Development of a Multi-layer Perceptron Artificial Neural Network Model to Determine Haul Trucks Energy Consumption

Organisation: Anglo American – The University of Queensland
Start and Estimated Duration: From 10 – December – 2012 To 07 – June – 2013

Summary: Diesel fuel is a significant source of energy in surface mining operations. Haul trucks are the primary users of this energy resource. Based on the analysis of the data collected from mine sites, Gross Vehicle Weight (GVW), Truck Speed (S) and Total Resistance (TR) were identified to be the most influential parameters affecting the fuel consumption. The relationship between the three parameters mentioned above and the truck fuel consumption is complicated. Thus, the development of a new approach using an artificial intelligence method was essential to create a reliable model for solving this problem. In this project, an Artificial Neural Network (ANN) model was developed to predict the fuel consumption of haul trucks in surface mines. It was found that the configuration of 3 input variables, 15 hidden cells and one output for the synthesised ANN model provided excellent results. The sensitivity analysis showed that all the three input variables (GVW, S and TR) have a noticeable effect on the truck fuel consumption.