Citas bibligráficas
Orellana, N., (2022). Mejora de la disponibilidad de un molino SAG basado en el diseño de un sistema de estimación del desgaste del revestimiento [Tesis, Universidad Nacional de Ingeniería]. http://hdl.handle.net/20.500.14076/23019
Orellana, N., Mejora de la disponibilidad de un molino SAG basado en el diseño de un sistema de estimación del desgaste del revestimiento [Tesis]. PE: Universidad Nacional de Ingeniería; 2022. http://hdl.handle.net/20.500.14076/23019
@misc{renati/712319,
title = "Mejora de la disponibilidad de un molino SAG basado en el diseño de un sistema de estimación del desgaste del revestimiento",
author = "Orellana Oyarce, Nestor André",
publisher = "Universidad Nacional de Ingeniería",
year = "2022"
}
The mining industry is oriented to the extraction and use of minerals and other elements present on the earth's surface. The concentrator plants have production lines that have equipment subject to different operation and production parameters. In the grinding process, the wear of the SAG mill lining is not of the linear type. The production parameters that affect this component of the SAG mill are: material hardness, material size and percentage of material type; as well as operating parameters such as: feeding tonnage, amount of incoming water flow, ball load percentage, power consumed, turning speed, among others. There is a small number of companies or consultants specialized in data analysis aimed at solving problems of predicting failures of mining equipment, such as SAG Mills, and thus improving their availability. The companies that offer these services do not provide adequate support, require an extended analysis time, do not offer results delivery time, and their costs are very high. For this reason, the present work proposes the design of a lining wear estimation system based on supervised learning algorithms of machine learning in order to improve the availability of a SAG mill in a shorter analysis time and lower costs.
Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons