Bibliographic citations
Sanchez, D., Rivera, L. (2024). Desarrollo de un modelo de Machine Learning para la detección de anomalías en Chancadores Primarios en la etapa de Chancado de extracción de cobre [Trabajo de suficiencia profesional, Universidad Peruana de Ciencias Aplicadas (UPC)]. http://hdl.handle.net/10757/674503
Sanchez, D., Rivera, L. Desarrollo de un modelo de Machine Learning para la detección de anomalías en Chancadores Primarios en la etapa de Chancado de extracción de cobre [Trabajo de suficiencia profesional]. PE: Universidad Peruana de Ciencias Aplicadas (UPC); 2024. http://hdl.handle.net/10757/674503
@misc{renati/419139,
title = "Desarrollo de un modelo de Machine Learning para la detección de anomalías en Chancadores Primarios en la etapa de Chancado de extracción de cobre",
author = "Rivera Vasquez, Luis Emerson",
publisher = "Universidad Peruana de Ciencias Aplicadas (UPC)",
year = "2024"
}
In the demanding workflows of mining operations, ensuring operational efficiency, and minimizing unplanned interruptions is of vital importance. In response to this need, it has become essential to adopt advanced technologies, where machine learning plays a crucial role in ensuring the reliability of critical equipment. In this context, a machine learning model based on an 'Autoencoder' neural network has been developed for early detection of anomalies in primary crushers, key equipment in the mining process. This technical work details the application of advanced machine learning techniques to strengthen fault detection and prevention, highlighting the construction and operation of this neural network model, as well as its impact on mining operations. This specific project involves the development of an early anomaly detection model for critical equipment in mining operations, such as primary crushers. After several working sessions with experts in equipment operation and maintenance, the model was validated, enabling timely monitoring and planning of anomalies to prevent unplanned downtimes. This approach has been successfully implemented in a copper mine, enabling monitoring of anomalies in the primary crusher and proactive maintenance planning based on the condition of these quantified anomalies. This project demonstrates how the effective application of machine learning can improve the reliability of critical equipment in mining operations, offering a replicable and adaptable model for other areas of the industry.
This item is licensed under a Creative Commons License