Research on Energy Management Strategy for Hybrid Electric Vehicles Based on Inverse Reinforcement Learning

被引：0

作者：

Qi C. ^{[1
]}

Song C. ^{[2
]}

Song S. ^{[3
]}

Jin L. ^{[2
]}

Wang D. ^{[3
]}

Xiao F. ^{[1
]}

机构：

[1] Jilin University, State Key Laboratory of Automotive Simulation and Control, Changchun

[2] College of Automotive Engineering, Jilin University, Changchun

[3] School of Mechanical and Aerospace Engineering, Jilin University, Changchun

来源：

Qiche Gongcheng/Automotive Engineering | 2023年 / 45卷 / 10期

关键词：

energy management strategy; hybrid electric vehicle; maximum entropy reverse reinforcement learning; positive reinforcement learning;

D O I：

10.19562/j.chinasae.qcgc.2023.10.016

中图分类号：

学科分类号：

摘要：

Energy management strategy is one of the key technologies for hybrid vehicles. With the continuous upgrading of computing power and hardware devices,more and more scholars have gradually carried out research on learning-based energy management strategies. In the study of reinforcement learning-based energy management strategies for hybrid electric vehicles,the orientation of the interaction between the intelligent agent and the environment is determined by the reward function. However,most of the current reward function design is subjectively determined or based on experience,which is difficult to objectively describe the expert's intention,so in that condition there is no guarantee that the intelligent body will learn the optimal driving strategy for a given reward function. To address these problems,an energy management strategy based on inverse reinforcement learning is proposed in this paper to obtain the reward function weights under the expert trajectory by means of inverse reinforcement learning and use them to guide the behavior of the engine and battery intelligent agents. Then,the modified weights are input again into the positive reinforcement learning training. The fuel consumption value,SOC variation curve,reward training process and power source torque are used to verify the accuracy of the weight value and its advantage in terms of fuel saving capability. In summary,the algorithm has improved the fuel saving effect by 5%~10%. © 2023 SAE-China. All rights reserved.

引用

页码：1954 / 1964and1974

共 19 条

[1] MAHAPATRA S, EGEL T, HASSAN R, Et al., Model based design for hybrid electric vehicle systems, Sensors, (2020)
[2] LI D G, YAN S, QIU J C, Et al., Rule-based power management strategy for parallel hydraulic hybrid vehicle, Chinese Journal of Automotive Engineering, 4, 2, pp. 116-124, (2014)
[3] PANG Y H., Research on energy management strategy of hybrid electric vehicle based on hierarchical reinforcement learning, (2022)
[4] LIU T., Reinforcement learning-based energy management for hybrid electric vehicles, (2017)
[5] TANG X L, CHEN J X, LIU T, Et al., Research on deep reinforcement learning-based intelligent car-following control and energy management strategy for hybrid electric vehicles, Journal of Mechanical Engineering, 57, 22, pp. 237-246, (2021)
[6] LI Y, HE H, PENG J, Et al., Energy management strategy for a series hybrid electric vehicle using improved deep Q-network learning algorithm with prioritized replay, DEStech Transactions on Environment Energy and Earth Science, (2019)
[7] CHAOUI H, GUALOUS H, BOULON L, Et al., Deep reinforcement learning energy management system for multiple battery based electric vehicles, IEEE Vehicle Power & Propulsion Conference, (2018)
[8] LIU C, YI L M., Power management for plug-in hybrid electric vehicles using reinforcement learning with trip information, Transportation Electrification Conference & Expo, (2014)
[9] LIU T, HU X, LI S E, Et al., Reinforcement learning optimized look-ahead energy management of a parallel hybrid electric vehicle, IEEE Asme Transactions on Mechatronics, (2017)
[10] YANG N, HAN L, XIANG C, Et al., Energy management for a hybrid electric vehicle based on blended reinforcement learning with backward focusing and prioritized sweeping, IEEE Transactions on Vehicular Technology, 99, (2021)

← 1 2 →