Predicting Burden Rock Velocity in Limestone Mines using Artificial Neural Network Models

Abstract

The prediction of burden rock velocity is crucial in optimizing the efficiency of mining and excavation operations. This study presents a novel approach utilizing Artificial Neural Networks (ANNs) to accurately predict the velocity of burden rocks based on various input parameters such as rock property, geological property and bench properties. A comprehensive dataset was collected from field measurements and laboratory experiments to train the ANN models. The performance of the ANN models such as Multi-layered Perceptron (MLP), Deep Neural Network (DNN), simple MLP and Backpropagation Neural Network (BPNN) was evaluated based on performance metrics R-squared (R)2, Mean Squared Error (MSE) and Mean Absolute Error (MAE). Among the developed ANN models, the BPNN model was found to be the most accurate predictive model for burden rock velocity, as evidenced by metrics R2(0.821), MSE (0.099) and MAE (0.226). The results indicate that the BPNN model effectively captures the complex relationships between the predictors and burden rock velocity. Advanced neural network algorithms such as recurrent neural networks and long short-term memory techniques can be used to improve the accuracy of presented neural network models. © 2025, World Researchers Associations. All rights reserved.