@inproceedings{35d129ea83d341b5a4b46cf7b8e8bb1d,
title = "Driving cycle and road grade on-board predictions for the optimal energy management in EV-PHEVs",
abstract = "The prediction of the driving cycle (vehicle speed profile versus time) and the road grade cycle (road grade profile versus time) can improve a variety of vehicle functions, especially the energy management of HEVs and PHEVs. The variability of the driving conditions (environment) together with the nonlinear and variable driver behaviour (driving style) makes the driving cycle 'on-board & real-time' prediction a highly complex task. This paper proposes an intelligent technique for the real time prediction of the vehicle speed and road grade profiles for the (selected) time horizon whilst the vehicle is in route. The proposed method uses an Artificial Neural Network which processes both the vehicle speed measurement (current and previous data samples) and some information related to the driving conditions present in the route, which could be obtained in advance from the new generation of vehicle navigation systems. The driving cycle and road grade on-board predictions allow the energy management system of HEV/PHEVs to achieve further reductions of fuel consumptions.",
keywords = "Driving Cycle, NARX Network, Neural Network, Optimal Energy Management, Predictive Control",
author = "Valera, {J. J.} and B. Heriz and G. Lux and J. Caus and B. Bader",
note = "Publisher Copyright: {\textcopyright} 2013 IEEE.; 27th World Electric Vehicle Symposium and Exhibition, EVS 2014 ; Conference date: 17-11-2013 Through 20-11-2013",
year = "2014",
month = oct,
day = "1",
doi = "10.1109/EVS.2013.6914763",
language = "English",
series = "2013 World Electric Vehicle Symposium and Exhibition, EVS 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2013 World Electric Vehicle Symposium and Exhibition, EVS 2014",
address = "United States",
}
