Journal
ENERGY
Volume 245, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.energy.2022.123182
Keywords
Energy management strategy; Double Q-learning; Elman neural network; Velocity prediction; Model prediction control
Categories
Funding
- National Key R&D Pro-gram of China [2018YFB0104000]
- National Natural Science Foundation of China [61763021]
- Double First-class Project of Kunming University of Science and Technology [202101BE070001-058, 845102-HOEMEVH2020-MSCAeIFe2018]
Ask authors/readers for more resources
This paper proposes an energy management strategy based on double Q-learning for plug-in hybrid electric vehicles to allocate power between multiple power sources. By establishing an effective offline learning controller and using a neural network to predict vehicle speed, the proposed strategy achieves superior fuel economy while adapting to different state of charge reference trajectories.
Energy management strategy (EMS) for plug-in hybrid electric vehicle (PHEV) is the key to improve the energy utilization efficiency and vehicle fuel economy. In this paper, a model predictive control (MPC) based on EMS coupled with double Q-learning (DQL) is presented to allocate the power between multiple power sources for PHEV. Firstly, the powertrain framework of the PHEV and its mathematical models were analyzed in detail. Then, based on the required power and speed, an effective convergent offline learning controller was established based on DQL algorithm. Subsequently, the multi-feature input Elman neural network was implemented to predict vehicle speed in MPC, and the trained DQL controller was applied to solve the rolling optimization process in MPC to find the optimal battery output in the prediction horizon. Finally, the proposed strategy was verified in Autonomie software, and the simulation results show that the proposed strategy can achieve a superior fuel economy close to that of the offline stochastic dynamic planning strategy, meanwhile with a perfect adaptability for different state of charge (SOC) reference trajectories.(c) 2022 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available