Reinforcement learning-based real-time energy management for a hybrid tracked vehicle
详细信息 查看全文
- 作者：Yuan Zou ; zouyuan@bit.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Teng Liu ; Dexing Liu ; Fengchun Sun
- 关键词：Hybrid tracked vehicle ; Markov chain ; Kullback&ndash ; Leibler divergence rate ; Reinforcement learning ; Energy management ; Control strategy
- 刊名：Applied Energy
- 出版年：2016
- 出版时间：1 June 2016
- 年：2016
- 卷：171
- 期：Complete
- 页码：372-382
- 全文大小：2034 K
文摘
- •
A systematic control-oriented model for the HTV was built.
- •
A Markov chain model learns power transition probability recursively.
- •
The Kullback–Leibler divergence rate determines the transition probability update.
- •
Reinforcement learning (RL) was applied to optimize the control strategy.
- •
The strategy improves fuel efficiency and works real time.