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

doi:10.3901/JME.2023.18.271

机械工程学报 ›› 2023, Vol. 59 ›› Issue (18): 271-282.doi: 10.3901/JME.2023.18.271

扫码分享

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

王跃飞^1,2, 王志¹, 孙睿¹, 王超¹, 肖锴¹, 潘斌¹

1. 合肥工业大学机械工程学院合肥 230009;
2. 安徽江淮汽车集团股份有限公司合肥 230022

收稿日期:2022-10-18 修回日期:2023-07-18 出版日期:2023-09-20 发布日期:2023-12-07
通讯作者: 王跃飞(通信作者),男,1977年出生,博士,副教授,硕士研究生导师。主要研究方向为车联网与智能汽车、汽车能量管理系统、工业互联网。E-mail:yuefeiw@hfut.edu.cn
作者简介:王志,男,1996年出生。主要研究方向为智能网联汽车能量管理策略。E-mail:wz_insomnia@163.com
基金资助:
国家自然科学基金(61202096)和安徽省重点研究与开发计划(202104a05020018)资助项目。

Equivalent Emission Minimization Strategy of Intelligent Connected HEV Based on Multi-step Prediction of Driving Intention

WANG Yuefei^1,2, WANG Zhi¹, SUN Rui¹, WANG Chao¹, XIAO Kai¹, PAN Bin¹

1. School of Mechanical Engineering, Hefei University of Technology, Hefei 230009;
2. Anhui Jianghuai Automobile Group Corp., Ltd., Hefei 230022

Received:2022-10-18 Revised:2023-07-18 Online:2023-09-20 Published:2023-12-07

摘要/Abstract

摘要： 车辆“碳达标”与“碳中和”是实现全社会碳达标的重要组成部分。为降低智能网联混合动力汽车(Intelligent connected HEV，ICHEV)总排放量，提出一种基于驾驶意图多步预测(Multi-step prediction of driving intention，MPDI)的ICHEV等效排放最小(Equivalent emissions minimization strategy，EEMS)能量在线管理策略。首先，给出车联网V2X下驾驶意图在线预测流程，构建基于CNN-LSTM的驾驶意图单步预测深度学习模型，提出驾驶意图多步递归预测方法；其次，考虑到发动机最大效率区与尾气最小排放区不一致，建立ICHEV等效尾气排放模型，提出基于EEMS的能量在线管理策略；再次，分析驾驶意图频繁变化对EEMS的扰动影响，设计基于MPDI的整车需求功率求解算法，给出EEMS策略的哈密顿函数求解方法。实验结果表明，基于MPDI的EEMS策略可有效降低ICHEV尾气排放量，与传统能量管理策略相比平均降低了25%。

关键词: 智能网联HEV, 能量管理策略, 驾驶意图预测, 等效尾气排放

Abstract: Vehicle "carbon compliance" and "carbon neutralization" are important components to achieve the carbon compliance of the whole society. To reduce the total emissions of Intelligent Connected HEV(ICHEV), an Equivalent Emissions Minimization Strategy(EEMS) of ICHEV based on multi-step prediction of driving intention(MPDI) is proposed. First, the online prediction process of driving intention under V2X is presented, a deep learning model of CNN-LSTM is constructed to make single-step prediction of driving intention, and a multi-step recursive prediction method of driving intention is proposed. Second, considering the inconsistency between the maximum efficiency zone and the minimum tailpipe emission zone of engine, an equivalent emission model of ICHEV energy consumption is established, and an energy online management strategy based on EEMS is proposed. Third, the disturbance effect of frequent change of driving intention on EEMS is analyzed, the algorithm for solving the whole vehicle demand power based on multi-step prediction of driving intention is given, and the Hamiltonian function solution method of EEMS is given. The experimental results show that the EEMS based on multi-step prediction of driving intention can effectively reduce ICHEV exhaust emissions by 25% on average compared with the traditional energy management strategy.

Key words: intelligent connected HEV, energy management strategy, driving intention prediction, equivalent exhaust emission

中图分类号:

TN915

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.

WANG Yuefei, WANG Zhi, SUN Rui, WANG Chao, XIAO Kai, PAN Bin. 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.

参考文献

[1] 王钦普,游思雄,李亮,等. 插电式混合动力汽车能量管理策略研究综述[J]. 机械工程学报,2017,53(16):1-19. WANG Qinpu,YOU Sixiong,LI Liang,et al. Survey on energy management strategy for plug-in hybrid electric vehicles[J]. Journal of Mechanical Engineering,2017,53(16),1-19.
[2] SHABBIR W,EVANGELOU S A. Threshold-changing control strategy for series hybrid electric vehicles[J]. Applied Energy,2019,235:761-775.
[3] 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,2019,55(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.
[4] LI J,ZHOU Q,WILLIAMS H,et al. Back-to-back competitive learning mechanism for fuzzy logic based supervisory control system of hybrid electric vehicles[J]. IEEE Transactions on Industrial Electronics,2020,67(10):8900-8909.
[5] LEE H,CHA S W. Reinforcement learning based on equivalent consumption minimization strategy for optimal control of hybrid electric vehicles[J]. SAE International Journal of Alternative Powertrains,2021,9:860-871.
[6] LI H,ZHOU Y,GUALOUS H,et al. Optimal cost minimization strategy for fuel cell hybrid electric vehicles based on decision-making framework[J]. IEEE Transactions on Industrial Informatics,2021,17(4):2388-2399.
[7] PAN C,LIANG Y,CHEN L,et al. Optimal control for hybrid energy storage electric vehicle to achieve energy saving using dynamic programming approach[J]. Energies,2019,12(4):588.
[8] 唐小林,李珊珊,王红,等. 网联环境下基于分层式模型预测控制的车队能量控制策略研究[J]. 机械工程学报,2020,56(14):119-128. TANG Xiaolin,LI Shanshan,WANG Hong,et al. Research on energy control strategy based on hierarchical model predictive control in connected environment[J]. Journal of Mechanical Engineering,2020,56(14):119-128.
[9] LI X,WANG W,YUAN Y,et al. An online optimal energy management strategy for a dual-mode power-split hybrid electric vehicle based on hybrid MPC algorithm[J]. Journal of Physics Conference Series,2021,1754(1):012135.
[10] LEI Z Z,QIN D,HOU L L,et al. An adaptive equivalent consumption minimization strategy for plug-in hybrid electric vehicles based on traffic information[J]. Energy,2020,190:1034-1044.
[11] ZHANG S W,LUO Y G,WANG J M,et al. Predictive energy management strategy for fully electric vehicles based on preceding vehicle movement[J]. IEEE Transactions on Intelligent Transportation Systems,2017,8(11):3049-3060.
[12] ZHANG Y J,GUO C,LIU Y G,et al. A novel strategy for power sources management in connected plug-in hybrid electric vehicles based on mobile edge computation framework[J]. Journal of Power Sources,2020,477:1764-1776.
[13] 刘晏宇,喻凡,宋娟娟,等. 采用神经网络与模糊控制的制动需求识别[J]. 中国机械工程,2020,31(23):2847-2855. LIU Yanyu,YU Fan,SONG Juanjuan,et al. Detection of brake requests using neural network and fuzzy control[J]. China Mechanical Engineering,2020,31(23):2847-2855.
[14] 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 Cong,HE Xiangkun,et al. Intention recognition and trajectory prediction for vehicles using LSTM network[J]. China Journal of Highway and Transport,2019,32(6):34-42.
[15] FU J T,FU Z M,SONG S Z. Model predictive control-based control strategy to reduce driving-mode switching times for parallel hybrid electric vehicle[J]. IEEE Transactions on Industrial Informatics,2021,43(1):167-177.
[16] KERNER B S,KLENOV S L,BRAKEMEIER A. Testbed for wireless vehicle communication:A simulation approach based on three-phase traffic theory[C]//2008 IEEE Intelligent Vehicles Symposium,2008:150-185.
[17] GUO J,HE H,PENG J,et al. A novel MPC-based adaptive energy management strategy in plug-in hybrid electric vehicles[J]. Energy,2019,175:378-392.
[18] The MathWorks,Inc. Matlab R2022b documentation,build hybrid electric vehicle P2 model[EB/OL].[2022-12-22]. https://www.mathworks.cn/help/autoblks/ug/explore-the-hybrid-electric-vehicle-p2-reference-application.html.

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

Equivalent Emission Minimization Strategy of Intelligent Connected HEV Based on Multi-step Prediction of Driving Intention

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

本文评价

[1]	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.
[2]	唐小林, 李珊珊, 王红, 段紫文, 李以农, 郑玲. 网联环境下基于分层式模型预测控制的车队能量控制策略研究[J]. 机械工程学报, 2020, 56(14): 119-128.
[3]	刘辉, 李训明, 王伟达, 韩立金, 闫正军. 基于最优功率分配因子的插电式混合动力汽车实时能量管理策略研究[J]. 机械工程学报, 2019, 55(4): 91-101.
[4]	张风奇, 胡晓松, 许康辉, 唐小林, 崔亚辉. 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.
[5]	王钦普, 游思雄, 李亮, 杨超. 插电式混合动力汽车能量管理策略研究综述[J]. 机械工程学报, 2017, 53(16): 1-19.
[6]	刘永刚, 李杰, 秦大同, 雷贞贞, 解庆波, 杨阳. 基于多工况优化算法的混合电动汽车参数优化[J]. 机械工程学报, 2017, 53(16): 61-69.
[7]	陈征, 刘亚辉, 杨芳. 基于进化-增强学习方法的插电式混合动力公交车能量管理策略[J]. 机械工程学报, 2017, 53(16): 86-93.
[8]	秦大同, 詹森, 曾育平, 苏岭. 基于驾驶风格识别的混合动力汽车能量管理策略[J]. 机械工程学报, 2016, 52(8): 162-169.
[9]	杨超, 焦晓红, 李亮, 游思雄, 颜丙杰, 马兹林. 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.
[10]	邹渊;陈锐;侯仕杰;胡晓松. 基于随机动态规划的混合动力履带车辆能量管理策略[J]. , 2012, 48(14): 91-96.
[11]	张博;郑贺悦;王成. 可外接充电混合动力汽车能量管理策略[J]. , 2011, 47(6): 113-120.
[12]	舒红;秦大同;胡明辉;杨亚联;叶明. 轻度混合动力汽车再生制动能量管理策略[J]. , 2009, 45(1): 167-173.
[13]	张承慧;吴剑;崔纳新. 基于无级变速器的并联式混合动力汽车能量管理策略[J]. , 2007, 43(10): 114-118.
[14]	朱元;田光宇;陈全世;吴昊. 混合动力汽车能量管理策略的四步骤设计方法[J]. , 2004, 40(8): 127-133.