| It is one of the effective solutions to solve current exhaust emission pollution,oil crisis and energy security by developing hybrid electric vehicle.The energy management strategy can improve fuel economy while meeting the power demand by reasonably distributing the driving power among multiple power sources.In order to instantaneously optimize power distribution and reduce furl consumption for paraller-series hybrid electric vehicle,the energy management strategy based on driving cycle identification is studied in this paper.The main contents include:(1)The mathmatical models of system components including vehicle,engine,motors and battery are established.And the mode switching rules are extracted from the Dynamic Optimization(DP)strategy to optimize the control parameters of the Rule-Based energy management strategy.(2)The Equivalent Consumption Minimization Strategy(ECMS)is studied in this paper.Based on the optimization results of DP strategy under single driving cycle,the optimal equivalent factors under different driving conditions are extracted and used to train BP neural network.Then the simulation results of the Adapted Equivalent Consumption Minimiza Strategy(A-ECMS)based on BP neural network and the A-ECMS strategy based on PI are compared.(3)The K-means++ clustering algorithm is used to cluster the standard driving cycles and construct four typical driving cycles.Three characteristic parameters are selected by using the correlation between characteristic parameters and fuel consumption.The decision tree algorithm and the distance discriminant method are used to identify the driving cycles respectively.Finally,the distance discrimination method with higher accuracy is selected as the driving cycle recognition algorithm.(4)The corresponding BP neural network and PI parameters are optimized under four typical driving cycles.Then the driving cycle identification algorithm and A-ECMS are combined and simulated.(5)The hardware-in-the-loop(HIL)real-time simulation platform is built with HCU vehicle controller,PXI real-time machine,CANoe and Veristand,etc.Finally the energy management strategy is verified on the HIL. |