Abstract: Aiming at the problem of poor adaptability of fuel cell vehicle energy management strategy in complex operating conditions, an adaptive fuzzy energy management strategy based on back propagation (BP) neural network was proposed. The Chinese passenger vehicle driving cycle (CLTC-P) was selected as the sample driving cycle, and the maximum speed, average speed and idle time ratio were used as the characteristic parameters to establish the BP neural network driving cycle recognition model. The fuzzy energy management strategies under three typical working conditions were developed, the parameters of the fuzzy strategy were optimized offline by using genetic algorithm, and the working conditions were identified online by using BP neural network and the appropriate strategy parameters were selected. The simulation results show that compared with the rule-based strategy and the fuzzy control strategy with condition recognition, the adaptive fuzzy energy management strategy can reduce the equivalent hydrogen consumption of the vehicle by 6.87% and 3.41%, respectively, which indicates that the proposed strategy can effectively identify random conditions, improve the problem of poor adaptability of the strategy, and further improve the economy of the vehicle.