Torque distribution strategy of PHEV based on FCMAC neural network
1. School of Electrical ＆ Electronic Engineering, Changchun University of Technology, Changchun, Jilin 130012, China; 2. R＆D Center of Great Wall Motor Co., Ltd., Baoding, Hebei 071000, China
Abstract：Due to the important impact of hybrid electric vehicle (HEV) distribution strategy on vehicle fuel economy and emissions, a vehicle torque distribution method was propared based on fuzzy cerebellar model articulation controller (FCMAC) neural network control. Based on the pregearbox twinaxle torque coupled PHEV, the FCMAC neural network control strategy was established with engine output torque as target. After discretization, the rule multiplied Gaussian fuzzy membership degree was inputted into FCMAC, and the engine torque was outputted through hash mapping and weight adjustment to realize the torque distribution of HEV. The simulation model was established on AVLCruise and Matlab/Simulink platform, and the simulation results were compared with those based on logic threshold control strategy. The results show that the FCMAC control strategy is better than the logic threshold control strategy under NEDC condition, and the fuel economy and the emissions of vehicle are improved.
2017, Vol. 38 
