dc.contributorVilla Garzón, Fernán Alonso
dc.creatorArenas Bustamante, Alexis Andrés
dc.date.accessioned2021-04-26T21:55:37Z
dc.date.accessioned2022-09-21T17:40:40Z
dc.date.available2021-04-26T21:55:37Z
dc.date.available2022-09-21T17:40:40Z
dc.date.created2021-04-26T21:55:37Z
dc.date.issued2021-04-05
dc.identifierhttps://repositorio.unal.edu.co/handle/unal/79417
dc.identifierUniversidad Nacional -Sede Medellín
dc.identifierRepositorio Universidad Nacional de Colombia
dc.identifierhttps://repositorio.unal.edu.co/
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/3402576
dc.description.abstractEn los sistemas de producción es importante gestionar la eficiencia general de los procesos y en igual medida hacer gestión sobre los reprocesos y rechazos que se presentan en las células productivas de tal forma que se identifiquen sus causas y se emprendan acciones que lleven a su disminución. En el presente trabajo se establece un proceso para facilitar la gestión del scrap del proceso de envasado de cosméticos partiendo de la implementación de una base de datos en SAP Business Warehouse que consolida la información de todas las variables que tienen influencia en el scrap. Adicionalmente, se hace una selección de las variables relevantes utilizando métodos de selección de características que luego son consideradas en la estimación de tres modelos de aprendizaje de máquinas que buscan determinar el scrap real de una orden de producción. Para la evaluación del desempeño de los modelos se utilizan las métricas de calidad MAE, RMSE y R2 score donde el modelo adecuado se obtiene a partir del modelo CART- Decision Tree que tiene un mejor desempeño tanto para el conjunto de entrenamiento como para el de validación.
dc.description.abstractIn production systems, it is important to manage the Overall Equipment Effectiveness and to the same extent manage the reprocesses and rejects that occur in the production cells in such a way that their causes are identified and actions are taken that lead to their reduction. In this work, a process is established to facilitate the scrap management of the cosmetic packaging process based on the implementation of a database in SAP Business Warehouse that consolidates the information on all the variables that influence scrap. In addition, a selection of the relevant variables is made using feature selection methods that are then considered in the estimation of three machine learning models that seek to determine the real waste of a production order. For the evaluation of the performance of the proposed models, the quality metrics MAE, RMSE and R2 score are used where the appropriate model is obtained from the CART-Decision Tree model that has a better performance for both the training and validation set.
dc.languagespa
dc.publisherUniversidad Nacional de Colombia
dc.publisherMedellín - Minas - Maestría en Ingeniería - Analítica
dc.publisherFacultad de Minas
dc.publisherMedellín
dc.publisherUniversidad Nacional de Colombia - Sede Medellín
dc.relationAltmann, A., Toloşi, L., Sander, O., & Lengauer, T. (2010). Permutation importance: a corrected feature importance measure. Bioinformatics, Volume 26, 1340–1347. Obtenido de https://doi.org/10.1093/bioinformatics/btq134 Bettayeb, B., Bassetto, S., & Sahnoun, M. (2014). Quality control planning to prevent excessive scrap production. Journal of Manufacturing Systems, 400-411. Biswas, P., & Sarker, B. (2008). Optimal batch quantity models for a lean production system with in-cycle rework and scrap. International Journal of Production Research. Biswas, P., & Sarker, B. (2008). Optimal batch quantity models for a lean production system with in-cycle rework and scrap. International Journal of Production Research, 6585-6610. Breiman, L. (2001). Random Forest. Obtenido de https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf Carmignani , G. (2017). Scrap value stream mapping (S-VSM): a new approach to improve the supply scrap management process. International Journal of Production Research, 3559-3576. Chen, J.-M., Lin, Y.-H., & Chen, Y.-C. (2010). Economic optimisation for an imperfect production system with rework and scrap rate. Int. J. Industrial and Systems Engineering, 92–109. Conceição, G. M., Nascimento Saldiva, P. H., & Singer, J. d. (2001). Modelos MLG e MAG para análise da associação entre poluição atmosférica e marcadores de morbi-mortalidade: uma introdução baseada em dados da cidade de São Paulo. Revista Brasileira de Epidemiología. Florian, E., Coupek, D., Caputo, D., Colledani, M., Penalva, M., Ortiz, J. A., . . . Kollegger, G. (2018). Zero Defect Manufacturing Strategies for Reduction of Scrap and Inspection Effort in Multi-Stage Production Systems. Procedia CIRP, 368–373. García, G. (2014). Sistema de predicción de ruido urbano mediante redes neuronales. Universidad de Granada, 223. Guazzelli, A. (2013). Predicciones sobre el futuro, parte 4: Ponga en marcha una solución predictiva. IBM developerWorks. Hastie, T., & Tibshirani, R. (1987). Generalized additive models: Some applications. Journal of the American Statistical Association, 371-386. Huber, S., Wiemer, H., Schneider, D., & Ihlenfeldt, S. (2019). DMME: Data mining methodology for engineering applications–a holistic extension to the CRISP-DM model. Procedia CIRP, 403-408. James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An Introduction to Statistical Learning with applications in R. Springer. Kvålseth, T. (1985). Cautionary Note about R 2. The American Statistician, 279-285. Recuperado el 29 de Diciembre de 2020, de https://www.ars.usda.gov/ARSUserFiles/80000000/SpatialWorkshop/19KramerSupplRsq.pdf Lein, Y., & Liu, H. (2003). Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution. 856–863. Obtenido de https://www.aaai.org/Papers/ICML/2003/ICML03-111.pdf Lewis, R. J. (2000). An Introduction to Classification and Decision Trees (CART) Analysis. Obtenido de https://www.researchgate.net/profile/Roger_Lewis6/publication/240719582_An_Introduction_to_Classification_and_Regression_Tree_CART_Analysis/links/0046352d3fb18f1740000000/An-Introduction-to-Classification-and-Regression-Tree-CART-Analysis.pdf Martínez Rodríguez, E. (2005). Errores frecuentes en la interpretación del coeficiente de determinación lineal. Anuario Jurídico y Económico Escuarialense. Masuch, R., Kelm, B., & Menze, B. (2009). A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinformatics. Obtenido de https://doi.org/10.1186/1471-2105-10-213 Moreno Sarmiento, E. (2008). Predicción con Series de Tiempo y Regresión. Politécnico Gran Colombiano. Murugaiah, U., Jebaraj Benjamin, S., Srikamaladevi Marathamuthu, M., & Muthaiyah, S. (2010). Scrap loss reduction using the 5‐whys analysis. International Journal of Quality & Reliability Management, 527-540. Nasir, M. (1993). Time Series Modelling and Prediction Using Neural Networks. Universiti Teknologi Mara. Navot, A., Shpigelman, L., Tishby, N., & Vaadia, E. (s.f.). Nearest Neighbor Based Feature Selection for Regression and its Application to Neural Activity. Recuperado el 26 de Diciembre de 2020, de https://papers.nips.cc/paper/2005/file/5a2756a3cb9cde852cad3c97e120b656-Paper.pdf Pandey, P., & Ahsan Akhtar Hasin , M. (1998). Lead time adjustment through scrap management, Production Planning & Control. 138-142. Pedersen, E. J., Miller, D. L., Simpson, G. L., & Ross, N. (2018). Hierarchical generalized additive models: an introduction with mgcv. Peerj. Pérez Rave, J., La Rotta, D., Madera, Y., Sánchez, K., Restrepo, G., & Rodríguez, M. (2011). Identificación y caracterización de mudas de transporte, procesos, movimientos y tiempos de espera en nueve pymes manufactureras incorporando la perspectiva del nivel operativo. Ingeniare: Revista Chilena de Ingeniería, 396-408. Rajkumar, S., Digambar, S., Dattatray, K., & Dattatray, R. (2019). Scrap Reduction Techniques. International Research Journal of Engineering and Technology (IRJET). Ravindra, K., Rattan, P., Mor, S., & Aggarwal, A. N. (2019). Generalized Additive Models: Building evidence of air pollution, climate change and human health. Environment International. Ribeiro, V., Goldschmidt, R., & Choren, R. (2009). Métodos para Previsão de Séries Temporais e suas Tendências de Desenvolvimento. Monografías en Sistemas e Computação, 1-26. Ruiz, P. (2007). La gestión de costes en Lean manufacturing. Cómo evaluar las mejoras en costes en un sistema Lean. Netbiblo, 17. Socconini, L. (2019). Lean Manufacturing. Paso a paso. Barcelona: Marge Books. Specht, D. F. (1991). A General Regression Neural Network. IEEE Transactions on Neural Networks, 2. Obtenido de https://d1wqtxts1xzle7.cloudfront.net/56278595/grnn.pdf?1523302618=&response-content-disposition=inline%3B+filename%3DA_General_Regression_Neural_Network.pdf&Expires=1609038386&Signature=F5lBPNL6xiRAYp5HNoyBz5jmW1788zaNgy01U54VJoZtsY9FznGNr-E~4nfqgS~0l2oE Velásquez, J. D., Zambrano, C., & Vélez, L. (2011). ARNN: Un paquete para la predicción de series de tiempo usando redes neuronales autorregresivas. Revista Avances en Sistemas e Informática, 177-181. Villa, F. (2010). Modelado y Predicción del Precio de la Electricidad en Mercados de Corto Plazo Liberalizados Usando Redes Cascada Correlación. Universidad Nacional de Colombia. Willmott, C. (1982). Some Comments on the Evaluation of Model Performance. Bulletin of the American Meteorological Society, 1309–1313. Recuperado el 29 de Diciembre de 2020, de www.jstor.org/stable/26222954 Wirth, R., & Hipp, J. (2000). CRISP-DM: Towards a standard process model for data mining. In Proceedings of the 4th international conference on the practical applications of knowledge discovery and data mining. Wood, S. N. (2018). Generalized Additive Models: An Introduction with R (2nd Edition). Journal of Statistical Software. Wood, S., & Wood, M. S. (2015). Package ‘mgcv’. R Package Version. 1-7. Yang, J., Yao, D., Zhan, X., & Zhan, X. (2014). Predicting Disease Risks Using Feature Selection Based on Random Forest and Support Vector Machine. Bioinformatics Research and Applications, 8492, 1-11. Zhang, G. B. (1998). Forecasting with artificial neural networks: the state of the art. International Journal of Forecasting, 35-62.
dc.rightsAtribución-NoComercial-SinDerivadas 4.0 Internacional
dc.rightshttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rightsinfo:eu-repo/semantics/openAccess
dc.titleUn modelo para la gestión del desperdicio (scrap) en el proceso de envasado de cosméticos
dc.typeTesis


Este ítem pertenece a la siguiente institución