基于工况识别与多元非线性回归优化的能量管理策略

中国机械工程

基于工况识别与多元非线性回归优化的能量管理策略

孙蕾1;林歆悠2;林国发3

1.华侨大学机电及自动化学院，厦门，361021
2.福州大学机械工程及自动化学院，福州,350002
3.上汽集团技术中心，上海,201804

出版日期:2017-11-25 发布日期:2017-11-23
基金资助:
国家自然科学基金资助项目（51505086）
National Natural Science Foundation of China （No. 51505086）

Energy Management Strategy Based on Type Recognition and Multivariate Nonlinear Regression Optimization

SUN Lei1;LIN Xinyou2;LIN Guofa3

1.College of Mechatronic and Automation,Huaqiao University,Xiamen，Fujian,361021
2.College of Mechanical Engineering and Automation,Fuzhou University,Fuzhou，350002
3.SAIC Motor Corporation Limited(SAIC Motor) Technical Center,Shanghai，201804

Online:2017-11-25 Published:2017-11-23
Supported by:
National Natural Science Foundation of China （No. 51505086）

摘要/Abstract

摘要： 为给混合动力汽车智能管理策略提供基础，开展了基于学习向量化(LVQ)神经网络的工况模式识别算法研究。选取4种典型微观道路类型工况和3类标准循环工况，提取11个参数为训练特征数据，建立了LVQ神经网络工况模式识别算法；在此基础上，以某款混联式动力系统为例，结合多元非线性回归分析制定相应控制策略；最后，基于Simulink仿真平台建立LVQ神经网络工况模式识别及整车仿真模型，分别采用中国城市典型循环工况以及构建UDDS+NYCC+UDDS的标准行驶工况进行道路工况识别验证。结果表明，所建立的LVQ神经网络工况识别算法可以准确识别工况模式并能有效提高能量管理策略的控制效果。

关键词: 学习向量化神经网络, 工况识别, 循环工况, 能量管理

Abstract: The type recognition algorithm of driving conditions was studied based on LVQ neural network，to provide the basis for the intelligent management strategy of hybrid electric vehicles. First, 11 characteristic parameters were extracted from 4 typical road type conditions and the 3 kinds of standard cycle conditions to train the data. Then, the LVQ neural network type recognition algorithm of driving condition was developed. Based on this, a hybrid power system was as an example, which combined with multiple nonlinear regression analysis to develop the corresponding control strategy. Finally, LVQ neural network type recognition simulation model of driving condition was established based on the Simulink simulation platform, type recognition tests were carried on under the Chinese city typical cycle road conditions, standard condition recognition tests were carried on by constructing UDDS+NYCC+UDDS driving conditions. The results show that the established LVQ neural network may accurately identify the type of driving condition types and the control effectiveness of the energy management strategy is improved effectively.

Key words: learning vector quantization(LVQ) neural network, type recognition, driving cycle type, energy management

中图分类号:

U461.8

孙蕾1;林歆悠2;林国发3. 基于工况识别与多元非线性回归优化的能量管理策略[J]. 中国机械工程.

SUN Lei1;LIN Xinyou2;LIN Guofa3. Energy Management Strategy Based on Type Recognition and Multivariate Nonlinear Regression Optimization[J]. China Mechanical Engineering.

参考文献

[1]林歆悠，孙冬野.基于工况识别的混联式混合动力客车控制策略研究[J]. 中国机械工程,2012, 23(7): 869-874.
LIN Xinyou, SUN Dongye. Development of Control Strategy for a Series-parallel Hybrid Electric City Bus Based on Roadway Type Recognition[J].China Mechanical Engineering, 2012, 23(7): 869-874.
[2]PARK J, CHEN Z, KILIARIS L, et al. Intelligent Vehicle Power Control Based on Machine Learning of Optimal Control Parameters and Prediction of Road Type and Traffic Congestion[J]. IEEE Transactions on Vehicular Technology, 2009,58(9):4741-4756.
[3]HUANG X, TAN Y, HE X. An Intelligent Multifeature Statistical Approach for the Discrimination of Driving Conditions of a Hybrid Electric Vehicle [J]. IEEE Transactions on Intelligent Transportation Systems, 2011,12(1): 453-465.
[4]ZHU W, BARTH M. Vehicle Trajectory-based Road Type and Congestion Recognition Using Wavelet Analysis [C]// IEEE Intelligent Transportation Systems Conference. Toronto, 2006: 876-884.
[5]HE H, SUN C, ZHANG X. A Method for Identification of Driving Patterns in Hybrid Electric Vehicles Based on a LVQ Neural Network[J]. Energies, 2012,5(9): 3363-3380.
[6]田毅, 张欣, 张良，等. 神经网络工况识别的混合动力电动汽车模糊控制策略[J].控制理论与应用, 2011,28(3): 363-369.
TIAN Yi, ZHANG Xin, ZHANG Liang, et al. Fuzzy Control Strategy for Hybrid Electric Vehicle Based on Neural Network Identification of Driving Conditions[J]. Control Theory & Applications, 2011,28(3): 363-369.
[7]詹森, 秦大同,曾育平. 基于遗传优化K均值聚类算法工况识别的混合动力汽车能量管理策略[J]. 中国公路学报，2016，29(4): 130-137.
ZHAN Sen，QIN Datong，ZENG Yuping. Energy Management Strategy of HEV Based on Driving Cycle Recognition Using Genetic Optimized K-means Clustering Algorithm[J]. China Journal of Highway and Transport, 2016，29(4): 130-137.
[8]石琴, 郑与波, 姜平. 基于运动学片段的城市道路行驶工况的研究[J]. 汽车工程, 2011, 33(3):256-261.
SHI Qin, ZHENG Yubo, JIANG Ping. A Research on Driving Cycle of City Roads Based on Microtrips[J]. Automotive Engineering, 2011, 33(3): 256-261.
[9]JIE X，HAN X，YE H，et al．Driving Cycle Recognition for Hybrid Electric Vehicle[C]// Transportation Electrification Asia-Pacific (ITEC Asia-Pacific). IEEE Conference and Expo. Beijing，2014：1-6.
[10]林歆悠，孙冬野. 基于ECMS混联式混合动力客车工况识别控制策略[J].湖南大学学报(自然科学版),2012,39(10):43-49.
LIN Xinyou, SUN Dongye. Driving Pattern Recognition Based on ECMS and Its Application to Control Strategy for a Series-parallel Hybrid Electric Bus[J].Journal of Hunan University（Naturnal Science）,2012,39(10):43-49.
[11]邓涛,卢任之,李亚南,等. 基于LVQ工况识别的混合动力汽车自适应能量管理控制策略[J]. 中国机械工程,2016,27(3):420-425.
DENG Tao, LU Renzhi, LI Yanan,et al. Adaptive Energy Control Strategy of HEV Based on Driving Cycle Recognition by LVQ Algorithm[J]. Journal of Mechanical Engineering ,2016,27(3):420-425.
[12]ZHANG S, XIONG R. Adaptive Energy Management of a Plug-in Hybrid Electric Vehicle Based on Driving Pattern Recognition and Dynamic Programming [J]. Applied Energy, 2015,155 :68-78.

[1]	高爱云;张风丽. 增程式混合动力洗扫车能量管理策略研究[J]. 中国机械工程, 2019, 30(19): 2356-2363.
[2]	吴进军1;颜丙杰2;方继根1;王西峰1;谢志鹏3;史洋4;李亮2. 插电式混合动力汽车的次优能量管理策略[J]. 中国机械工程, 2019, 30(11): 1336-1342.
[3]	殷国栋, 李广民, 朱侗, 陈建松. [分布式驱动电动汽车动力学控制]四轮驱动电动汽车多Agent能量管理体系研究[J]. 中国机械工程, 2018, 29(15): 1765-1771.
[4]	石琴, 仇多洋, 吴冰, 李一鸣, 刘炳姣. [智能感知]基于粒子群优化支持向量机算法的行驶工况识别及应用[J]. 中国机械工程, 2018, 29(15): 1875-1883.
[5]	钱立军1;荆红娟1;邱利宏1，2. 基于随机模型预测控制的四驱混合动力汽车能量管理[J]. 中国机械工程, 2018, 29(11): 1342-1348.
[6]	邓涛;韩海硕;罗俊林. 基于动态规划算法的混合动力汽车改进型ECMS能量管理控制研究[J]. 中国机械工程, 2018, 29(03): 326-332.
[7]	司远, 钱立军, 邱利宏, 李浩. 基于等效油耗最小的四驱混合动力汽车能量管理[J]. 中国机械工程, 2017, 28(09): 1112-1117.
[8]	阚萍, 邱利宏, 钱立军, 王金波. 基于Willans Line的双轴驱动混合动力越野车实时能量管理[J]. 中国机械工程, 2016, 27(11): 1546-1553.
[9]	郑悦 , 谢长君, 黄亮 , 全书海 , 谭保华, . 锂电池与超级电容混合电动汽车系统在环综合测试[J]. 中国机械工程, 2016, 27(06): 821-826.
[10]	邓涛, 卢任之, 李亚南, 林椿松. 基于LVQ工况识别的混合动力汽车自适应能量管理控制策略[J]. 中国机械工程, 2016, 27(03): 420-425.
[11]	秦大同1;彭志远2;刘永刚1;段志辉3;杨阳1. 基于工况识别的混合动力汽车动态能量管理策略[J]. 中国机械工程, 2014, 25(11): 1550-1555.
[12]	许世景1，2;吴志新1，3. 基于PMP的HEV全局最优能量管理策略研究[J]. 中国机械工程, 2014, 25(1): 138-141.
[13]	林歆悠1;薛瑞1;孙冬野2 . 混联式混合动力客车能量管理实时优化算法研究[J]. 中国机械工程, 2013, 24(18): 2539-2543.
[14]	林歆悠, 孙冬野. 基于工况识别的混联式混合动力客车控制策略研究[J]. 中国机械工程, 2012, 23(7): 869-874.
[15]	李振磊, 林逸, 龚旭. 基于Start-Stop技术的微混轿车仿真及试验研究 [J]. 中国机械工程, 2010, 21(1): 110-114.