Bibliographic citations
Yato, D., Zamudio, J. (2024). Modelo de gestión de inventarios para el abastecimiento de repuestos de una flota de operaciones aplicando Machine Learning en una mina subterránea del sur del Perú [Trabajo de suficiencia profesional, Universidad Peruana de Ciencias Aplicadas (UPC)]. http://hdl.handle.net/10757/674668
Yato, D., Zamudio, J. Modelo de gestión de inventarios para el abastecimiento de repuestos de una flota de operaciones aplicando Machine Learning en una mina subterránea del sur del Perú [Trabajo de suficiencia profesional]. PE: Universidad Peruana de Ciencias Aplicadas (UPC); 2024. http://hdl.handle.net/10757/674668
@misc{renati/419401,
title = "Modelo de gestión de inventarios para el abastecimiento de repuestos de una flota de operaciones aplicando Machine Learning en una mina subterránea del sur del Perú",
author = "Zamudio Navarro, Juan Diego",
publisher = "Universidad Peruana de Ciencias Aplicadas (UPC)",
year = "2024"
}
The use of machine learning as a scientific discipline in the field of artificial intelligence applied to the field of the mining industry presents advantages such as obtaining predictions and estimates based on the electronic collection of information and the experience acquired during all processes. In this sense, the objective of this work is to provide an inventory management model with the use of machine learning as a solution for the supply of spare parts for an operations fleet in an underground mine in southern Peru. After a background investigation, it was observed that there is no machine learning model to predict the stock of fleet spare parts, there is research into new technologies for this same problem, but the proposed solution is not applied. This is due to the type of demand that these spare parts require. For this reason, information was captured in a period of time from July to December 2023, where the inventory management for the month of December of that same year is known and acts as testing data, and an attempt will be made to predict with the previous 5 months with data known as training data. Before applying any machine learning model, you must first know which data sample is going to be used. In this case, the ABC method was used to, through the accumulated percentage, know the criticality of the most important products in our scoop among all the other spare parts. After the sample is obtained, it is structured and processed online in a workspace under the Python system or IDLE, such as Colab. Once the data was normalized and statistically analyzed, we proceeded to train and test the data, to then execute its operation and know what the prediction is in the inventory management of the scoop spare parts.
This item is licensed under a Creative Commons License