EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hierarchical Reinforcement Learning-Based Energy Management for Hybrid Electric Vehicles with Gear-Shifting Strategy

Cong Lan, Hailong Zhang, Yongjuan Zhao, Huipeng Du, Jinglei Ren, Jiangyu Luo

Machines · 23.08.2025 · 13 (9) · 754

DOI: 10.3390/machines13090754 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 23.08.2025. Verfasst von Cong Lan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Fundamental Research Program of Shanxi Province, Technology Innovation Leading Talent Team for Special Unmanned Systems and Intelligent Equipment.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The energy management strategy (EMS) is a core technology for improving the fuel economy of hybrid electric vehicles (HEVs). However, the coexistence of both discrete and continuous control variables, along with complex physical constraints in HEV powertrains, presents significant challenges for the design of efficient EMSs based on deep reinforcement learning (DRL). To further enhance fuel efficiency and coordinated powertrain control under complex driving conditions, this study proposes a hierarchical DRL-based EMS. The proposed strategy adopts a layered control architecture: the upper layer utilizes the soft actor–critic (SAC) algorithm for continuous control of engine torque, while the lower layer employs a deep Q-network (DQN) for discrete gear selection optimization. Through offline training and online simulation, experimental results demonstrate that the proposed strategy achieves fuel economy performance comparable to dynamic programming (DP), with only a 3.06% difference in fuel consumption. Moreover, it significantly improves computational efficiency, thereby enhancing the feasibility of real-time deployment. This study validates the optimization potential and real-time applicability of hierarchical reinforcement learning for hybrid control in HEV energy management. Furthermore, its adaptability is demonstrated through sustained and stable performance under long-duration, complex urban bus driving conditions.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Program of Shanxi Province
  • Technology Innovation Leading Talent Team for Special Unmanned Systems and Intelligent Equipment

Zitieren

APA

Lan, C., Zhang, H., Zhao, Y., Du, H., Ren, J., & Luo, J. (2025). Hierarchical Reinforcement Learning-Based Energy Management for Hybrid Electric Vehicles with Gear-Shifting Strategy. Machines, 13(9), 754. https://doi.org/10.3390/machines13090754

Vancouver

Lan C, Zhang H, Zhao Y, Du H, Ren J, Luo J. Hierarchical Reinforcement Learning-Based Energy Management for Hybrid Electric Vehicles with Gear-Shifting Strategy. Machines. 2025;13(9):754. doi:10.3390/machines13090754

BibTeX
@article{Lan2025,
  author = {Lan, Cong and Zhang, Hailong and Zhao, Yongjuan and Du, Huipeng and Ren, Jinglei and Luo, Jiangyu},
  title = {Hierarchical Reinforcement Learning-Based Energy Management for Hybrid Electric Vehicles with Gear-Shifting Strategy},
  journal = {Machines},
  year = {2025},
  volume = {13},
  number = {9},
  pages = {754},
  doi = {10.3390/machines13090754}
}
Kostenlos starten →