EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Energy Saving for Hybrid Tractor Based on Working Condition Prediction and DDPG-Fuzzy Control

Shilong Fan, Xianghai Yan, Shuaishuai Ge, Junjiang Zhang, Mengnan Liu

World Electric Vehicle Journal · 29.08.2025 · 16 (9) · 490

DOI: 10.3390/wevj16090490 ↗

Kurz gefasst

Fachartikel in der Zeitschrift World Electric Vehicle Journal, online erschienen am 29.08.2025. Verfasst von Shilong Fan und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Henan Province K&D Project, Henan Provincial Natural Science Foundation Project, Opening Foundation of Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To significantly reduce fuel consumption and improve fuel economy in hybrid tractor under complex working conditions, an energy—saving strategy based on working condition prediction and Deep Deterministic Policy Gradient and Fuzzy control (DDPG-Fuzzy) was proposed. Firstly, a hybrid tractor system dynamics model containing diesel, motor, and power battery was established. Secondly, a working condition prediction model for plowing velocity and resistance was constructed based on the adaptive cubic exponential smoothing method. Finally, a two-layer control architecture was designed. The upper layer adopted the DDPG algorithm, which takes demand torque, equivalent fuel consumption, and the State of Charge (SOC) as state inputs to optimize energy consumption by generating the diesel benchmark torque through the policy network. The lower layer introduced a fuzzy control compensation mechanism that calculates the torque correction based on the plowing velocity error and the plowing resistance deviation to adjust the power allocation. In light of on this, an energy—saving strategy for hybrid tractor based on working condition prediction and DDPG-Fuzzy control was proposed. Under a standard 140 s plowing cycle, the results showed that the working condition prediction model achieved mean prediction accuracies of 97% for plowing velocity and 96.8% for plowing resistance. Under plowing conditions, the proposed strategy reduced the equivalent fuel consumption by 9.7% compared to the power-following strategy, and reduced SOC by 4.4% while maintaining it within a reasonable range. By coordinating the operation of the diesel and motor within high-efficiency regions, this approach enhances fuel economy under complex working conditions.

Förderung

  • Henan Province K&D Project
  • Henan Provincial Natural Science Foundation Project
  • Opening Foundation of Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education
  • National Key R&D Program of China
  • Support for Young Talents in He Lu Region

Zitieren

APA

Fan, S., Yan, X., Ge, S., Zhang, J., & Liu, M. (2025). Research on Energy Saving for Hybrid Tractor Based on Working Condition Prediction and DDPG-Fuzzy Control. World Electric Vehicle Journal, 16(9), 490. https://doi.org/10.3390/wevj16090490

Vancouver

Fan S, Yan X, Ge S, Zhang J, Liu M. Research on Energy Saving for Hybrid Tractor Based on Working Condition Prediction and DDPG-Fuzzy Control. World Electric Vehicle Journal. 2025;16(9):490. doi:10.3390/wevj16090490

BibTeX
@article{Fan2025,
  author = {Fan, Shilong and Yan, Xianghai and Ge, Shuaishuai and Zhang, Junjiang and Liu, Mengnan},
  title = {Research on Energy Saving for Hybrid Tractor Based on Working Condition Prediction and DDPG-Fuzzy Control},
  journal = {World Electric Vehicle Journal},
  year = {2025},
  volume = {16},
  number = {9},
  pages = {490},
  doi = {10.3390/wevj16090490}
}
Kostenlos starten →