Energy Management for a Power-Split Plug-in Hybrid Electric Vehicle Based on Dynamic Programming and Neural Networks

Abstract

This paper focuses on building an efficient, online, and intelligent energy management controller to improve the fuel economy of a power-split plug-in hybrid electric vehicle (PHEV). Based on a detailed powertrain analysis, the battery current can be optimized to improve the fuel economy using dynamic programming (DP). Three types of drive cycles, i.e., highway, urban, and urban (congested), are classified, and six typical drive cycles are analyzed and simulated to study all the driving conditions. The online intelligent energy management controller is built, which consists of two neural network (NN) modules that are trained based on the optimized results obtained by DP methods, considering the trip length and duration. Based on whether the trip length and duration are known or unknown, the controller will choose the corresponding NN module to output the effective battery current commands to realize the energy management. Numerical simulation shows that the proposed controller can improve the fuel economy of the vehicle.