杨曜泽,霍为炜

• 1:北京信息科技大学机电工程学院

摘要(Abstract)：

为提升燃料电池车辆（fuel cell electric vehicles, FCEVs）能量管理对未来负载变化的感知与前瞻决策能力，针对未来信息输入形式与控制目标匹配不足的问题，研究未来短时需求表征及其控制应用。采用交通模拟软件SUMO(simulation of urban mobility)构建实时道路信息数据集，建立未来5 s驱动需求功率预测模型，比较直接功率预测与速度预测—功率换算2条路线，并构造低维未来短时需求表征，在统一深度强化学习（deep reinforcement learning, DRL）框架下开展能量管理验证。结果表明：极限梯度提升（extreme gradient boosting, XGBoost）综合预测性能较好，决定系数为0.571；直接功率预测路线更优；引入未来短时需求表征后，双延迟深度确定性策略梯度（twin delayed deep deterministic policy gradient, TD3）总等效金额下降18.7%，最小荷电状态（state of charge, SOC）上升15.4%，综合经济性与安全性均得到改善。

关键词(KeyWords)： 燃料电池车辆;驱动需求预测;未来短时需求表征;深度强化学习;能量管理

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 杨曜泽,霍为炜

DOI: 10.16508/j.cnki.11-5866/n.2026.03.012

参考文献(References)：

• [1]KHALATBARISOLTANI A,ZHOU H T,TANG X L,et al.Energy management strategies for fuel cell vehicles:a comprehensive review of the latest progress in modeling,strategies, and future prospects[J]. IEEE Transactions on Intelligent Transportation Systems,2024,25(1):14-32.
• [2]PRAMUANJAROENKIJ A,KAKA??S. The fuel cell electric vehicles:the highlight review[J]. International Journal of Hydrogen Energy,2023,48(25):9401-9425.
• [3]SULAIMAN N,HANNAN M A,MOHAMED A,et al. A review on energy management system for fuel cell hybrid electric vehicle:issues and challenges[J]. Renewable and Sustainable Energy Reviews,2015,52:802-814.
• [4]SONG K,WANG X D,LI F Q,et al. Pontryagin′s minimum principle-based real-time energy management strategy for fuel cell hybrid electric vehicle considering both fuel economy and power source durability[J]. Energy,2020,205:118064.
• [5]陈薇玉，姜莉.氢燃料电池混合动力汽车能量管理策略研究综述[J].黑龙江工程学院学报，2024,38(4):1-8.CHEN W Y, JIANG L. A review of energy management strategies for hydrogen fuel cell hybrid electric vehicles[J].Journal of Heilongjiang Institute of Technology,2024,38(4):1-8.(in Chinese)
• [6]WANG W,HAO Z,QU F F,et al. Review of energy management methods for fuel cell vehicles:from the perspective of driving cycle information[J]. Sensors,2023,23(20):8571.
• [7]XU Y G,XU E Y,ZHENG W G,et al. Hierarchical modelpredictive-control-based energy management strategy for fuel cell hybrid commercial vehicles incorporating traffic information[J]. Sustainability,2023,15(17):12833.
• [8]XU E Y,MA M C,ZHENG W G,et al. An energy management strategy for fuel-cell hybrid commercial vehicles based on adaptive model prediction[J]. Sustainability,2023,15(10):7915.
• [9]LI F X,WANG X L,BAO X C,et al. Energy management strategy for fuel cell vehicles based on online driving condition recognition using dual-model predictive control[J]. Sensors,2024,24(23):7647.
• [10]QUAN S W,WANG Y X,XIAO X L,et al. Real-time energy management for fuel cell electric vehicle using speed predictionbased model predictive control considering performance degradation[J]. Applied Energy,2021,304:117845.
• [11]YANG D,WANG L,YU K J,et al. A reinforcement learningbased energy management strategy for fuel cell hybrid vehicle considering real-time velocity prediction[J]. Energy Conversion and Management,2022,274:116453.
• [12]王姝，韩琪，赵轩，等.融合机器视觉的插电式混合动力汽车预测型能量管理策略[J].汽车工程，2025,47(4):625-635.WANG S,HAN Q,ZHAO X,et al. Predictive energy management strategy of plug-in hybrid electric vehicle with computer vision[J]. Automotive Engineering,2025,47(4):625-635.(in Chinese)
• [13]AMINI M R,FENG Y H,YANG Z,et al. Long-term vehicle speed prediction via historical traffic data analysis for improved energy efficiency of connected electric vehicles[J].Transportation Research Record:Journal of the Transportation Research Board,2020,2674(11):17-29.
• [14]ZENG T,ZHANG C Z,ZHANG Y Y,et al. Optimizationoriented adaptive equivalent consumption minimization strategy based on short-term demand power prediction for fuel cell hybrid vehicle[J]. Energy,2021,227:120305.
• [15]李卫，郑春花，许德州.基于深度强化学习的燃料电池混合动力汽车能量管理策略研究[J].集成技术，2021,10(3):47-60.LI W,ZHENG C H,XU D Z. Research on energy management strategy of fuel cell hybrid vehicles based on deep reinforcement learning[J]. Journal of Integration Technology,2021,10(3):47-60.(in Chinese)
• [16]LIU T,HUO W W,LU B,et al. Reinforcement learning-based co-optimization of adaptive cruise speed control and energy management for fuel cell vehicles[J]. Energy Technology,2024,12(1):2300541.
• [17]トヨタ自動車株式会社.トヨタMIRAI主要諸元表[EB/OL].(2015-01)[2026-04-11]. https：//toyota. jp/pages/contents/mirai/001_p_001/pdf/spec/mirai_spec_201501. pdf.Toyota Motor Corporation. Toyota MIRAI Main Specifications Table[EB/OL].(2015-01)[2026-04-11]. https：//toyota. jp/pages/contents/mirai/001_p_001/pdf/spec/mirai_spec_201501.pdf.(in Japanese)
• [18]LEE H,CHA S W. Energy management strategy of fuel cell electric vehicles using model-based reinforcement learning with data-driven model update[J]. IEEE Access,2021,9:59244-59254.
• [19]HAN Y,AHN S. Estimation of traffic flow rate with data from connected-automated vehicles using Bayesian inference and deep learning[J]. Frontiers in Future Transportation,2021,2:644988.
• [20]黄宇航，陈勇.基于模糊卡尔曼滤波的锂电池SOC估算研究[J].北京信息科技大学学报（自然科学版），2019,34(3):48-52.HUANG Y H,CHEN Y. Research on SOC estimation for lithium battery based on fuzzy adaptive Kalman filtering[J].Journal of Beijing Information Science and Technology University,2019,34(3):48-52.(in Chinese)