Bibliographic citations
Polo, J., (2024). Modelo predictivo de costo unitario mediante machine learning para optimizar parámetros de acarreo de mineral en una mina subterránea, Pataz [Universidad Nacional de Trujillo]. https://hdl.handle.net/20.500.14414/22303
Polo, J., Modelo predictivo de costo unitario mediante machine learning para optimizar parámetros de acarreo de mineral en una mina subterránea, Pataz []. PE: Universidad Nacional de Trujillo; 2024. https://hdl.handle.net/20.500.14414/22303
@misc{renati/882742,
title = "Modelo predictivo de costo unitario mediante machine learning para optimizar parámetros de acarreo de mineral en una mina subterránea, Pataz",
author = "Polo Salinas, Junior",
publisher = "Universidad Nacional de Trujillo",
year = "2024"
}
The objective of this research was to apply a unit cost predictive model using machine learning techniques to optimize the haulage parameters of mineral in an underground mine in Pataz in 2024. The methodology employed was a non-experimental, cross-sectional descriptive design with an applicative focus. Seven mathematical machine learning models were used. The validation of instruments was conducted using the Holti coefficient (0.83), indicating very good reliability. The hypothesis test was performed using the T-test, which yielded a statistical significance of less than 0.01 (p<0.01), accepting the research hypothesis (alternate). The results indicated that total fuel consumption and total fuel cost had the highest correlation with the unit cost, with values of 0.83 and 0.85, respectively. Among the seven models used, XGBoost was the most accurate with an R² of 0.99, followed by Random Forest and Decision Tree with R² values of 0.97 and 0.96, respectively. Conversely, the models with the lowest accuracy were Bayesian Regression and Support Vector Regression with R² values of 0.88 and 0.80, respectively. Ten scenarios were created with variations in the different operational parameters that influence unit haulage cost, with the lowest cost being scenario 2, which had a value of 21.15 USD/h. It was concluded that a lower unit cost of haulage can be achieved by reducing fuel consumption, mechanical and pneumatic maintenance hours, maintaining haulage speed, and increasing the number of trips.
This item is licensed under a Creative Commons License