Heavy duty vehicle fuel consumption modeling using artificial neural networks

Oskar Wysocki, Lipika Deka, David Elizondo
2019 2019 25th International Conference on Automation and Computing (ICAC)  
In this paper an artificial neural network (ANN) approach to modelling fuel consumption of heavy duty vehicles is presented. The proposed method uses easy accessible data collected via CAN bus of the truck. As a benchmark a conventional method, which is based on polynomial regression model, is used. The fuel consumption is measured in two different tests, performed by using a unique test bench to apply the load to the engine. Firstly, a transient state test was performed, in order to evaluate
more » ... e polynomial regression and 25 ANN models with different parameters. Based on the results, the best ANN model was chosen. Then, validation test was conducted using real duty cycle loads for model comparison. The neural network model outperformed the conventional method and represents fuel consumption of the engine operating in transient states significantly better. The presented method can be applied in order to reduce fuel consumption in utility vehicles delivering accurate fuel economy model of truck engines, in particular in low engine speed and torque range.
doi:10.23919/iconac.2019.8895072 dblp:conf/iconac/WysockiDE19 fatcat:n75b245fwzhlvcnhe4h6r54qgu