022). Service Quality and Customer Satisfaction in the Post Pandemic World: A Study of Saudi Auto Care Industry. Frontiers in Psychology, Volume 13-2022. https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2022.842141
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.ddc620 - Ingeniería y operaciones afines::621 - Física aplicada
dc.subject.lembAutomoviles - Mantenimiento y reparación
dc.subject.lembTelamática
dc.subject.proposalMantenimiento predictivospa
dc.subject.proposalAprendizaje automáticospa
dc.subject.proposalTelemáticaspa
dc.subject.proposalOptimización servicio posventaspa
dc.subject.proposalVehículos pesadosspa
dc.subject.proposalPredictive maintenanceeng
dc.subject.proposalMachine learningeng
dc.subject.proposalTelematicseng
dc.subject.proposalAfter-sales service optimizationeng
dc.subject.proposalHeavy-duty vehicleseng
dc.subject.wikidataMantenimiento predictivo
dc.subject.wikidataAprendizaje automático (Inteligencia artificial)
dc.titleModelo de mantenimiento predictivo basado en machine learning y datos telemáticos para optimización logística en el servicio posventa de vehículos pesadosspa
dc.title.translatedPredictive maintenance model based on machine learning and telematic data for logistics optimization in the after-sales service of heavy-duty vehicleseng
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
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
Trabajo Final MSc_Julian Urrea.pdf
Tamaño:
2.14 MB
Formato:
Adobe Portable Document Format

Bloque de licencias

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