Artificial Neural Network Based Predictive Real Drive Emission and Fuel Economy Simulation of Motorcycles 2018-32-0030
As the number of different engine and vehicle concepts for powered-two wheelers is very high and will even rise with hybridization, the simulation of emissions and fuel consumption is indispensable for further development towards more environmentally friendly mobility. In this work, an adaptive artificial neural network based predictive model for emission and fuel consumption simulation of motorcycles operated in real world conditions is presented. The model is developed in Matlab and Simulink and is integrated into a longitudinal vehicle dynamic simulation whereby it is possible to simulate various and not yet measured test cycles. Subsequently, it is possible to predict real drive emissions RDE and on-road fuel consumption by a minimum of previous measurement effort. The modelling approach is adaptive in terms of usability for different engine and exhaust gas treatment systems as the model does not require specific knowledge of technical vehicle parameters, which might be unknown due to manufacturers’ concealment. Backpropagation is used as supervised learning technique for training the neural networks and various learning inputs are investigated and evaluated. The paper expands on previous research of possible measurement methodologies for real drive emissions for motorcycles to minimize the effort in estimating real world effects and to serve as a tool for further improvement towards upcoming more stringent emission limits. Therefore, the applicability of the software will be shown with three examples. Moreover, tools are presented to assign emission relevant scenarios to specific driving patterns and to assess them according to the vehicles driving dynamic.
Citation: Hiesmayr, J., Schmidt, S., Hausberger, S., and Kirchberger, R., "Artificial Neural Network Based Predictive Real Drive Emission and Fuel Economy Simulation of Motorcycles," SAE Technical Paper 2018-32-0030, 2018, https://doi.org/10.4271/2018-32-0030. Download Citation
Johannes Hiesmayr, Stephan Schmidt, Stefan Hausberger, Roland Kirchberger
Graz University of Technology
SAE/JSAE Small Engine Technology Conference