Mostrar el registro sencillo del documento

dc.rights.licenseAtribución-NoComercial-SinDerivadas 4.0 Internacional
dc.contributor.advisorGómez Jaramillo, Francisco Albeiro
dc.contributor.authorPrado Gamba, Lina Fernanda
dc.date.accessioned2022-06-28T18:37:02Z
dc.date.available2022-06-28T18:37:02Z
dc.date.issued2022
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/81638
dc.descriptionilustraciones, gráficas, tablas
dc.description.abstractLa falta de información relevante para la toma de decisiones es uno de los grandes problemas a los que se enfrentan los departamentos de mantenimiento en las empresas. Esta tesis explora un método automático para aportar a la solución de este problema mediante la extracción de información relevante de los registros históricos de las actividades de mantenimiento realizadas en los equipos. Dada la naturaleza de los datos, texto no estructurado con lenguaje técnico, se plantea la implementación de diferentes representaciones (bag of words, term frequency-inverse document frequency, Fasttext y Doc2vec) para alimentar los modelos de aprendizaje de ma ́quina que realizan la estructuración de información importante contenida en los documentos. En la búsqueda del modelo con mejor rendimiento se compararon modelos de support vector machine, random forest, gaussian naive bayes y gradient boosting trees. Estos modelos se aplicaron a datos provenientes de un negocio de venta y renta de maquinaria amarilla; se consideraron 12 montacargas de 3 modelos diferentes y 4 variables independientes en las cuales se extrae información: tipología, falla encontrada, estado final y sistema. Los modelos con mejor rendimiento alcanzaron un f1-score macro 0,86, 0,8, 0,81 y 0,68 con 3 support vector machine y un gradient boosting trees. Se concluye que para obtener mejores resultados el paso a seguir es aumentar la base de datos y expandir el campo de aplicación. (Texto tomado de la fuente).
dc.description.abstractThe lack of relevant information for decision-making is one of the major problems that maintenance departments face. In this thesis, an automatic method is explored to contribute to the solution of this problem by extracting relevant information from the records that are kept of the maintenance activities carried out on the equipment. Given the nature of the data, unstructured text with technical language, the implementation of different representations (bag of words, term frequency–inverse document frequency, Fasttext and Doc2vec) is proposed for the machine learning models that carry out the structuring of relevant information contained in the documents. In the search for the best performing model, support vector machine, random forest, gaussian naive bayes and gradient boosting trees models were compared. The models were applied to data from a business of sale and rental of yellow machinery; 15 forklifts of 3 different models and four independent variables in which information is extracted were considered: typology, fault found, final state and system. The best performing models achieved f1-score macro 0,86, 0,8, 0,81 y 0,68 with 3 support vector.
dc.format.extentxii, 73 páginas
dc.format.mimetypeapplication/pdf
dc.language.isospa
dc.publisherUniversidad Nacional de Colombia
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject.ddc510 - Matemáticas::519 - Probabilidades y matemáticas aplicadas
dc.titleModelo de aprendizaje para estructurar los datos de las hojas de vida de maquinaria amarilla
dc.typeTrabajo de grado - Maestría
dc.type.driverinfo:eu-repo/semantics/masterThesis
dc.type.versioninfo:eu-repo/semantics/acceptedVersion
dc.publisher.programBogotá - Ciencias - Maestría en Ciencias - Matemática Aplicada
dc.description.notesIncluye anexos
dc.contributor.researchgroupComputational Modeling of Biological Systems Research Group - COMBIOS
dc.description.degreelevelMaestría
dc.description.degreenameMagíster en Ciencias - Matemática Aplicada
dc.description.researchareaAprendizaje de máquina
dc.description.researchareaMatemática aplicada
dc.identifier.instnameUniversidad Nacional de Colombia
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombia
dc.identifier.repourlhttps://repositorio.unal.edu.co/
dc.publisher.departmentDepartamento de Matemáticas
dc.publisher.facultyFacultad de Ciencias
dc.publisher.placeBogotá, Colombia
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotá
dc.relation.referencesAkhbardeh, F., Desell, T., and Zampieri, M. (2020a). Maintnet: A collaborative open-source library for predictive maintenance language resources. arXiv preprint arXiv:2005.12443.
dc.relation.referencesAkhbardeh, F., Desell, T., and Zampieri, M. (2020b). Nlp tools for predictive maintenance records in maintnet. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: System Demonstrations, pages 26–32.
dc.relation.referencesAlpaydin, E. (2020). Introduction to machine learning. MIT press.
dc.relation.referencesAmazon Web Services, I. (2021). What is data labe- ling? [en l ́ınea]. urlhttps://aws.amazon.com/es/sagemaker/data-labeling/what-is-data- labeling/[5 de Diciembre].
dc.relation.referencesArif-Uz-Zaman, K., Cholette, M. E., Ma, L., and Karim, A. (2017). Extracting failure time data from industrial maintenance records using text mi- ning. Advanced Engineering Informatics, 33:388–396.
dc.relation.referencesBeltrán, J. M. J. (2000). Indicadores de gestion una herramienta para lograr la competitividad.
dc.relation.referencesBishop, C. (2014). Bishop-pattern recognition and machine learning-springer 2006. Antimicrob. Agents Chemother, pages 03728–14.
dc.relation.referencesBojanowski, P., Grave, E., Joulin, A., and Mikolov, T. (2017). Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5:135–146.
dc.relation.referencesBokinsky, H., McKenzie, A., Bayoumi, A., McCaslin, R., Patterson, A., Matthews, M., Schmidley, J., and Eisner, L. (2013). Application of natural language processing techniques to marine v-22 maintenance data for populating a cbm-oriented database. In AHS Airworthiness, CBM, and HUMS Specialists’ Meeting, Huntsville, AL.
dc.relation.referencesBortolini, R. and Forcada, N. (2020). Analysis of building maintenance requests using a text mining approach: Building services evaluation. Building Research & Information, 48(2):207–217.
dc.relation.referencesBouabdallaoui, Y., Lafhaj, Z., Yim, P., Ducoulombier, L., and Bennadji, B. (2020). Natural language processing model for managing maintenance requests in buildings. Buildings, 10(9):160.
dc.relation.referencesBreiman, L. (2001). Random forests. Machine learning, 45(1):5–32.
dc.relation.referencesBrundage, M. P., Sexton, T., Hodkiewicz, M., Dima, A., and Lukens, S. (2021). Technical language processing: Unlocking maintenance knowledge. Manufacturing Letters, 27:42–46.
dc.relation.referencesButters, J. and Ciravegna, F. (2008). Using similarity metrics for terminology recognition. In LREC.
dc.relation.referencesButters, J. and Ciravegna, F. (2010). Authoring technical documents for effective retrieval. In International Conference on Knowledge Engineering and Knowledge Management, pages 287–300. Springer.
dc.relation.referencesCarvalho, T. P., Soares, F. A., Vita, R., Francisco, R. d. P., Basto, J. P., and Alcala ́, S. G. (2019). A systematic literature review of machine learning methods applied to predictive maintenance. Computers & Industrial Engineering, 137:106024.
dc.relation.referencesçınar, Z. M., Abdussalam Nuhu, A., Zeeshan, Q., Korhan, O., Asmael, M., and Safaei, B. (2020). Machine learning in predictive maintenance towards sustainable smart manufacturing in industry 4.0. Sustainability, 12(19):8211.
dc.relation.referencesAcademias de la Lengua Española y Real Academia Española, A. (2021). Diccionario de la lengua española - edición del tricentenario. [versión 23.5 en línea]. https://dle.rae.es/ [5 de Diciembre].
dc.relation.referencesde Jonge, B. and Scarf, P. A. (2020). A review on maintenance optimization. European journal of operational research, 285(3):805–824.
dc.relation.referencesDevaney, M., Ram, A., Qiu, H., and Lee, J. (2005). Preventing failures by mining maintenance logs with case-based reasoning. In Proceedings of the 59th meeting of the society for machinery failure prevention technology (MFPT-59).
dc.relation.referencesDing, S.-H. and Kamaruddin, S. (2015). Maintenance policy optimization—literature review and directions. The international journal of advanced manufacturing technology, 76(5):1263–1283.
dc.relation.referencesGhosh, S., Roy, S., and Bandyopadhyay, S. K. (2012). A tutorial review on text mining algorithms. International Journal of Advanced Research in Computer and Communication Engineering, 1(4):7.
dc.relation.referencesGrandini, M., Bagli, E., and Visani, G. (2020). Metrics for multi-class classification: an overview. arXiv preprint arXiv:2008.05756.
dc.relation.referencesGunay, H. B., Shen, W., and Yang, C. (2019). Text-mining building maintenance work orders for component fault frequency. Building Research & Information, 47(5):518–533.
dc.relation.referencesHirschberg, J. and Manning, C. D. (2015). Advances in natural language processing. Science, 349(6245):261–266.
dc.relation.referencesKohavi, R. (1998). Glossary of terms. Special issue on applications of machine learning and the knowledge discovery process, 30(271):127–132.
dc.relation.referencesKumar, U., Galar, D., Parida, A., Stenstro ̈m, C., and Berges, L. (2013). Maintenance performance metrics: a state-of-the-art review. Journal of Quality in Main- tenance Engineering.
dc.relation.referencesLe, Q. and Mikolov, T. (2014). Distributed representations of sentences and documents. In International conference on machine learning, pages 1188–1196. PMLR.
dc.relation.referencesLundgren, C., Skoogh, A., and Bokrantz, J. (2018). Quantifying the effects of maintenance–a literature review of maintenance models. Procedia CIRP, 72:1305–1310.
dc.relation.referencesLuque, C., Luna, J. M., Luque, M., and Ventura, S. (2019). An advanced review on text mining in medicine. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 9(3):e1302.
dc.relation.referencesLópez (2019). Your guide to natural language processing (nlp). [en línea]. https://towardsdatascience.com/your-guide-to-natural-languag-processing-nlp- 48ea2511f6e1 [5 de Diciembre].
dc.relation.referencesMahesh, B. (2020). Machine learning algorithms-a review. International Journal of Science and Research (IJSR).[Internet], 9:381–386.
dc.relation.referencesMárquez Vásquez, D. et al. (2011). Plan de negocios de una empresa que brinda servicios de mantenimiento predictivo en colombia. B.S. thesis, Uniandes.
dc.relation.referencesMarzec, M., Uhl, T., and Michalak, D. (2014). Verification of text mi- ning techniques accuracy when dealing with urban buses maintenance data. Diagnostyka, 15.
dc.relation.referencesMcallister (2021). Mcallister. [en l ́ınea]. https://mcallister.com.co [5 de Diciembre].
dc.relation.referencesMcKenzie, A., Matthews, M., Goodman, N., and Bayoumi, A. (2010). Information extraction from helicopter maintenance records as a springboard for the future of maintenance text analysis. In International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, pages 590–600. Sprin- ger.
dc.relation.referencesNagasaka, M., Sato, M., and Kinoshita, E. (2018). Integrated analy- sis system for elevator optimization maintenance using ontology processing and text mining. In Safety and Reliability–Safe Societies in a Changing World, pages 3093–3098. CRC Press.
dc.relation.referencesNakagawa, T. (2006). Maintenance theory of reliability. Springer Science & Business Media.
dc.relation.referencesOjala, M. and Garriga, G. C. (2010). Permutation tests for studying classifier performance. Journal of Machine Learning Research, 11(6).
dc.relation.referencesOlarte, W., Botero, M., and CANON, B. A. (2010). Análisis de vibraciones: una herramienta clave en el mantenimiento predictivo. Scientia et technica, 16(45):219–222.
dc.relation.referencesParida, A. (2006). Maintenance performance measurement system: Application of ict and e-maintenance concepts. International journal of COMADEM, 9(4):30.
dc.relation.referencesPelham, J. G. and Hockley, C. (2017). Analysis of short form maintenance records for nff using nlp, phrase matching, and bayesian learning. Procedia CIRP, 59:257–262.
dc.relation.referencesPrasertrungruang, T. and Hadikusumo, B. (2007). Heavy equipment management practices and problems in thai highway contractors. Engineering, construction and Architectural management.
dc.relation.referencesQi, P., Zhang, Y., Zhang, Y., Bolton, J., and Manning, C. D. (2020). Stanza: A python natural language processing toolkit for many human languages. arXiv preprint arXiv:2003.07082.
dc.relation.referencesSánchez Gómez, A. M. et al. (2017). Técnicas de mantenimiento predictivo: metodología de aplicación en las organizaciones.
dc.relation.referencesStenström, C., Al-Jumaili, M., and Parida, A. (2015). Natural language processing of maintenance records data. International Journal of COMADEM, 18(2):33–37.
dc.relation.referencesUbaque Castillo, Y. M., Aguirre Zabala, E. L., et al. (2019). Estructuración del programa de mantenimiento predictivo por condición para los equipos del área de producción en la empresa kellogg de colombia sa.
dc.relation.referencesSzücs, B. and Ballagi, (2020). Artificial intelligence in mainte- nance: The industrial application of natural language processing.
dc.relation.referencesUsuga Cadavid, J. P., Grabot, B., Lamouri, S., Pellerin, R., and Fortin, A. (2020). Valuing free-form text data from maintenance logs through transfer learning with camembert. Enterprise Information Systems, pages 1–29.
dc.relation.referencesWang, H., Liu, Z., Xu, Y., Wei, X., and Wang, L. (2020). Short text mining framework with specific design for operation and maintenance of power equipment. CSEE Journal of Power and Energy Systems.
dc.relation.referencesYang, C., Chen, Q., Shen, W., and Gunay, B. (2017). Toward failure mode and effect analysis for heating, ventilation and air-conditioning. In 2017 IEEE 21st International Conference on Computer Supported Cooperative Work in Design (CSCWD), pages 408–413. IEEE.
dc.relation.referencesYang, Z., Baraldi, P., and Zio, E. (2020). A novel method for maintenance record clustering and its application to a case study of maintenance optimization. Reliability Engineering & System Safety, 203:107103.
dc.relation.referencesZhang, H. (2004). The optimality of naive bayes. AA, 1(2):3.
dc.relation.referencesZhang, Y., Chen, M., and Liu, L. (2015). A review on text mining. In 2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS), pages 681–685. IEEE.
dc.relation.referencesZhao, Y., Xu, T.-h., and Hai-feng, W. (2014). Text mining based fault diagnosis of vehicle on-board equipment for high speed railway. In 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), pages 900–905. IEEE.
dc.relation.referencesUnico organismo de normalización en españa (2021). Une-en 13306:2011. [en líınea]. www.une.org[5 de Diciembre].
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess
dc.subject.lembComputational linguistics
dc.subject.lembLingüística computacional
dc.subject.lembMachine learning
dc.subject.lembAprendizaje automático (Inteligencia artificial)
dc.subject.lembMachinery
dc.subject.lembMaquinaria
dc.subject.proposalMantenimiento
dc.subject.proposalRegistros de mantenimiento
dc.subject.proposalExtraccion de información
dc.subject.proposalAprendizaje de máquina
dc.subject.proposalProcesamiento de lenguaje natural
dc.subject.proposalMaintenance
dc.subject.proposalMaintenance logs
dc.subject.proposalInformation extraction
dc.subject.proposalMachine learning
dc.subject.proposalNatural language processing.
dc.title.translatedMachine learning model to structure yellow machinery logs
dc.type.coarhttp://purl.org/coar/resource_type/c_bdcc
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.contentText
dc.type.redcolhttp://purl.org/redcol/resource_type/TM
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2
dcterms.audience.professionaldevelopmentEstudiantes
dcterms.audience.professionaldevelopmentInvestigadores


Archivos en el documento

Thumbnail

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

Mostrar el registro sencillo del documento

Atribución-NoComercial-SinDerivadas 4.0 InternacionalEsta obra está bajo licencia internacional Creative Commons Reconocimiento-NoComercial 4.0.Este documento ha sido depositado por parte de el(los) autor(es) bajo la siguiente constancia de depósito