Evaluación de estrategias de agrupamiento no supervisadas en la determinación de patrones asociados a fallas de sistemas térmicos en tractocamiones graneleros

dc.contributor.advisorBranch Bedoya, John William
dc.contributor.advisorRestrepo Martínez, Alejandro
dc.contributor.authorZapata Rincón, Andrés Mauricio
dc.contributor.refereeJuan David Ospina Arango
dc.contributor.researchgroupGrupo de Promoción E Investigación en Mecánica Aplicada Gpimaspa
dc.contributor.researchgroupGidia: Grupo de Investigación YyDesarrollo en Inteligencia Artificialspa
dc.date.accessioned2022-06-02T14:02:10Z
dc.date.available2022-06-02T14:02:10Z
dc.date.issued2022-02-28
dc.descriptionilustraciones, diagramas, gráficas, tablasspa
dc.description.abstractEsta tesis tiene como finalidad evaluar estrategias de agrupamiento no supervisadas para datos asociados a tractocamiones graneleros, en la detección de patrones de falla en sistemas térmicos. El estudio de estas técnicas es importante en el ámbito del mantenimiento predictivo basado en datos con la implementación de algoritmos de aprendizaje de máquinas que permitan planificar adecuadamente cronogramas de mantenimiento en empresas de transporte de carga. Para el desarrollo de la tesis, se usa como fuente de información los dispositivos de telemetría de los tractocamiones graneleros de una empresa colombiana de transporte de carga que reportan datos en tiempo real de la medición de variables como velocidad, temperaturas, estado de operación del vehículo, entre otras para el año 2020. También se usa el histórico de ingresos a taller de la flota de 116 tractocamiones donde se analizan los ingresos a taller para la intervención de sistemas térmicos. Estos datos son el insumo para la evaluación de las estrategias de agrupamiento propuestas en este trabajo. Los resultados parten desde la obtención de los datos, preparación de estos y análisis descriptivos para implementar técnicas de reducción de dimensionalidad en la información y posteriormente evaluar el comportamiento de algoritmos de agrupamiento para la detección de patrones de falla que se relacionen a daños en sistemas térmicos de los vehículos. Con el desarrollo de este trabajo se encuentra un potencial para el ahorro en costos correctivos de la flota en taller que apunte a una adecuada gestión de la flota en modelos de pago por uso, apalancando la disponibilidad de los vehículos en las operaciones de transporte. (Texto tomado de la fuente)spa
dc.description.abstractThe purpose of this thesis is to evaluate unsupervised clustering strategies for data associated with bulk carrier trucks, in the detection of failure patterns in thermal systems. The study of these techniques is important in the field of data-based predictive maintenance with the implementation of machine learning algorithms that allow proper planning of maintenance schedules in freight transport companies. For the development of the thesis, the telemetry devices of the bulk tractor trucks of a Colombian cargo transport company are used as a source of information, which report data in real time of the measurement of variables such as speed, temperatures, state of operation of the vehicle, among others for the year 2020. The history of workshop entries of the fleet of 116 tractor-trailers is also used, where workshop entries for the intervention of thermal systems are analyzed. These data are the input for the evaluation of the grouping strategies proposed in this work. The results start from obtaining the data, preparing them and descriptive analysis to implement dimensionality reduction techniques in the information and subsequently evaluate the behavior of grouping algorithms for the detection of failure patterns that are related to damage in thermal systems. With the development of this work, there is a potential for savings in corrective costs of the fleet in the workshop that points to an adequate management of the fleet in pay-per-use models, leveraging the availability of vehicles in transport operations.eng
dc.description.curricularareaÁrea Curricular de Ingeniería de Sistemas e Informáticaspa
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagister en Ingeniería - Analíticaspa
dc.description.researchareaMantenimiento predictivospa
dc.description.researchareaAnálisis de datosspa
dc.format.extentxvii, 112 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/81488
dc.language.isospaspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Medellínspa
dc.publisher.departmentDepartamento de la Computación y la Decisiónspa
dc.publisher.facultyFacultad de Minasspa
dc.publisher.placeMedellín, Colombiaspa
dc.publisher.programMedellín - Minas - Maestría en Ingeniería - Analíticaspa
dc.relation.referencesAllaoui, M., Kherfi, M. L., & Cheriet, A. (2020). Considerably improving clustering algorithms using UMAP dimensionality reduction technique: A comparative study. En Lecture Notes in Computer Science (pp. 317–325). Springer International Publishing.spa
dc.relation.referencesAmruthnath, N., & Gupta, T. (2019). Fault diagnosis using clustering. What statistical test to use for hypothesis testing? Machine Learning and Applications An International Journal, 6(1), 17–33. https://doi.org/10.5121/mlaij.2019.6102spa
dc.relation.referencesBangui, H., Ge, M., & Buhnova, B. (2018). Exploring big data clustering algorithms for internet of things applications. Proceedings of the 3rd International Conference on Internet of Things, Big Data and Security.spa
dc.relation.referencesBendechache, M., Kechadi, M.-T., & Le-Khac, N.-A. (2016). Efficient large scale clustering based on data partitioning. 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA).spa
dc.relation.referencesBraga, P. H. M., & Bassani, H. F. (2018). A semi-supervised self-organizing map for clustering and classification. 2018 International Joint Conference on Neural Networks (IJCNN).spa
dc.relation.referencesButikofer Lagos, G. (2017). Optimización del mantenimiento preventivo de flotas en base a técnicas de clustering y aprendizaje supervisado.spa
dc.relation.referencesCar and Driver. (2019, junio 15). ¿Cómo influye la temperatura del aceite en el motor?. Recuperado de https://www.caranddriver.com/es/coches/planeta-motor/a60565/temperatura-aceite-como-influye-en-el-motor/spa
dc.relation.referencesCastellanos, G. C., & Rodríguez, J. E. R. (2011). Agrupamiento de datos de series de tiempo. Estado del arte. Revista vínculos, 8(1), 210-231.spa
dc.relation.referencesChaudhuri, A. (2018). Predictive maintenance for industrial IoT of vehicle fleets using hierarchical modified fuzzy support vector machine. En arXiv [cs.AI]. http://arxiv.org/abs/1806.09612spa
dc.relation.referencesChekkala, V. L. (2020). Predictive Maintenance for Fault Diagnosis and Failure Prognosis in Hydraulic System (Doctoral dissertation, Dublin, National College of Ireland).spa
dc.relation.referencesÇınar, Z. M., Abdussalam Nuhu, A., Zeeshan, Q., Korhan, O., Asmael, M., & Safaei, B. (2020). Machine learning in predictive maintenance towards sustainable smart manufacturing in Industry 4.0. Sustainability, 12(19), 8211. https://doi.org/10.3390/su12198211spa
dc.relation.referencesDelua, J. (12 de marzo de 2021). Supervised vs. Unsupervised Learning: What´s the Difference?. IBM. https://www.ibm.com/cloud/blog/supervised-vs-unsupervised-learningspa
dc.relation.referencesEspadoto, M., Hirata, N., & Telea, A. (2021). Self-supervised dimensionality reduction with neural networks and pseudo-labeling. Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.spa
dc.relation.referencesForest, F., Lebbah, M., Azzag, H., & Lacaille, J. (2019). Deep architectures for joint clustering and visualization with self-organizing maps. En Lecture Notes in Computer Science (pp. 105–116). Springer International Publishing.spa
dc.relation.referencesGuo, X., Liu, X., Zhu, E., & Yin, J. (2017). Deep Clustering with Convolutional Autoencoders. En Neural Information Processing (pp. 373–382). Springer International Publishing.spa
dc.relation.referencesHeidari, S., Alborzi, M., Radfar, R., Afsharkazemi, M. A., & Rajabzadeh Ghatari, A. (2019). Big data clustering with varied density based on MapReduce. Journal of Big Data, 6(1). https://doi.org/10.1186/s40537-019-0236-xspa
dc.relation.referencesIbrahim, S. K., Ahmed, A., Zeidan, M. A. E., & Ziedan, I. E. (2020). Machine learning techniques for satellite fault diagnosis. Ain Shams Engineering Journal, 11(1), 45–56. https://doi.org/10.1016/j.asej.2019.08.006spa
dc.relation.referencesKucukyilmaz, T. (2014). Parallel K-means algorithm for shared memory multiprocessors. Journal of computer and communications, 02(11), 15–23. https://doi.org/10.4236/jcc.2014.211002spa
dc.relation.referencesLacaille, J., & Come, E. (2011). Visual mining and statistics for a turbofan engine fleet. 2011 Aerospace Conference.spa
dc.relation.referencesLangone, R., Alzate, C., De Ketelaere, B., & Suykens, J. A. K. (2013). Kernel spectral clustering for predicting maintenance of industrial machines. 2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).spa
dc.relation.referencesLøkse, S., Bianchi, F. M., Salberg, A.-B., & Jenssen, R. (2017). Spectral clustering using PCKID - A probabilistic cluster kernel for incomplete data. En arXiv [stat.ML]. http://arxiv.org/abs/1702.07190spa
dc.relation.referencesMcConville, R., Santos-Rodriguez, R., Piechocki, R. J., & Craddock, I. (2021). N2D: (not too) deep clustering via clustering the local manifold of an autoencoded embedding. 2020 25th International Conference on Pattern Recognition (ICPR).spa
dc.relation.referencesMcInnes, L., Healy, J., & Melville, J. (2018). UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. En arXiv [stat.ML]. http://arxiv.org/abs/1802.03426spa
dc.relation.referencesMurakami, T. (2002). Development of Vehicle Health Monitoring System ( VHMS / WebCARE ) for Large-Sized Construction Machine. Construction, 48(150), 15–21.spa
dc.relation.referencesNowaczyk, S. S., Rognvaldsson, T., Byttner, S., Prytz, R., Nowaczyk, S. S., Rögnvaldsson, T., Thorsteinn, R., Byttner, S., Rognvaldsson, T., Byttner, S., Prytz, R., Nowaczyk, S. S., & Rögnvaldsson, T. (2013). Analysis of Truck Compressor Failures Based on Logged Vehicle Data. 9th International Conference on Data Mining, Las Vegas, Nevada, USA, July. https://www.researchgate.net/publication/256486984.spa
dc.relation.referencesPacella, M., & Papadia, G. (2020). Fault diagnosis by multisensor data: A data-driven approach based on spectral clustering and pairwise constraints. Sensors (Basel, Switzerland), 20(24), 7065. https://doi.org/10.3390/s20247065spa
dc.relation.referencesPalmqvist, A. (2016). Exploratory data analysis of Volvo trucks repair history towards modelling a trucks lifetime maintenance needs (Dissertation). Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-32244spa
dc.relation.referencesPeerXP Team. (2017, October 17). The 6 stages of data processing cycle - PeerXP team. Medium. https://medium.com/@peerxp/the-6-stages-of-data-processing-cycle-3c2927c466ffspa
dc.relation.referencesPerr-sauer, J., Duran, A., Phillips, C., Perr-sauer, J., Duran, A., & Phillips, C. (2020). Clustering Analysis of Commercial Vehicles Using Automatically Extracted Features from Time Seriesspa
dc.relation.referencesPrytz, R. (2014). Machine learning methods for vehicle predictive maintenance using off-board and on-board data. In Thesis (Vol. 9, Issue 9). www.hh.se/hupData Clustering Analysis of Commercial Vehicles Using Automatically Extracted Features from Time Series Data. January.spa
dc.relation.referencesRanasinghe, K., Kapoor, R., Gardi, A., Sabatini, R., Wickramanayake, V., & Ludovici, D. (2020). Vehicular sensor network and data analytics for a health and usage management system. Sensors (Basel, Switzerland), 20(20), 5892. https://doi.org/10.3390/s20205892spa
dc.relation.referencesSaeed, M. M., Al Aghbari, Z., & Alsharidah, M. (2020). Big data clustering techniques based on Spark: a literature review. PeerJ. Computer Science, 6(e321), e321. https://doi.org/10.7717/peerj-cs.321spa
dc.relation.referencesSarma, A., Goyal, P., Kumari, S., Wani, A., Challa, J. S., Islam, S., & Goyal, N. (2019). ΜDBSCAN: An exact scalable DBSCAN algorithm for big data exploiting spatial locality. 2019 IEEE International Conference on Cluster Computing (CLUSTER).spa
dc.relation.referencesSefidian, Amir. (18 de diciembre de 2020). How to determine Epsilon and MinPts parameters of DBSCAN clustering. http://www.sefidian.com/2020/12/18/how-to-determine-epsilon-and-minpts-parameters-of-dbscan-clustering/spa
dc.relation.referencesScikit-learn: Machine Learning in Python, Pedregosa et al., JMLR 12, pp. 2825-2830, 2011.spa
dc.relation.referencesSreedhar, C., Kasiviswanath, N., & Chenna Reddy, P. (2017). Clustering large datasets using K-means modified inter and intra clustering (KM-I2C) in Hadoop. Journal of Big Data, 4(1). https://doi.org/10.1186/s40537-017-0087-2spa
dc.relation.referencestSNE vs.UMAP: Estructura global. (2020, March 5). ICHI.PRO. https://ichi.pro/es/tsne-vs-umap-estructura-global-85213320100375spa
dc.relation.referencesUllah, S., & Kim, D.-H. (2020). Lightweight driver behavior identification model with sparse learning on in-vehicle CAN-BUS sensor data. Sensors (Basel, Switzerland), 20(18), 5030. https://doi.org/10.3390/s20185030spa
dc.relation.referencesVan der Maaten, L., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of machine learning research, 9(11).spa
dc.relation.referencesVore, S. (2016). Methods to analyze large automotive fleet-tracking datasets with application to light-and medium-duty plug-in hybrid electric vehicle work trucks (Doctoral dissertation, Colorado State University).spa
dc.relation.referencesWattenberg, et al., "How to Use t-SNE Effectively", Distill, 2016. http://doi.org/10.23915/distill.00002spa
dc.relation.referencesYang, B., Fu, X., Sidiropoulos, N. D., & Hong, M. (2017). Towards K-means-friendly spaces: Simultaneous deep learning and clustering. 34th International Conference on Machine Learning, ICML 2017, 8, 5888–5901.spa
dc.relation.referencesYen, K. S., Ravani, B., & Lasky, T. A. (2015). DOE Fleet In-Vehicle Data Acquistion System (FIDAS) Technical Support and Testing (No. CA16-2516).spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-NoComercial 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/spa
dc.subject.ddc000 - Ciencias de la computación, información y obras generales::004 - Procesamiento de datos Ciencia de los computadoresspa
dc.subject.ddc000 - Ciencias de la computación, información y obras generales::005 - Programación, programas, datos de computaciónspa
dc.subject.ddc000 - Ciencias de la computación, información y obras generales::006 - Métodos especiales de computaciónspa
dc.subject.ddc620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingenieríaspa
dc.subject.lembCamiones - Mantenimiento y reparación
dc.subject.lembCalefacción y ventilación en vehículos
dc.subject.proposalMantenimiento Predictivospa
dc.subject.proposalAprendizaje de Máquinasspa
dc.subject.proposalSistemas térmicosspa
dc.subject.proposalAgrupamiento no supervisadospa
dc.subject.proposalDetección de patronesspa
dc.subject.proposalPredictive Maintenanceeng
dc.subject.proposalMachine Learningeng
dc.subject.proposalThermal Systemseng
dc.subject.proposalUnsupervised Clusteringeng
dc.subject.proposalPattern Detectioneng
dc.titleEvaluación de estrategias de agrupamiento no supervisadas en la determinación de patrones asociados a fallas de sistemas térmicos en tractocamiones granelerosspa
dc.title.translatedEvaluation of unsupervised grouping strategies in the determination of patterns associated with failures of thermal systems in bulk truckseng
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:
1026134819.2022.pdf
Tamaño:
3.25 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería - Analítica

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: