Prediction of energy consumption in grinding using artificial neural networks to improve the distribution of fragmentation size [Predicción del consumo de energía en la molienda utilizando redes neuronales artificiales para mejorar la distribución del tamaño de la fragmentación]

Abstract

The study focuses on the prediction of energy consumption in grinding processes using artificial neural networks (ANN). The purpose was to develop a predictive model based on artificial neural networks to estimate energy consumption in grinding and improve the fragmentation size distribution, which is crucial for the efficiency of mining and metallurgical operations. Energy consumption in grinding represents a significant part of operating costs and directly influences the profitability of operations. The ANN was trained from a data set of 126 records, which were divided into 80% for training and 20 % for model testing. The results of this research highlight optimal performance of the predictive model with performance metrics such as Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE) and Correlation Coefficient (R2), with values of 0.78, 1.39, 1.18 and 0.98, respectively in the estimation of energy consumption in the grinding process. Finally, these results indicate that the ANN achieved an accurate prediction of energy consumption in the grinding process, this will allow better baking in energy optimization.