Adaptive energy management strategy based on frequency domain power distribution

Aiming at the special needs of heavy-duty hybrid electric vehicles(HEVs)., an adaptive energy management strategy based on frequency domain power distribution is proposed. This article uses MATLAB/Simulink to establish a dynamic model of a heavy-duty HEV. Firstly, the nonlinear autoregressive with external input(NARX) neural network is used to predict the speed of the vehicle. Secondly, according to the predicted vehicle speed, principal component analysis and K-means clustering method are used to classify the working conditions, the corresponding control parameters are adjusted adaptively according to the working conditions category, and the power is distributed in the frequency domain. A piece of real vehicle driving cycle data of the vehicle is used as the simulation condition to verify and analyze the strategy. The simulation results show that this strategy can quickly restore the deviated battery state-of-charge (SoC) to the target value and maintain it stably. The battery's charge and discharge current amplitude are effectively reduced, and meanwhile, the transient working conditions of the engine are reduced too, and therefore the engine can work on the optimal efficiency curve. It is verified that this strategy is an effective real-time energy management strategy for heavy-duty HEVs.