Application of Car-Following Model Based on Neural Network to FCEV Power System

In order to improve the overall economy of fuel cell vehicle, this paper proposes an energy management strategy based on Car-Following Model Long Short-Term Memory Neural Network (LSTM-CFM), which classified vehicles according Vehicle_ID, Frame_ID, Global_Time and other core data vehicle information collected from Next Generation Simulation (NGSIM) set US 101 highway in south California. The two adjacent were identified extracted processed into LSTM-CFM for training. simulation stage, UDDS (a standard driving condition) is taken as condition followed 50m initial distance between following target vehicle. Under these conditions, we can get speed prediction model. designed principle minimum equivalent consumption, factor be solved by using prediction. results show that under better than rule-based strategy, verifies effectiveness strategy.