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

doi:10.3901/JME.2017.16.086

机械工程学报 ›› 2017, Vol. 53 ›› Issue (16): 86-93.doi: 10.3901/JME.2017.16.086

• 特邀专栏：汽车先进动力系统的设计、优化与控制（下） • 上一篇下一篇

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

陈征¹, 刘亚辉², 杨芳¹

1. 宁波工程学院理学院宁波 315211;
2. 清华大学汽车安全与节能国家重点实验室北京 100084

收稿日期:2016-09-18 修回日期:2017-01-20 发布日期:2017-08-20
通讯作者: 刘亚辉(通信作者),男,1980年出生,博士。主要研究方向为人-车系统动力学及混合动力汽车。E-mail:liuyahui@tsinghua.edu.cn E-mail:liuyahui@tsinghua.edu.cn
作者简介:陈征,男,1977年出生,博士。主要研究方向为混合动力车辆能量管理策略。E-mail:jeffchenzheng@yahoo.com;杨芳,女,1978年出生,博士,副教授。主要研究方向为非线性系统控制。E-mail:liusha_02@163.com
基金资助:
国家自然科学基金资助项目（61503205，51375009）

Energy Management Strategy for Plug-in Hybrid Electric Bus with Evolutionary-Reinforcement Learning Method

CHEN Zheng¹, LIU Yahui², YANG Fang¹

1. Science School, Ningbo University of Technology, Ningbo 315211;
2. State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing 100084

Received:2016-09-18 Revised:2017-01-20 Published:2017-08-20

摘要/Abstract

摘要： 插电式混合动力客车越来越多出现在城市公交领域。为了更好地提升车辆的燃油经济性，整车能量管理策略成为一大研究热点。提出一种基于进化-增强学习方法的插电式混合动力公交车能量优化管理策略。首先，给出简化的车辆模型并基于增强学习系统给出能耗的优化目标函数；其次，针对此优化目标函数给出了初始的控制策略种群，并用进化算法求出最优的能量控制策略和最优能耗值；最后，通过仿真分析验证了算法的有效性。提出的新方法相对传统的电量消耗-维持（Charge depleting charge sustaining，CDCS）策略减少了大约12%的花费。

关键词: 插电式混合动力公交车, 进化算法, 能量管理策略, 同轴并联, 增强学习

Abstract: A growing number of plug-in hybrid electric buses(PHEB) emerge in the city traffic field. In order to achieve better economical performance of PHEB, the study of energy management strategy(EMS) for PHEB is become the focus of the research. This paper proposes a method of EMS for PHEB based on reinforcement learning. First of all, a simplified vehicle model is presented, and the function of optimal energy consumption is obtained through the reinforcement learning system. Secondly, initial population of control strategy respect to the cost function, and optimal control strategy and energy consumption value are obtained using evolutional algorithm. Finally, simulation results are presented to illustrate the effectiveness of this method. The cost of the energy consumption via novel strategy in this paper decrease about 12% compared with traditional CDCS strategy.

Key words: energy management strategy, evolutionary algorithm, plug-in hybrid electric bus, reinforcement learning, single-shaft parallel

中图分类号:

U469

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.

CHEN Zheng, LIU Yahui, YANG Fang. Energy Management Strategy for Plug-in Hybrid Electric Bus with Evolutionary-Reinforcement Learning Method[J]. Journal of Mechanical Engineering, 2017, 53(16): 86-93.

参考文献

[1] LI Liang, YANG Chao, ZHANG Yahui, et al. Correctional DP-based energy management strategy of plug-in hybrid electric bus for city-bus-route[J]. IEEE Transactions on Vehicular Technology, 2015, 64(7):2792-2803.
[2] LI Liang, YOU Sixiong, YANG Chao, et al. Driving-behavior-aware stochastic model predictive control for plug-in hybrid electric buses[J]. Applied Energy, 2016, 162(1):868-879.
[3] CHEN Zheng, LI Liang, YAN Bingjie, et al. Multi-mode energy management for plug-in hybrid electric buses based on driving cycles prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(10):2811-2821.
[4] PEREZ L, BOSSIO G, MOITRE D, et al. Optimization of power management in an hybrid electric vehicle using dynamic programming[J]. Mathematics and Computers in Simulation, 2006, 73(1):244-254.
[5] HANNAN M, AZIDIN F, MOHAMED A. Hybrid electric vehicles and their challenges:A review[J]. Renewable and Sustainable Energy Reviews, 2014, 29:135-150.
[6] OPILA D, WANG X, MCGEE R, et al. Real-time implementation and hardware testing of a hybrid vehicle energy management controller based on stochastic dynamic programming[J]. Journal of Dynamic Systems, Measurement, and Control, 2013, 135(2):021002.
[7] LI Liang, YAN Bingjie, YANG Chao, et al. Application oriented stochastic energy management for Plug-in Hybrid electric bus with AMT[J]. IEEE Transactions on Vehicular Technology, 2016, 65(6):4459-4470.
[8] NUESCH T, CEROFOLINI A, MANCINI G, et al. Equivalent consumption minimization strategy for the control of real driving NOx emissions of a diesel hybrid electric vehicle[J]. Energies, 2014, 7(5):3148-3178.
[9] GUPTA V. ECMS based hybrid algorithm for energy management in parallel hybrid electric vehicles[J]. HCTL Open International Journal of Technology Innovations and Research (IJTIR), 2015, 14:2321-1814.
[10] CAIRANO S, BERNARDINI D, BEMPORAD A, et al. Stochastic MPC with learning for driver-predictive management[J]. IEEE Transactions on Control Systems Technology, 2014, 22(3):1018-1031.
[11] BORHAN H, VAHIDI A, PHILLIPS A, et al. MPC-based energy management of a power-split hybrid electric vehicle[J]. IEEE Transactions on Control Systems Technology, 2012, 20(3):593-603.
[12] XIONG Weiwei, YIN Chengliang, ZHANG Yong, et al. Series-parallel hybrid vehicle control strategy design and optimization using real-valued genetic algorithm[J]. Chinese Journal of Mechanical Engineering, 2009, 22(6):862-868.
[13] NUESCH T, ELBERT P, FLANKL M, et al. Convex optimization for the energy management of hybrid electric vehicles considering engine start and gearshift costs[J]. Energies, 2014, 7(2):834-856.
[14] DEXTREIT C, KOLMANOVSKY I. Game theory controller for hybrid electric vehicles[J]. IEEE Transactions on Control Systems Technology, 2014, 22(2):652-663.
[15] KIM N, CHA S, PENG H. Optimal control of hybrid electric vehicles based on Pontryagin's minimum principle[J]. IEEE Transactions on Control Systems Technology, 2011, 19(5):1279-1287.
[16] DELPRAT S, LAUBER J, GUERRA T, et al. Control of a parallel hybrid powertrain:Optimal control[J]. IEEE Transactions on Vehicular Technology, 2004, 53(3):872-881.
[17] KAELBLING L, LITTMAN M, MOORE A. Reinforcement learning:A survey[J]. Journal of Artificial Intelligence Research, 1996:237-285.
[18] SUN Yong, MA Zilin, TANG Gongyou, et al. Estimation method of state-of-charge for lithium-ion battery used in hybrid electric vehicles based on variable structure extended kalman filter[J]. Chinese Journal of Mechanical Engineering, 2016, 29(4):717-726.
[19] SUN Yong, CHEN Zheng, YAN Bingjie, et al. A learning method for energy optimization of the pug-in hybrid electric bus[J]. Sci. China Tech. Sci., 2015, 58(7):1242-1249.

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

Energy Management Strategy for Plug-in Hybrid Electric Bus with Evolutionary-Reinforcement Learning Method

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]	李满宏, 张明路, 张建华, 田颖, 马艳悦. 基于增强学习的六足机器人自由步态规划[J]. 机械工程学报, 2019, 55(5): 36-44.
[2]	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.
[3]	管超, 张则强, 李云鹏, 贾林. 多行设备布局的一种多目标差分进化算法和线性规划混合方法[J]. 机械工程学报, 2019, 55(13): 160-174.
[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]	陈昊, 董金龙, 陈曦, 邬冠华, 周正干. GH4169晶粒尺寸的多参数超声评价方法[J]. 机械工程学报, 2018, 54(24): 18-26.
[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]	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.
[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]	魏彤, 田双彪. 基于RLS-DE算法的多变量径向磁轴承系统辨识[J]. 机械工程学报, 2016, 52(3): 143-150.
[10]	高建平, 赵金宝, 杨松, 郗建国. 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.
[11]	牟健慧, 郭前建, 高亮, 张伟, 牟建彩. 基于混合的多目标遗传算法的多目标流水车间逆调度问题求解方法^*[J]. 机械工程学报, 2016, 52(22): 186-197.
[12]	车林仙. 多样性保持离散差分进化算法及齿轮传动优化应用^*[J]. 机械工程学报, 2016, 52(21): 44-55.
[13]	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.
[14]	车林仙，杜力，黄勇刚. 球面四杆机构函数综合的带修复策略可行性规则差分进化算法[J]. 机械工程学报, 2015, 51(11): 31-40.
[15]	王前;杨志坚;丁康. 基于新自适应差分进化算法的Magic Formula轮胎模型参数辨识方法研究[J]. , 2014, 50(6): 120-128.