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

doi:10.19562/j.chinasae.qcgc.2025.04.004

Abstract

Abstract:

For the problems of inaccurate speed prediction and poor SOC adaptability under the traditional model predictive control， the plug-in hybrid electric vehicle （PHEV） is taken as the research object， and the speed prediction model based on computer vision is combined with the deep deterministic policy gradient （DDPG） algorithm to achieve the real-time state of charge （SOC） reference trajectory planning and optimal power allocation control of PHEV. A SOC reference trajectory planning model based on the enhanced DDPG is constructed， and a speed prediction model based on computer vision with cascaded long short-term memory network is constructed， based on which the optimal controller based on the model predictive control is used to achieve the accurate tracking of the SOC reference trajectory and power optimization. The results show that compared to the traditional DDPG， the strategy proposed in this paper increases the overall vehicle economy by 5.66% ， reaching 97.93% of the global optimal algorithm. It also improves the overall vehicle economy by 2.92% compared to the energy management strategy without computer vision.

Key words: plug-in hybrid electric vehicle, energy management strategy, computer vision, speed prediction, reference trajectory

Shu Wang,Qi Han,Xuan Zhao,Penghui Xie. Predictive Energy Management Strategy of Plug-in Hybrid Electric Vehicle with Computer Vision[J].Automotive Engineering, 2025, 47(4): 625-635.

Figures/Tables 23

References 26

1	陈轶嵩，兰利波，郝卓，等.面向碳中和的新能源汽车全生命周期评价研究综述及趋势展望［J］.汽车工程学报，2022，12（4）：360-374.
	CHEN Y S， LAN L B， HAO Z， et al. Review and future prospects of life cycle assessment of new energy vehicles towards carbon neutrality［J］. Chinese Journal of Automotive Engineering， 2022， 12（4）： 360-374.
2	朱镇，曾令新，林勇刚，等.融合工况预测的混合动力拖拉机自适应能量管理策略［J］.西安交通大学学报，2023，57（12）：201-210.
	ZHU Z， ZENG L X， LIN Y G， et al. Adaptive energy management strategy for hybrid tractors based on condition prediction［J］. Journal of Xi’an Jiaotong Univerisity， 2023， 57（12）： 201-210.
3	王跃飞，王志，孙睿，等. 基于驾驶意图多步预测的智能网联 HEV 等效排放最小控制策略［J］. 机械工程学报， 2023， 59（18）： 271-282.
	WANG Y F， WANG Z， SUN R， et al. Equivalent emission minimization strategy of intelligent connected HEV based on multi-step prediction of driving intention［J］. Journal of Mechanical Engineering， 2023， 59（18）： 271-282.
4	黄康，王强，邱明明，等. 考虑模式切换频率的多模式混合动力汽车参数优化［J］. 西安交通大学学报， 2019， 53（7）： 99-107.
	HUANG K， WANG Q， QIU M M， et al. Parameter optimization of multi-mode hybrid vehicle considering mode switching frequency ［J］. Journal of Xi’an Jiaotong University， 2019， 53（7）： 99-107.
5	施德华，袁超，汪少华，等.考虑驾驶风格的混合动力汽车强化学习能量管理策略［J］.西安交通大学学报，2024，58（10）：51-62.
	SHI D H， YUAN C， WANG S H， et al. Reinforcement learning energy management strategy for hybrid electric vehicle considering driving style［J］. Journal of Xi’an Jiaotong Univerisity， 2024，58（10）：51-62.
6	TRAN D， VAFAEIPOUR M， BAGHDADI M， et al. Thorough state-of-the-art analysis of electric and hybrid vehicle powertrains： topologies and integrated energy management strategies［J］. Renewable and Sustainable Energy Reviews， 2020， 119： 109596.
7	YANG C， DU X L， WANG W D， et al. Variable optimization domain-based cooperative energy management strategy for connected plug-in hybrid electric vehicles［J］. Energy， 2024， 290： 130206.
8	施德华，容香伟，汪少华，等. 基于功率比的混合动力汽车模糊自适应等效燃油消耗最小策略研究［J］.西安交通大学学报，2022，56（1）：12-21.
	SHI D H， RONG X W， WANG S W， et al. Fuzzy adaptive equivalent consumption minimization strategy for hybrid electric vehicle based on power ratio［J］. Journal of Xi’an Jiaotong University， 2022， 56（1）： 12-21.
9	LIU X D，DU J，MA J， et al. An adaptive co-state design method for PMP-based energy management of plug-in hybrid electric vehicles based on fuzzy logical control［J］. Journal of Energy Storage， 2024， 102：114118.
10	CHAI H， ZHAO X， YU Q， et al. Adaptive equivalent consumption minimization strategy based on road grade estimation for a plug-in hybrid electric truck［J］. Journal of Energy Storage， 2023， 70： 108035.
11	JU F， MURGOVSKI N， ZHUANG W C， et al. Predictive energy management with engine switching control for hybrid electric vehicle via ADMM［J］. Energy， 2023， 263： 125971.
12	LI Y P， WANG F， TANG X L， et al. Convex optimization-based predictive and bi-level energy management for plug-in hybrid electric vehicles［J］. Energy， 2022， 257： 124672.
13	齐春阳，宋传学，宋世欣，等.基于逆强化学习的混合动力汽车能量管理策略研究［J］.汽车工程，2023，45（10）：1954-1964，1974.
	QI C Y， SONG C X， SONG S X， et al. Research on energy management strategy for hybrid electric vehicles based on inverse reinforcement learnin［J］. Automotive Engineering， 2023， 45（10）： 1954-1964，1974.
14	HE H W， MENG X F， WANG Y， et al. Deep reinforcement learning based energy management strategies for electrified vehicles： recent advances and perspectives［J］. Renewable and Sustainable Energy Reviews， 2024， 192： 114248.
15	DU G D， ZOU Y， ZHANG X D， et al. Deep reinforcement learning based energy management for a hybrid electric vehicle［J］. Energy， 2020， 201： 117591.
16	TANG X L， CHEN J X， PU H Y， et al. Double deep reinforcement learning-based energy management for a parallel hybrid electric vehicle with engine start-stop strategy［J］. IEEE Transactions on Transportation Electrification， 2022， 8（1）： 1376-1388.
17	ZHAGN J， TAO J， HU Y， et al. An energy management strategy based on DDPG with improved exploration for battery/supercapacitor hybrid electric vehicle［J］. IEEE Transactions on Intelligent Transportation Systems， 2024， 25（5）： 3999-4008.
18	TANG X L， ZHANG J M， PI D W， et al. Battery health-aware and deep reinforcement learning-based energy management for naturalistic data-driven driving scenarios［J］. IEEE Transactions on Transportation Electrification， 2022， 8（1）： 948-964.
19	袁田，赵轩，刘瑞，等.考虑交通参与者的城市交叉口车速预测模型［J］.东南大学学报（自然科学版），2023， 53（2）： 326-333.
	YUAN T， ZHAO X， LIU R， et al. Speed prediction model at urban intersections considering traffic participant［J］. Journal of Southeast University （Natural Science Edition）， 2023， 53（2）： 326-333.
20	HUI L， LI X M，WANG W D， et al. Markov velocity predictor and radial basis function neural network based real-time energy management strategy for plug-in hybrid electric vehicles［J］.Energy， 2018， 152： 427-444.
21	XIE S， HU S S， TANG X L， et al. Model predictive energy management for plug-in hybrid electric vehicles considering optimal battery depth of discharge［J］. Energy， 2019， 173： 667-678.
22	LI G P， ZHANG J L， HE H. Battery SOC constraint comparison for predictive energy management of plug-in hybrid electric bus［J］. Applied Energy， 2017， 194： 578-587.
23	LIU Y G， LI J， CHEN Z， et al. Research on a multi-objective hierarchical prediction energy management strategy for range extended fuel cell vehicles［J］. Journal of Power Sources， 2019， 429： 55-66.
24	GUO L X， ZHANG X D， ZOU Y， et al. Cost-optimal energy management strategy for plug-in hybrid electric vehicles with variable horizon speed prediction and adaptive state-of-charge reference［J］. Energy， 2021， 232： 120993.
25	TANG X L， JIA T， HU X S， et al. Naturalistic data-driven predictive energy management for plug-in hybrid electric vehicles［J］. IEEE Transactions on Transportation Electrification， 2020， 7（2）： 497-508.
26	HE H W， HUANG R C， MENG X F，et al. A novel hierarchical predictive energy management strategy for plug-in hybrid electric bus combined with deep deterministic policy gradient［J］. Journal of Energy Storage， 2022， 52： 104787.

参数	数值
整车整备质量/kg	1 680
滚动半径/m	0.352
迎风面积/m²	2.26
风阻系数	0.371
滚动阻力系数	0.012
传动系效率	0.90
旋转质量换算系数	1.07
主减速器速比	6.328

预测模型类型	RMSE/（km·h^-1）	MAE/（km·h^-1）	SCC/%
RBF神经网络	2.873	1.968	99.77
单层LSTM	10.570	8.610	79.95
级联式LSTM	2.096	1.511	99.85

策略	MAE	RMSE	SCC/%
DDPG	0.041 35	0.048 19	96.735
E-DDPG	0.015 13	0.021 33	98.903

策略	MAE	RMSE	SCC/%
DP-SOC	0.004 0	0.006 4	99.83
DQN-SOC	0.026 2	0.036 3	97.80
Time-SOC	0.005 5	0.009 7	99.63
E-DDPG-SOC	0.003 6	0.005 9	99.86

策略	总油耗/L	电力/（kW·h）	总成本/元	经济性/%
DP	15.37	16.43	139.39	100
DDPG	16.90	15.85	151.07	92.27
DP-SOC	16.20	16.16	145.79	95.61
E-DDPG-SOC	15.79	16.04	141.77	97.93

Predictive Energy Management Strategy of Plug-in Hybrid Electric Vehicle with Computer Vision

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 23

References 26

Related Articles 15

Metrics

Comments

Recommended 0

策略	计算时间/s
策略	SOC规划	MPC控制器计算
E-DDPG-SOC	11.64	0.214
DP-SOC	1 496.24	0.237

[1]	Yapeng Li,Xiaolin Tang,Xiaosong Hu. Study on Eco-driving of PHEVS Based on Hierarchical Control Strategy [J]. Automotive Engineering, 2023, 45(4): 551-560.
[2]	Jinxia Liu,Zhihao Liang,Qiang Wang,Mingxing Wen. Research on the Equivalent Fuel Consumption Minimizing Energy Management Strategy of Through-the-Road Vehicle [J]. Automotive Engineering, 2023, 45(2): 285-292.
[3]	Chunyang Qi,Chuanxue Song,Shixin Song,Liqiang Jin,Da Wang,Feng Xiao. Research on Energy Management Strategy for Hybrid Electric Vehicles Based on Inverse Reinforcement Learning [J]. Automotive Engineering, 2023, 45(10): 1954-1964.
[4]	Yong Chen,Changyin Wei,Xiaoyu Li,Yanlin Li,Caixia Liu,Xiaozhe Lin. Research on Fuzzy Energy Management Strategy for Extended-Range Electric Vehicles with Driving Condition Identification [J]. Automotive Engineering, 2022, 44(4): 514-524.
[5]	Zhichao Liu,Tianlei Zheng,Shaohui Liu,Huiming Gong. Research on Energy Consumption and Driving Range Evaluation Method of Plug-in Hybrid Electric Passenger Car [J]. Automotive Engineering, 2022, 44(2): 161-170.
[6]	Junqiu Li,Jiwei Liu,Chaofeng Zhu. Research on Energy Management of Hybrid Electric Vehicle Based on Time-Varying Chassis Configuration [J]. Automotive Engineering, 2022, 44(12): 1866-1876.
[7]	Ningkang Yang,Lijin Han,Hui Liu,Xin Zhang. Research on Efficiency Optimization Based Energy Management Strategy for a Hybrid Electric Vehicle with Reinforcement Learning [J]. Automotive Engineering, 2021, 43(7): 1046-1056.
[8]	Jie Hu,Ming Wang,Di Liu,Fuwu Yan,Kai Cao. Optimization of Control Strategy for Hybrid Power System Based on Traffic Information [J]. Automotive Engineering, 2021, 43(5): 675-682.
[9]	Hao Zhang,Qinhao Fan,Wei Wang,Jin Huang,Zhi Wang. Reinforcement Learning Based Energy Management Strategy for Hybrid Electric Vehicles Using Multi⁃mode Combustion [J]. Automotive Engineering, 2021, 43(5): 683-691.
[10]	Long Chen,Zhixing Chen,Xing Xu,Feng Wang,Yingfeng Cai,Tao Zhang. Energy Management Strategy of Plug⁃in Hybrid Electric Vehicle with Engine Start and Stop Optimization [J]. Automotive Engineering, 2021, 43(3): 313-322.
[11]	Mingming Qiu,Longkai Cao,Kang Huang,Yilei Zhang,Hao Liu. Brake by Wire Pressure Sliding Mode Control Based on Visual Recognition [J]. Automotive Engineering, 2021, 43(1): 68-76.
[12]	Zhang Yan, Duan Lian, Yuan Xiayi, Jiang Liang, Xu Yanghui, Lan Fengchong. Experimental Study on Energy Flow in a Plug-in Hybrid Electric Vehicle at Low Battery SOC [J]. Automotive Engineering, 2020, 42(5): 688-693.
[13]	Yang Ye, Zhang Youtong, Zhang Biao, Hu Shaoyi. Adaptive Energy Management Strategy for Plug-in Hybrid Electric Bus Based on Equivalent Factor Optimization [J]. Automotive Engineering, 2020, 42(3): 292-298.
[14]	Jin Hui, Zhang Zihao. Review of Research on HEV Energy Management Based on Adaptive Dynamic Programming [J]. Automotive Engineering, 2020, 42(11): 1490-1496.
[15]	Xia Hongpu, Wang Bin, Wu Guangyao, Li Tie & Tong Ronghui. Sensitivity Analysis on Energy Consumption ofPHEV Based on Real Vehicle Road Data [J]. Automotive Engineering, 2019, 41(9): 990-997.