基于门控机制的混合预测模型的混合动力车辆自适应能量管理

doi:10.3901/JME.260715

机械工程学报 ›› 2026, Vol. 62 ›› Issue (14): 302-312.doi: 10.3901/JME.260715

扫码分享

基于门控机制的混合预测模型的混合动力车辆自适应能量管理

杨东坡¹, 高嘉辉¹, 施德华¹, 曾小华²

1. 江苏大学汽车与交通工程学院镇江 212000;
2. 吉林大学汽车底盘集成与仿生全国重点实验室长春 130000

收稿日期:2025-06-18 修回日期:2026-03-29 发布日期:2026-08-29
作者简介:杨东坡(通信作者)，男，1991年出生，博士，硕士研究生导师。主要研究方向为新能源汽车节能与新能源技术。E-mail：yangdp@ujs.edu.cn;曾小华，男，1977年出生，博士，教授，博士研究生导师。主要研究方向为新能源汽车设计与控制。E-mail：jlu_dtzx@163.com
基金资助:
江苏省青年自然基金(BK20240872)、国家自然科学基金(52394265)和江苏大学大学生创新训练计划(202410299786X)资助项目。

Adaptive Energy Management of Hybrid Electric Vehicles Based on Gate Control Mechanism of Hybrid Prediction Model

YANG Dongpo¹, GAO Jiahui¹, SHI Dehua¹, ZENG Xiaohua²

1. College of Automotive and Transportation Engineering, Jiangsu University, Zhenjiang 212000;
2. National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun 130000

Received:2025-06-18 Revised:2026-03-29 Published:2026-08-29

摘要/Abstract

摘要： 为了改善车辆的节能效果，预测控制已成为混合动力车辆能源管理策略的研究热点。随着驾驶条件的多样性，预测模型精度直接影响车辆性能。为解决这一问题，提出一种基于门控机制的混合预测模型的自适应能量管理框架，主要集成个性化驾驶模式识别、门控机制的混合预测车速模型和模型预测控制。为提高模式识别精度，基于个性化混合聚类方法，提出一种融合个性化特征的贝叶斯优化多层感知机神经网络模型，较基于基础车辆特征的识别模型提升了2.69%；根据个性化驾驶模式识别的结果，融合门控机制混合专家网络进行速度预测，提高预测精度。并进一步分析了不同车速预测模型精度对混合动力车辆自适应能量管理策略的影响，提出的方法可以实现节约3.34%～8.65%的燃油消耗。

关键词: 混合动力车辆, 能源管理策略, 混合预测模型, 门控机制

Abstract: To improve the energy-saving effect of vehicles, predictive control has become a research hotspot in energy management strategies for hybrid electric vehicles. With the diversity of driving conditions, the accuracy of prediction models directly affects vehicle performance. To address this issue, an adaptive energy management framework based on a hybrid prediction model using gate control mechanism is proposed, which mainly integrates personalized driving pattern recognition, a hybrid prediction vehicle speed model with gate control mechanism, and model predictive control. To improve the accuracy of pattern recognition, a Bayesian optimized multi-layer perceptron neural network model integrating personalized features is proposed based on personalized mixed clustering method, which has improved by 2.69% compared to the recognition model based on basic vehicle features; Based on the results of personalized driving pattern recognition, a hybrid expert network with gate control mechanism is used for speed prediction to improve prediction accuracy. Furthermore, the impact of different vehicle speed prediction model accuracies on the adaptive energy management strategy of hybrid electric vehicles is analyzed, and the proposed method can achieve fuel consumption savings of 3.34%～8.65%.

Key words: hybrid electric vehicles, energy management strategies, hybrid prediction model, gate control mechanism

中图分类号:

U469

杨东坡, 高嘉辉, 施德华, 曾小华. 基于门控机制的混合预测模型的混合动力车辆自适应能量管理[J]. 机械工程学报, 2026, 62(14): 302-312.

YANG Dongpo, GAO Jiahui, SHI Dehua, ZENG Xiaohua. Adaptive Energy Management of Hybrid Electric Vehicles Based on Gate Control Mechanism of Hybrid Prediction Model[J]. Journal of Mechanical Engineering, 2026, 62(14): 302-312.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://www.cjmenet.com.cn/CN/10.3901/JME.260715

http://www.cjmenet.com.cn/CN/Y2026/V62/I14/302

参考文献

[1] 杨宁康，韩立金，刘辉，等. 基于效率优化的混合动力车辆强化学习能量管理策略研究[J]. 汽车工程，2021，43(7)：1046-1056. YANG Ningkang，HAN Lijin，LIU Hui，et al. Research on efficiency optimization based energy management strategy for a hybrid electric vehicle with reinforcement learning[J]. Automotive Engineering，2021，43(7)：1046-1056.
[2] 杨超，杜雪龙，王伟达，等. 基于端云协同优化的混合动力车辆实时能量管理策略研究[J]. 机械工程学报，2025，61(16)：227-238. YANG Chao，DU Xuelong，Wang Weida，et al. Research on real-time energy management strategy for hybrid electric vehicles based on edge-cloud collaborative optimization[J]. Journal of Mechanical Engineering，2025，61(16)：227-238.
[3] SUN Xiaodong，XUE Mingzhou，CAI Yingfeng，et al. Adaptive ECMS based on EF optimization by model predictive control for plug-in hybrid electric buses[J]. IEEE Transactions on Transportation Electrification，2023，9(2)：2153-2163.
[4] QI Chunyang，SONG Chuanxue，WANG Da，et al. Action advising and energy management strategy optimization of hybrid electric vehicle agent based on uncertainty analysis[J]. IEEE Transactions on Transportation Electrification，2024，10(3)：6940-6949.
[5] 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. 2019，119：109596.
[6] Peng Jiankun，He Hongwen，Xiong Rui. Rule based energy management strategy for a series–parallel plug-in hybrid electric bus optimized by dynamic programming[J]. Applied Energy，2016，185：1633-1643.
[7] 张风奇，胡晓松，许康辉，等. 混合动力汽车模型预测能量管理研究现状与展望[J]. 机械工程学报，2019，55(10)：86-108. ZHANG Fengqi，HU Xiaosong，XU Kanghui，et al. Current status and prospects for model predictive energy management in hybrid wlectric vehicles[J]. Journal of Mechanical Engineering，2019，55(10)：86-108.
[8] SHI Dehua，XU Han，WANG Shaohua，et al. Deep reinforcement learning based adaptive energy management for plug-in hybrid electric vehicle with double deep Q-network[J]. Energy，2024，305：132402.
[9] Jiang Q，Ossart F，Marchand C. Comparative study of real-time HEV energy management strategies[J]. IEEE Transactions on Vehicular Technology，2017，66(12)：10875-10888.
[10] 朱鹏兴，胡建军，李嘉佳，等. 考虑驾驶风格不确定性的插电式混合动力汽车个性化生态自适应巡航协同优化方法[J]. 机械工程学报，2025，61(18)：214-229. ZHU Pengxing，HU Jianjun，LI Jiajia，et al. Co-optimization method for personalized eco-adaptive cruise control of plug-in hybrid electric vehicles considering uncertainties in driving style[J]. Journal of Mechanical Engineering，2025，61(18)：214-229.
[11] Zhou Y，Li H，Ravey A，et al. An integrated predictive energy management for light-duty range-extended plug-in fuel cell electric vehicle[J]. Journal of Power Sources，2020，451：227780.
[12] Wu Yue，Huang Zhiwu，Zheng Yusheng，et al. Spatial-temporal data-driven full driving cycle prediction for optimal energy management of battery/supercapacitor electric vehicles[J]. Energy Conversion and Management，2023，277：116619.
[13] Ma Bin，Li Penghui. Optimal flexible power allocation energy management strategy for hybrid energy storage system with genetic algorithm-based model predictive control[J]. Energy，2025，324：135958.
[14] ZHANG Yang，LI Qingxin，WEN Chengqing，et al. Predictive equivalent consumption minimization strategy based on driving pattern personalized reconstruction[J]. Applied Energy，2024，367：123424.
[15] Zhou L，Yang D，Zeng X，et al. Multi-objective real-time energy management for series-parallel hybrid electric vehicles considering battery life[J]. Energy Conversion and Management，2023，290：117234.
[16] Zhou Yang，Yang Fan，Guo Yansiqi，et al. Adaptive energy management for fuel cell heavy trucks based on wavelet neural network speed predictor and real-time weight distribution[J]. IEEE Transactions on Transportation Electrification，2025，11(1)：5069-5083.
[17] Yang Dongpo，Liu Tong，Zhang Xuanming，et al. Construction of high-precision driving cycle based on Metropolis-Hastings sampling and genetic algorithm[J]. Transportation Research Part D：Transport and Environment，2023，118(2)：103715.
[18] 郭克难. 基于融合改进K-means聚类算法的数据检测技术[J]. 电子设计工程，2024，32(5)：41-45. GUO Kenan. Data detection technology based on fusion improved K-means clustering algorithm[J]. Electronic Design Engineering，2024，32(5)：41-45.
[19] Yang Dongpo，Liu Tong，Song Dafeng，et al. A real time multi-objective optimization guided-MPC strategy for power-split hybrid electric bus based on velocity prediction[J]. Energy，2023，276：127583.
[20] 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 Zhen，ZENG Lingxin，LIN Yonggang，et al. Adaptive energy management strategy for hybrid tractors based on condition prediction[J]. Journal of Xi’an Jiaotong University，2023，57(12)：201-210.
[21] 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 Shu，HAN Qi，ZHAO Xuan，et al. Predictive energy management strategy of plug-in hybrid electric vehicle with computer vision[J]. Automotive Engineering，2025，47(4)：625-635.
[22] ZHANG Dongxue，WANG Zhennan，JIAO Xiaohong，et al. Vehicle speed prediction using a convolutional neural network combined with a gated recurrent unit with attention[J]. Proceedings of the Institution of Mechanical Engineers，Part D：Journal of Automobile Engineering，2025，239(36)：2175-2191.
[23] QIAN Weizhu，NIELSEN T，ZHAO Yan，et al. Uncertainty-aware temporal graph convolutional network for traffic speed forecasting[J]. IEEE Transactions on Intelligent Transportation Systems，2024，25(8)：8578-8590.
[24] ZHANG Yuxin，YANG Yalian，ZOU Yunge. Research on collaborative energy management strategy for extended range electric vehicles under multi-lane scenarios[J]. Journal of Power Sources，2025，645：237193.
[25] 朱建功，戴海峰，王学远，等. 从电池管理到电化学数字电源[J]. 电气工程学报，2024，19(1)：3-22. ZHU Jiangong，DAI Haifeng，WANG Xueyuan，et al. Battery management towards the digitalized electrochemical power source[J]. Journal of Electrical Engineering，2024，19(1)：3-22.

基于门控机制的混合预测模型的混合动力车辆自适应能量管理

Adaptive Energy Management of Hybrid Electric Vehicles Based on Gate Control Mechanism of Hybrid Prediction Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	杨超, 杜雪龙, 王伟达, 杨刘权, 项昌乐. 基于端云协同优化的混合动力车辆实时能量管理策略研究[J]. 机械工程学报, 2025, 61(16): 227-238.
[2]	彭程, 陈俐. 混合动力车辆滑摩起动离合器扭矩实时估计方法[J]. 机械工程学报, 2025, 61(16): 217-226.
[3]	王峰, 张健, 徐兴, 王春海, 阙红波, 高扬. 行星耦合PHEV模式切换过程全频段瞬态扭振特性分析与主动抑制[J]. 机械工程学报, 2023, 59(4): 173-189.
[4]	姜丹娜, 黄英. 通过道路并联混合动力车辆的低频纵振主动控制[J]. 机械工程学报, 2017, 53(14): 68-76.
[5]	王伟达;项昌乐;韩立金;马越;刘辉. 机电复合传动系统综合控制策略[J]. , 2011, 47(20): 152-158.