Online power management strategy for plug-in hybrid electric vehicles based on deep reinforcement learning and driving cycle reconstruction  

作　　者：Zhiyuan Fang Zeyu Chen Quanqing Yu Bo Zhang Ruixin Yang 

机构地区：[1]School of Mechanical Engineering and Automation,Northeastern University,Wenhua Road,110819 Shenyang,China [2]National Engineering Laboratory for Electric Vehicles,Beijing Institute of Technology,Zhongguancun South Street,100081 Beijing,China [3]School of Automotive Engineering,Harbin Institute of Technology,Wenhua West Road,264209 Weihai,China

出　　处：《Green Energy and Intelligent Transportation》2022年第2期62-74,共13页新能源与智能载运（英文）

基　　金：National Natural Science Foundation of China(51977029,52177210);Liaoning Provincial Science and Technology planned project(2021JH6/10500135);Fundamental Research Funds for the Central Universities(N2003002);Any opinions expressed in this paper are solely those of the authors and do not represent those of the sponsors.

摘　　要：This paper proposes a novel power management strategy for plug-in hybrid electric vehicles based on deep reinforcement learning algorithm.Three parallel soft actor-critic(SAC)networks are trained for high speed,medium speed,and low-speed conditions respectively;the reward function is designed as minimizing the cost of energy cost and battery aging.During operation,the driving condition is recognized at each moment for the algorithm invoking based on the learning vector quantization(LVQ)neural network.On top of that,a driving cycle reconstruction algorithm is proposed.The historical speed segments that were recorded during the operation are reconstructed into the three categories of high speed,medium speed,and low speed,based on which the algorithms are online updated.The SAC-based control strategy is evaluated based on the standard driving cycles and Shenyang practical data.The results indicate the presented method can obtain the effect close to dynamic programming and can be further improved by up to 6.38%after the online update for uncertain driving conditions.

关 键 词：Electric vehicle Deep reinforcement learning Power management strategy Driving cycle reconstruction Optimal control strategy 

分 类 号：U469.7[机械工程—车辆工程]