Prediction of fuel consumption of haulage trucks in open pit mines

Abstract

Fuel consumption by haulage trucks is one of the costliest components in open-pit mining. Reducing fuel consumption by trucks could lead to large savings in materials handling costs. This study sought to investigate the factors that affect fuel consumption by haul trucks and to propose an algorithm for predicting fuel consumption by trucks in open-pit mines. Case Based Reasoning (CBR) methods namely case-based reasoning using forward sequential selection (CBR-FSS), traditional CBR and Naive techniques were used to predict fuel consumption using datasets from Komatsu and Caterpillar trucks operating at Orapa Mine. The results show that the CBR method can be used to predict fuel consumption by trucks in open-pit mines; the predicted values of fuel consumption using the CBR-FSS technique gave better results in terms of much lower absolute residual values on all the datasets used, gave higher standardised accuracy values and effect sizes than the other prediction techniques. Thus, the CBR-FSS can be used as a mine planning tool to predict fuel consumption using available data from the previous trips. It is recommended that mine managers use the CBR method in predicting fuel consumption by haulage trucks to reduce fuel costs and identify trucks with high fuel consumption for early maintenance work to be done on them. Finally, larger datasets from other mines with effects of weather should be used in future studies to improve the accuracy of the predictions and make the findings more applicable to all conditions in open-pit mines.