Mesoscopic forecasting of vehicular consumption using neural networks

Accurate forecasting of vehicular consumption is a task of primary importance for several applications. Herein, a vehicular consumption prediction model is proposed, with special emphasis on robustness and reliability. Both features are enabled due to the selection of general regression neural networks (GRNNs) for the implementation of the proposed model. GRNNs are widely used among neural networks because of their capabilities for fast learning and successful convergence to the solution. In particular, the designed GRNN is responsible for approximating the nonlinearities and the specificities between the factors identified as major contributors in vehicular consumption. In order to evaluate its efficiency, a case study involving the application of the introduced model in fully electric vehicles (FEVs) is examined. The performance of the proposed model is successfully validated using real measurements collected during a data acquisition field campaign.

[1]  Hesham Rakha,et al.  The effects of route choice decisions on vehicle energy consumption and emissions , 2008 .

[2]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[3]  Jian-Da Wu,et al.  Development of a predictive system for car fuel consumption using an artificial neural network , 2011, Expert Syst. Appl..

[4]  S. J. Pachernegg,et al.  A Closer Look at the Willans-Line , 1969 .

[5]  Junichi Murata,et al.  Ecological Vehicle Control on Roads With Up-Down Slopes , 2011, IEEE Transactions on Intelligent Transportation Systems.

[6]  Imed Ben Dhaou,et al.  Fuel estimation model for ECO-driving and ECO-routing , 2011, Intelligent Vehicles Symposium.

[7]  Sedat Bayseç,et al.  Prediction of torque and specific fuel consumption of a gasoline engine by using artificial neural networks , 2010 .

[8]  Michele Scardi,et al.  Developing an empirical model of phytoplankton primary production: a neural network case study , 1999 .

[9]  Jian-Da Wu,et al.  A forecasting system for car fuel consumption using a radial basis function neural network , 2012, Expert Syst. Appl..

[10]  Bart van Arem,et al.  Eco-routing: Comparing the fuel consumption of different routes between an origin and destination using field test speed profiles and synthetic speed profiles , 2011, 2011 IEEE Forum on Integrated and Sustainable Transportation Systems.

[11]  Hesham Rakha,et al.  ESTIMATING VEHICLE FUEL CONSUMPTION AND EMISSIONS BASED ON INSTANTANEOUS SPEED AND ACCELERATION LEVELS , 2002 .

[12]  H. Christopher Frey,et al.  Evaluation of numerical models for simulation of real-world hot-stabilized fuel consumption and emissions of gasoline light-duty vehicles , 2006 .

[13]  Abdullah Uzun,et al.  A parametric study for specific fuel consumption of an intercooled diesel engine using a neural network , 2012 .

[14]  H Jianming,et al.  Traffic congestion identification based on image processing , 2012 .

[15]  Yuanyuan Song,et al.  Study on Eco-Route Planning Algorithm and Environmental Impact Assessment , 2013, J. Intell. Transp. Syst..

[16]  Russell G. Death,et al.  An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data , 2004 .

[17]  Yong-Kul Ki.  Speed-measurement model utilising embedded triple-loop sensors , 2011 .

[18]  Matthew J. Barth,et al.  Eco-Routing Navigation System Based on Multisource Historical and Real-Time Traffic Information , 2012, IEEE Transactions on Intelligent Transportation Systems.

[19]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.