Blasted muckpile modeling in open pit mines using an artificial neural network designed by genetic algorithm

The shape of a blasted rock mass, or simply muckpile, affects the efficiency of loading machines. A muckpile is defined with two main parameters known as throw and drop, while several blasting parameters will influence the muckpile shape. This paper studies the prediction of the muckpile shape in open-pit mines by applying an artificial neural network designed by a genetic algorithm. In that regard, a genetic algorithm has been used in preparing the neural network architecture and parameters. Moreover, input variables have been reduced using the principal component analysis. Finally, the best models for predicting throw and drop determined. Analyzing the performance of the proposed models indicates their superiority in predicting the muckpile shape. As a result, the Mean Squared Error of the throw was 0.53 for the training data and 1.24 for the testing data. While for the drop, the errors were 0.45 and 0.58 for the training and testing data, respectively. Furthermore, the sensitivity analysis shows that specific-charge effects drop and throw more.