基于K-均值聚类和支持向量机的电动汽车行驶工况研究

doi:10.3969/j.issn.1674-0696.2021.05.20

重庆交通大学学报（自然科学版） ›› 2021, Vol. 40 ›› Issue (05): 129-139.DOI: 10.3969/j.issn.1674-0696.2021.05.20

基于K-均值聚类和支持向量机的电动汽车行驶工况研究

余曼,赵炜华,吴玲,李郁菡

(西安航空学院车辆工程学院，陕西西安 710077)

收稿日期:2020-03-02 修回日期:2020-08-19 出版日期:2021-05-17 发布日期:2021-05-18
作者简介:余曼(1988—)，女，陕西西安人，讲师，博士，主要从事电动汽车及其控制技术方面的研究。E-mail：364896557@qq.com
基金资助:
国家自然科学基金项目(51507013)；陕西省重点产业创新链（群）项目（2018ZDCXL-GY-05-03-01，2019ZDLGY15-01，2019ZDLGY15-02）；陕西省重点研发计划重点项目（2018ZDXM-GY-082）；交通部重点实验室开放基金项目（300102229507）

Working Condition of Electric Vehicle Based on K-Mean Clustering and Support Vector Machine

YU Man, ZHAO Weihua, WU Ling, LI Yuhan

(School of Vehicle Engineering, Xian Aeronautical University, Xi’an 710077, Shaanxi, China)

Received:2020-03-02 Revised:2020-08-19 Online:2021-05-17 Published:2021-05-18
Supported by:

摘要/Abstract

摘要： 针对现有行驶工况难以反映车辆真实驾驶情况的问题，以国内典型大中型城市——西安市为例，对电动汽车行驶工况构建方法进行研究。根据西安市道路布局，设计了城市道路行驶工况数据采集方案；提出了一种K-均值聚类和支持向量机相结合的半监督分类模型，构建了西安工况；最后将西安工况与原始试验数据和国际标准行驶工况进行对比。研究结果表明：西安工况与实际道路行驶数据特征参数的相对误差均小于5%，平均相对误差仅为2.66%，构建的行驶工况能够真实反映西安市车辆的运动特征；且由于动力系统的差异，电动汽车工况比内燃机车工况更为激进。

关键词: 车辆工程, 电动汽车, 行驶工况, K-均值聚类, 支持向量机

Abstract: Aiming at the problem that the current driving cycles were difficult to reflect the real driving conditions of vehicles, taking Xian—a typical large city in China as an example, the construction method of driving cycle of electric vehicles was studied. Firstly, according to the road layout of Xian, the data acquisition scheme of urban road driving condition was designed. Then a semi-supervised classification model combining K-means clustering and support vector machine was proposed to construct the Xian driving cycle. Finally, the Xian driving cycle was compared with the original test data and the international standard driving cycles. The research results show that the relative error between the characteristic parameters of the Xian working condition and actual road driving data is less than 5%, and the average relative error is only 2.66%, which indicates that the constructed driving cycle can truly reflect the motion characteristics of vehicles in Xian. Moreover, because of the difference of power system, the driving cycle of electric vehicle is more radical than that of internal combustion engine vehicle.

Key words: vehicle engineering, electric vehicle, driving cycle, K-means clustering, support vector machine

中图分类号:

U469.72

余曼,赵炜华,吴玲,李郁菡. 基于K-均值聚类和支持向量机的电动汽车行驶工况研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(05): 129-139.

YU Man, ZHAO Weihua, WU Ling, LI Yuhan. Working Condition of Electric Vehicle Based on K-Mean Clustering and Support Vector Machine[J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(05): 129-139.

参考文献

［1］ BRADY J, OMAHONY M. Development of a driving cycle to evaluate the energy economy of electric vehicles in urban areas［J］.Applied Energy,2016,177:165-178.
［2］毛世越，秦兰芝，Maya B D，等.2018中国乘用车实际道路行驶与油耗分析年度报告［R］.北京：能源与交通创新中心，2018.
MAO Shiyue, QIN Lanzhi, MAYA B D, et al. 2018 New Data Analysis on Real-World Driving and Fuel Consumption for Passenger Cars in China ［R］. Beijing: Innovation Center for Energy and transportation, 2018.
［3］ BRADY J, OMAHONY M . Development of a driving cycle to evaluate the energy economy of electric vehicles in urban areas［J］.Applied Energy, 2016, 177:165-178.
［4］ JING Z, WANG G, ZHANG S, et al. Building Tianjin driving cycle based on linear discriminant analysis［J］.Transportation Research Part D: Transport and Environment, 2017, 53:78-87.
［5］ SHI Q, LIU B, GUAN Q, et al. A genetic ant colony algorithm-based driving cycle generation approach for testing driving range of battery electric vehicle［J］.Advances in Mechanical Engineering, 2020, 12(1):168781401990105..
［6］曹骞，李君，刘宇，等.基于马尔科夫链的长春市乘用车行驶工况构建［J］.吉林大学学报(工学版)，2018，48(5):1366-1373.
CAO Qian, LI Jun, LIU Yu, et al. Construction of driving cycle based on Markova chain for passenger car in Changchun city［J］.Journal of Jilin University (Engineering and Technology Edition), 2018, 48(5): 1366-1373.
［7］王国林，郭新，张树培，等.基于短行程法的轻型乘用车行驶工况构建［J］.重庆交通大学学报(自然科学版)，2019，38(2):139-143.
WANG Guolin, GUO Xin, ZHANG Shupei, et al.Driving cycle development of light vehicles based on short trip method ［J］.Journal of Chongqing Jiaotong University (Natural Science), 2019, 38(2): 139-143.
［8］邓雪，李家铭，曾浩健，等. 层次分析法权重计算方法分析及其应用研究［J］.数学的实践与认识，2012, 42(7):93-100.
DENG Xue, LI Jiaming, ZENG Haojian, et al. Research on computation methods of AHP weight vector and its applications ［J］.Mathematics in Practice and Theory, 2012, 42 (7): 93-100.
［9］郑殿宇，吴晓刚，陈汉,等.哈尔滨城区乘用车行驶工况的构建［J］.公路交通科技，2017,34(4): 101-107.
ZHENG Dianyu, WU Xiaogang, CHEN Han, et al. Construction of driving conditions for passenger cars in Harbin urban area ［J］.Highway Communications Science and Technology, 2017,34(4): 101-107.
［10］马志雄，李孟良，张富兴,等.主成分分析法在车辆实际行驶工况开发中的应用［J］.武汉理工大学学报(信息与管理工程版)，2004，26(4):32-35.
MA Zhixiong, LI Mengliang, ZHANG Fuxing, et al. A study on the application of PCA to the development of vehicle real driving cycle ［J］.Journal of Wuhan University of Technology (Information and Management Engineering Edition), 2004,
26 (4): 32-35 .
［11］刘丹.基于支持向量机与k-means混合分类模型的多光谱遥感影像分类研究［D］.昆明：昆明理工大学，2013.
LIU Dan.Research on Multispectral Remote Sensing Image Classification Based on Hybrid Model of the SVM and K-means ［D］. Kunming: Kunming University of Science and Technology, 2013.
［12］ VAPNIK V. The Nature of Statistical Learning Theory［M］. Berlin:Springer, 1999.
［13］ PENG Y, YUAN Z, YANG H . Development of a representative driving cycle for urban buses based on the K-means cluster method［J］.Cluster Computing, 2018, 22(2):1-10.
［14］ DAVIDSON G S, WYLIE B N, BOYACK K W. Cluster stability and the use of noise in interpretation of clustering［C］∥ Proceedings of the IEEE Symposium on Information Visualization, 2001.［s.l.］: IEEE, 2001.23-30.
［15］ LUXBURG U V. Clustering stability: An overview［J］.Foundations & Trends in Machine Learning, 2010, 2(3): 235-274.
［16］ BENDAVID S, SIMON H U, PAL D. Stability of k-means clustering［C］∥Conference on Learning Theory. ［s.l.］: Springer, 2007:20-34.
［17］ CHANG C C, LIN C J. LIBSVM: A library for support vector machines［J］.ACM Transactions on Intelligent Systems and Technology (TIST), 2011, 2(3): 1-27.
［18］徐晓明.SVM参数寻优及其在分类中的应用［D］.大连:大连海事大学，2014.
XU Xiaoming.SVM Parameter Optimization and Its Application in Classification ［D］. Dalian: Dalian Maritime University, 2014.
［19］ GONG H, ZOU Y, YANG Q,et al. Generation of a driving cycle for battery electric vehicles：A case study of Beijing［J］.Energy, 2018, 150:901-912.
［20］ HUNG W T, TONG H Y, LEE C P,et al. Development of a practical driving cycle construction methodology: A case study in Hong Kong［J］.Transportation Research Part D: Transport and Environment, 2007, 12(2):115-128.
［21］ HO S H, WONG Y D, CHANG W C. Developing Singapore driving cycle for passenger cars to estimate fuel consumption and vehicular emissions［J］.Atmospheric Environment, 2014, 97:353-362.
［22］秦大同，詹森，漆正刚.基于K-均值聚类算法的行驶工况构建方法［J］.吉林大学学报(工学版)， 2016，46(2):383-389.
QIN Datong, ZHAN Sen, QI Zhenggang. Driving cycle construction using K-means clustering method ［J］.Journal of Jilin University (Engineering & Technology Edition), 2016, 46 (2): 383- 389.
［23］ HUERTAS J I, QUIRAMA L F, GIRALDO M, et al. Comparison of three methods for constructing real driving cycles ［J］.Energies, 2019, 12(4): 665-671.

[1]	辛亮1,2，杜子学1，杨震2，许舟洲2. 单轴转向架跨座式单轨车辆的主动控制研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(07): 123-127.
[2]	张东东，宗子淳，冯金芝. 基于NSGA-Ⅱ算法的两挡AMT换挡规律多目标优化[J]. 重庆交通大学学报（自然科学版）, 2021, 40(07): 128-135.
[3]	李胜永1，张智华1，王胜男2，王孟2. 面向交通工具金属材料的缺损识别算法[J]. 重庆交通大学学报（自然科学版）, 2021, 40(07): 136-144.
[4]	杜子学，邬浩鑫. 悬挂参数对直线电机跨座式单轨车辆气隙稳定性和运行平稳性影响[J]. 重庆交通大学学报（自然科学版）, 2021, 40(06): 124-129.
[5]	邓明阳1,2，郭应时1. 电动汽车插补耦合无线充电技术的研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(06): 130-135.
[6]	杜子学，马川翔. 车体铰接式跨座式单轨列车运行稳定性分析[J]. 重庆交通大学学报（自然科学版）, 2021, 40(05): 122-128.
[7]	曹源文1，陈作1，赵江2，张晓强3，郑婷婷4. 多路况下轮式装载机行驶稳定性研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(05): 140-146.
[8]	杜子学，邬浩鑫，杨震. 直线电机跨座式单轨车辆曲线通过能力分析[J]. 重庆交通大学学报（自然科学版）, 2021, 40(04): 127-132.
[9]	邓涛1，李鑫2. 智能车辆横纵向运动综合控制方法研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(04): 133-140.
[10]	李耀华，刘洋，宋伟萍，邵攀登，任田园. 基于行驶工况的零部件耐久性测试工况构建[J]. 重庆交通大学学报（自然科学版）, 2021, 40(04): 141-146.
[11]	刘祯1,3，林鑫1,2，吴华伟1,3，叶从进1,3，耿向阳4. 基于STAR-CCM+的IGBT散热翅片结构设计研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(03): 128-134.
[12]	李军，张俊，张世义. 基于ABP-EKF算法的锂电池SOC估计[J]. 重庆交通大学学报（自然科学版）, 2021, 40(03): 135-140.
[13]	郝刚1,2，金涛1. 基于隐马尔科夫模型的滚动轴承性能衰退评估[J]. 重庆交通大学学报（自然科学版）, 2021, 40(02): 123-128.
[14]	刘朝涛,狄科宏,杜子学,杨震. 跨座式单轨弓网耦合主动控制研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(02): 129-135.
[15]	隗寒冰,贺少川. 基于深度强化学习的插电式柴电混合动力汽车多目标优化控制策略[J]. 重庆交通大学学报（自然科学版）, 2021, 40(01): 44-52.

基于K-均值聚类和支持向量机的电动汽车行驶工况研究

Working Condition of Electric Vehicle Based on K-Mean Clustering and Support Vector Machine

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