PROJECT TITLE :
Velocity Predictors for Predictive Energy Management in Hybrid Electric Vehicles
The performance and practicality of predictive energy management in hybrid electric vehicles (HEVs) are highly hooked in to the forecast of future vehicular velocities, each in terms of accuracy and computational potency. In this transient, we have a tendency to provide a comprehensive comparative analysis of three velocity prediction methods, applied inside a model predictive management framework. The prediction process is performed over every receding horizon, and the predicted velocities are used for fuel economy optimization of a power-split HEV. We assume that no telemetry or on-board sensor data is available for the controller, and the particular future driving profile is completely unknown. Basic principles of exponentially varying, stochastic Markov chain, and neural network-based velocity prediction approaches are described. Their sensitivity to tuning parameters is analyzed, and therefore the prediction precision, computational value, and resultant vehicular fuel economy are compared.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here