Prediction of Ore Production in a Limestone Underground Mine by Combining Machine Learning and Discrete Event Simulation Techniques

Abstract

This study proposes a novel approach for enhancing the productivity of mining haulage systems by developing a hybrid model that combines machine learning (ML) and discrete event simulation (DES) techniques to predict ore production. This study utilized time data collected from a limestone underground mine using tablet computers and Bluetooth beacons for 15 weeks. The collected data were used to train an ML model to predict truck cycle time, and the support vector regression with particle swarm optimization (PSO–SVM) model demonstrated the best performance. The PSO–SVM model accurately predicted cycle time with a mean absolute error (MAE) of 2.79 min, mean squared error (MSE) of 14.29 min2, root mean square error (RMSE) of 3.79 min, and coefficient of determination (R2) of 0.68. The output of the ML model was linked to the DES model to predict ore production for each truck, section, and time period. Verification of the DES model demonstrated its ability to accurately simulate the haulage system in the study area by comparing production logs with the simulation results. This study’s novel approach offers a new method for predicting ore production and determining the optimal equipment combination for each workplace, thus enhancing productivity in mining haulage systems.