Prediction of vehicle velocity for model predictive control
Document Type
Conference Proceeding
Publication Date
2015
Department
Department of Electrical and Computer Engineering
Abstract
In model predictive control, knowledge about the future trajectories of the set points or disturbances is used to optimize the overall system performance, Camacho and Bordons (2007). For hybrid electric vehicles, by predicting the future Driver's Desired Velocity (DDV), fuel economy, or emissions can be improved, Debert et al. (2010). For predicting DDV, different approaches have been suggested, for example, artificial neural networks, Fotouhi et al. (2011), statistical methods, or methods based on GPS and Geographical Information Systems(GIS), Keulen et al. (2009). In this work, some of these approaches are introduced and autoregressive methods with GPS/GIS information are evaluated.
Publication Title
IFAC-PapersOnLine
Recommended Citation
Rezaei, A.,
&
Burl, J.
(2015).
Prediction of vehicle velocity for model predictive control.
IFAC-PapersOnLine,
28(15), 257-262.
http://doi.org/10.1016/j.ifacol.2015.10.037
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/6510
