基于数据融合的混合动力汽车速度轮廓预测

doi:10.3901/JME.2024.06.342

机械工程学报 ›› 2024, Vol. 60 ›› Issue (6): 342-353.doi: 10.3901/JME.2024.06.342

扫码分享

基于数据融合的混合动力汽车速度轮廓预测

高凯^1,2, 罗攀¹, 谢进¹, 胡林¹, 陈彬¹, 杜荣华^1,2

1. 长沙理工大学汽车与机械工程学院长沙 410114;
2. 长沙理工大学智能道路与车路协同湖南省重点实验室长沙 410114

收稿日期:2023-06-22 修回日期:2023-12-11 出版日期:2024-03-20 发布日期:2024-06-07
通讯作者: 胡林，男，1978年出生，博士，教授，博士研究生导师。主要研究方向为车辆智能化，车辆安全。E-mail：hulin@csust.edu.cn
作者简介:高凯，男，1985年出生，博士，副教授，硕士研究生导师。主要研究方向为自动驾驶汽车感知与控制，智能交通与车联网应用。E-mail：kai_g@csust.edu.cn;罗攀，男，2000年出生。主要研究方向为新能源汽车，机器学习。E-mail：luo_pan@stu.csust.edu.cn
基金资助:
国家杰出青年科学基金(52325211)、中瑞国际合作(52211530054)、湖南省教育厅科学研究重点(21A0193)、长沙理工大学智能道路与车路协同湖南省重点实验室开放基金(kfj190701)和湖南省研究生科研创新(QL20230207)资助项目。

Hybrid Electric Vehicle Speed Profile Prediction Based on Data Fusion

GAO Kai^1,2, LUO Pan¹, XIE Jin¹, HU Lin¹, CHEN Bin¹, DU Ronghua^1,2

1. College of Automotive and Mechanical Engineering, Changsha University of Science & Technology, Changsha 410114;
2. Hunan Key Laboratory of Smart Roadwasy and Cooperative Vehicle-Infrastructure Systems, Changsha University of Science & Technology, Changsha 410114

Received:2023-06-22 Revised:2023-12-11 Online:2024-03-20 Published:2024-06-07

摘要/Abstract

摘要： 能量管理策略(Energy management strategy, EMS)可优化不同场景下混合动力汽车(Hybrid electric vehicles, HEV)的能量消耗，降低排放，提高燃油经济性。优化的关键之一是汽车速度轮廓的预测：预测未来区间的速度轮廓，进而计算需求功率，优化发动机和电动机的功率分配。因此提出一种融合驾驶行为和激光雷达数据的车辆速度轮廓智能预测方法，可应用于满足驾驶意愿的装备激光雷达的混合动力车辆能量优化。首先，构建一个基于门控循环单元(Gated recurrent unit, GRU)网络的驾驶意图识别模型，以从车辆状态中识别驾驶员的驾驶意图，实时考虑驾驶员的驾驶需求。其次，在智能车辆和传统车辆混行的交通场景中，依赖于车辆通信的速度轮廓预测方法可能不可用，研究的交通流速度由车辆上配备的激光雷达估计。算法采用联合概率数据关联跟踪器和交互多模型方法，实时得到前方车辆相对本车的速度，无需道路、工况等先验知识。最后，融合驾驶意图和前方车辆相对本车的速度，预测未来1 s内驾驶员期望的速度曲线。试验结果表明，GRU模型训练的准确率在85%～95%，识别的准确率可达到88%，可有效的识别驾驶员的驾驶意图。提出的方法具有良好的测速精度。预测的速度和实际速度的差距在较小范围内，可用于EMS中，进而为动力电池管理系统(Battery management strategy, BMS)合理控制动力电池的能量输出提供依据。

关键词: 能量管理, 速度轮廓预测, 数据融合, 驾驶意图, 激光雷达

Abstract: Energy Management Strategy (EMS) can optimize energy consumption, reduce emissions and improve fuel economy of hybrid electric vehicles (HEV) in different scenarios. One of the keys of optimization is the prediction of vehicle speed profile： predict the speed profile of the future interval, and then calculate the power demand, and optimize the power distribution of the engine and motor. Therefore, an intelligent prediction method of vehicle velocity profile based on driving behavior and lidar data is proposed, which could be applied to energy optimization of lidar equipped hybrid electric vehicle to satisfy driving intention. Firstly, a driving intention recognition model based on gated recurrent unit (GRU) network is constructed to identify driving intentions from vehicle states, and driver's driving needs are considered in real time. Secondly, in the traffic scene where intelligent vehicles and traditional vehicles are mixed, the speed profile prediction method relying on vehicle communication may not be available. In this study, the traffic flow speed is estimated by lidar equipped on vehicles. The algorithm used the Joint Probability Data Association tracker and Interactive Multipul Model method to get the speed of the vehicle in front relative to the vehicle in real time, without prior knowledge of road and condition. Finally, the driver's expected speed curve in the next second is predicted by integrating the driving intention and the relative speed of the vehicle ahead. Experimental results show that the training accuracy of GRU model is between 85%-95%, and the recognition accuracy can reach 88%, which can effectively identify the driver's driving intention. The proposed method has good velocity measurement accuracy. Prediction speed and actual speed of the gap in a smaller range, can be used for EMS, then for power battery management system (BMS) provides the basis for reasonable control of power battery energy output.

Key words: energy management, velocity profile prediction, data fusion, driving intention, lidar

中图分类号:

U461

高凯, 罗攀, 谢进, 胡林, 陈彬, 杜荣华. 基于数据融合的混合动力汽车速度轮廓预测[J]. 机械工程学报, 2024, 60(6): 342-353.

GAO Kai, LUO Pan, XIE Jin, HU Lin, CHEN Bin, DU Ronghua. Hybrid Electric Vehicle Speed Profile Prediction Based on Data Fusion[J]. Journal of Mechanical Engineering, 2024, 60(6): 342-353.

参考文献

[1] 熊瑞. 动力电池管理系统核心算法[M]. 北京：机械工业出版社， 2018. XIONG Rui. Core algorithm of battery management system for EVs[M]. Beijing：China Machine Press，2018.
[2] 胡林，田庆韬，黄晶，等. 电动汽车锂离子电池-超级电容混合储能系统能量分配与参数匹配研究综述[J].机械工程学报，2022，58(16)：224-237. HU Lin，TIAN Qingtao，HUANG Jing，et al. Review on energy distribution and parameter matching of lithium-ion battery-super capacitor hybrid energy storage system for electric vehicles[J]. Journal of Mechanical Engineering，2022，58(16)： 224-237.
[3] GAO K，LUO P，XIE J，et al. Energy management of plug-in hybrid electric vehicles based on speed prediction fused driving intention and LIDAR[J]. Energy，2023，284：128535.
[4] SUN C，MOURA S J，HU X，et al. Dynamic traffic feedback data enabled energy management in plug-in hybrid electric vehicles[J]. IEEE Transactions on Control Systems Technology，2015，23(3)：1075-1086.
[5] 高建平，赵金宝，杨松，等. 基于驾驶意图的插电式混合动力公交车控制策略[J]. 机械工程学报，2016，52(24)：107-114. GAO Jianping，ZHAO Jinbao，YANG Song，et al. Control strategy of plug-in hybrid electric bus based on driver intention[J]. Journal of Mechanical Engineering，2016，52(24)：107-114．
[6] BENDER F A，KASZYNSKI M，SAWODNY O. Drive cycle prediction and energy management optimization for hybrid hydraulic vehicles[J]. IEEE Transactions on vehicular technology，2013，62(8)：3581-3592.
[7] LIU T，HU X，LI S E，et al. Reinforcement learning optimized look-ahead energy management of a parallel hybrid electric vehicle[J]. IEEE/ASME transactions on mechatronics，2017，22(4)：1497-1507.
[8] XIE S，HU X，XIN Z，et al. Time-efficient stochastic model predictive energy management for a plug-in hybrid electric bus with an adaptive reference state-of-charge advisory[J]. IEEE Transactions on Vehicular Technology，2018，67(7)：5671-5682.
[9] 杨超，焦晓红，李亮，等. 面向公交客车应用的插电式混合动力实时优化策略研究[J]. 机械工程学报， 2015，51(22)：111-119. YANG Chao，JIAO Xiaohong，LI Liang，et al. Research on city-bus application-oriented real-time optimal energy management strategy for plug-in hybrid electric bus[J]. Journal of Mechanical Engineering， 2015，51(22)：111-119.
[10] LI G，ZHU F，QU X，et al. Driving style classification based on driving operational pictures[J]. IEEE Access，2019，7：90180-90189.
[11] WANG R，LUKIC S M. Review of driving conditions prediction and driving style recognition based control algorithms for hybrid electric vehicles[C]// 2011 IEEE Vehicle power and propulsion conference. IEEE，2011：1-7.
[12] LÜ C，HU X，SANGIOVANNI-VINCENTELLI A，et al. Driving-style-based codesign optimization of an automated electric vehicle：A cyber-physical system approach[J]. IEEE Transactions on Industrial Electronics，2018，66(4)：2965-2975.
[13] CHEN C，LIU L，QIU T，et al. Driver’s intention identification and risk evaluation at intersections in the Internet of vehicles[J]. IEEE Internet of Things Journal，2018，5(3)：1575-1587.
[14] LI M，CAO H，SONG X，et al. Shared control driver assistance system based on driving intention and situation assessment[J]. IEEE Transactions on Industrial Informatics，2018，14(11)：4982-4994.
[15] LEI Y，ZHANG Y，FU Y，et al. Research on adaptive gearshift decision method based on driving intention recognition[J]. Advances in Mechanical Engineering，2018，10(10)：1-12.
[16] YI D，SU J，LIU C，et al. Trajectory clustering aided personalized driver intention prediction for intelligent vehicles[J]. IEEE Transactions on Industrial Informatics，2018，15(6)：3693-3702.
[17] PENG B，ZHANG H，XUAN F，et al. Torque distribution strategy of electric vehicle with in-wheel motors based on the identification of driving intention[J]. Automotive Innovation，2018，1：140-146.
[18] SALEH K，HOSSNY M，NAHAVANDI S. Driving behavior classification based on sensor data fusion using LSTM recurrent neural networks[C]// 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). IEEE，2017：1-6.
[19] LIU Y，ZHAO P，QIN D，et al. Driving intention identification based on long short-term memory and a case study in shifting strategy optimization[J]. IEEE Access，2019，7：1-12.
[20] YUAN J，YANG L. Predictive energy management strategy for connected 48V hybrid electric vehicles[J]. Energy，2019，187：115952.
[21] 张利鹏，贾启康，刘威，等. 基于驾驶意图识别的多模耦合驱动系统能量管理[J]. 机械工程学报，2020，55(18)：112-124. ZHANG Lipeng，JIA Qikang，LIU Wei，et al. Energy management of multi-mode coupling drive system based on driver intention recognition[J]. Journal of Mechanical Engineering，2019，55(18)：112-124.
[22] 邓涛，罗远平. 基于驾驶意图云模型识别的混合动力汽车A-ECMS的构建[J]. 汽车安全与节能学报，2020，11(3)：305. DENG Tao，LUO Yuanping. Construction of hybrid electric vehicle a-ecms based on cloud model recognition of driving intention[J]. Journal of Automotive Safety and Energy，2020，11(3)：305-313.
[23] 季学武，费聪，何祥坤，等. 基于LSTM网络的驾驶意图识别及车辆轨迹预测[J]. 中国公路学报，2019，32(6)：34-42. JI Xuewu，FEI Chong，HE Xiangkun，et al. Driving intention identification and vehicle trajectory prediction based on lstm network[J]. China Journal of Highways，2019，32(6)：34-42.
[24] 宋晓琳，曾艳兵，曹昊天，等. 基于长短期记忆网络的换道意图识别方法[J]. 中国公路学报，2021，34(11)：236-245. SONG Xiaolin，ZENG Yanbing，CAO Hao-tian，et al， Lane change intention recongnition method based on LSTM network[J]. China Journal of Highways，2021，34(11)：236-245.
[25] YANG J Y，CHOU L D，TUNG C F，et al. Average-speed forecast and adjustment via VANETs[J]. IEEE Transactions on Vehicular Technology，2013，62(9)：4318-4327.
[26] ZHANG F，XI J，LANGARI R. Real-time energy management strategy based on velocity forecasts using V2V and V2I communications[J]. IEEE Transactions on Intelligent Transportation Systems，2016，18(2)： 416-430.
[27] JIANG B，FEI Y. Traffic and vehicle speed prediction with neural network and hidden markov model in vehicular networks[C]// 2015 IEEE Intelligent Vehicles Symposium (IV). IEEE，2015：1082-1087.
[28] SUN C，HU X，MOURA S J，et al. Velocity predictors for predictive energy management in hybrid electric vehicles[J]. IEEE Transactions on Control Systems Technology，2014，23(3)：1197-1204.
[29] WOJKE N，HÄSELICH M. Moving vehicle detection and tracking in unstructured environments[C]// 2012 IEEE International Conference on Robotics and Automation. IEEE，2012：3082-3087.
[30] DEWAN A，CASELITZ T，TIPALDI G D， et al. Motion-based detection and tracking in 3d lidar scans[C]// 2016 IEEE International Conference on Robotics and Automation (ICRA). IEEE，2016：4508-4513.
[31] LUO Z，HABIBI S，MOHRENSCHILDT M V. LiDAR based real time multiple vehicle detection and tracking[J]. International Journal of Computer and Information Engineering，2016，10(6)：1125-1132.

基于数据融合的混合动力汽车速度轮廓预测

Hybrid Electric Vehicle Speed Profile Prediction Based on Data Fusion

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	蒋翔宇, 冯毅雄, 洪兆溪, 胡炳涛, 司恒远, 谭建荣. 基于多级数据融合的核电站运行功能健康状态评估[J]. 机械工程学报, 2024, 60(4): 200-211.
[2]	李琳, 赵万忠, 王春燕. 基于Bi-GLSTM网络的车辆驾驶意图分析与识别[J]. 机械工程学报, 2024, 60(10): 51-63.
[3]	魏小栋, 孙超, 刘波, 霍为炜, 任强, 孙逢春. 燃料电池汽车车速与能量联合优化[J]. 机械工程学报, 2023, 59(8): 204-212.
[4]	吕黎曙, 邓朝晖, 岳文辉, 万林林, 刘涛. 单颗磨粒磨削机理与数据融合驱动的磨削过程建模分析[J]. 机械工程学报, 2023, 59(7): 200-215.
[5]	高锋阳, 张浩然. 氢燃料电池混合动力有轨电车的自适应瞬时等效能耗优化[J]. 机械工程学报, 2023, 59(6): 226-238.
[6]	高锋阳, 张浩然, 王文祥, 李明明. 规则控制与行驶工况相结合的现代有轨电车能量管理策略[J]. 机械工程学报, 2023, 59(4): 221-231.
[7]	金贤球, 雷涛, 闵志豪, 宋丽娜, 张星雨, 张晓斌. 分布式电推进飞机能量优化动态管理技术研究^*[J]. 电气工程学报, 2023, 18(3): 315-331.
[8]	王跃飞, 王志, 孙睿, 王超, 肖锴, 潘斌. 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.
[9]	张佐乾, 吴红飞, 杨帆, 杜益如, 余海涛, 刘越, 邢岩. 高峰均比脉冲功率独立电源系统关键技术研究综述^*[J]. 电气工程学报, 2023, 18(1): 43-55.
[10]	柳晨光, 郭珏菡, 吴勇, 初秀民, 吴文祥, 雷超凡. 无人水面艇三维激光雷达目标实时识别系统[J]. 机械工程学报, 2022, 58(4): 202-211.
[11]	刘永刚, 于丰宁, 章新杰, 陈峥, 秦大同. 基于激光点云与图像融合的3D目标检测研究[J]. 机械工程学报, 2022, 58(24): 289-299.
[12]	张晗, 杨继斌, 张继业, 徐晓惠. 燃料电池有轨电车能量管理与速度曲线协同优化[J]. 机械工程学报, 2022, 58(10): 169-179.
[13]	方燕琼, 唐升卫, 顾博川, 代仕勇, 叶向前. 基于二进制位缺失标识与改进D-S证据理论的数据融合技术研究^*[J]. 电气工程学报, 2021, 16(3): 184-191.
[14]	唐小林, 陈佳信, 刘腾, 李佳承, 胡晓松. 基于深度强化学习的混合动力汽车智能跟车控制与能量管理策略研究[J]. 机械工程学报, 2021, 57(22): 237-246.
[15]	彭湃, 耿可可, 殷国栋, 庄伟超, 刘帅鹏, 徐利伟. 基于传感器融合里程计的相机与激光雷达自动重标定方法[J]. 机械工程学报, 2021, 57(20): 206-214.