A Novel Velocity Forecast Method for Improving Predictive Energy Management of Plug-In Hybrid Electric Vehicles

In this paper, a novel velocity predicted method based on Wavelet Transform (WT) and Radial Basis Function Neural Network (RBF-NN) is introduced to achieve the predictive energy management for plug-in hybrid electric vehicles (PHEVs). Three cases including RBF-NN, 1 RBF-NN with WT and 2 RBF-NN with WT, are taken into account for comparison. The corresponding model predictive control (MPC) algorithm is employed to testify the improvement of fuel economy based on the predicted velocity profile. Simulation results show that the combined algorithm of 1 RBF-NN and WT can attain satisfactory performance, which increases the prediction accuracy by 7.31% compared with that by other two cases. In addition, the computational time of the proposed predictive method is 2.8649 ms, justifying that it can be efficiently employed in the practical application.