Trip Distance Adaptive Equivalent Hydrogen Consumption Minimization Strategy for Fuel Cell Vehicles integrating Driving Cycle Prediction

To effectively enhance the fuel economy of plug-in fuel cell vehicles and realize the optimal energy distribution between fuel cell and power battery, considering the close relationship between driving cycle, state of charge (SOC), equivalent factor and hydrogen consumption, strategy of trip distance adaptive equivalent consumption minimum integrating driving cycle prediction is proposed. The neural network based on back propagation is used to realize the prediction of short-term vehicle speed and analyze the change of vehicle energy demand in the future. At the same time, the equivalent factor is dynamically corrected in real time by using driving distance and SOC to realize the adaptability of energy management strategy. The simulation results show that the driving cycle prediction algorithm based on neural network can predict the future short-term conditions better, and its accuracy is 12.5 % higher than that of Markov method. The hydrogen consumption of the proposed energy management strategy under UDDS condition is 55.6 % lower than that of CD/CS strategy. Hardware-in-the-loop experiment verifies that the hydrogen consumption under EUDC condition is 26.8 % lower than that of CD/CS strategy.