摘要
为有效促进汽车节能减排和新技术发展,文中提出了一种改进全局K Means聚类算法的汽车行驶工况构建方法,通过采集城市道路行驶工况的数据并对数据进行预处理,利用主成分分析法和改进的K Means聚类算法分别对运动学片段中实验数据的12个特征参数进行降维和聚类,拟合出某城市汽车行驶工况。分析结果表明:拟合曲线的汽车运动特性能更好代表所采集数据源的相应特性,两者的误差小,时耗低,行驶工况拟合度高,能综合反映实际车辆运行的状况。
In order to develop new technology for effective energy saving and emission reduction,this paper presents a method for constructing automobile driving cycle based on the improved global K Means clustering algorithm(IGKM).The data of urban road driving conditions was collected and preprocessed.Twelve characteristic parameters of the data in the kinematics section were reduced and clustered by using the method of principal component analysis and the improved K Means clustering algorithm,with the fitted driving cycle in a city obtained.The results show that the vehicle motion characteristics of the fitted curve can better represent the corresponding characteristics of the collected data sources,with small error,low time consumption and high fitting degree,which fully reflects the actual driving cycle of vehicles.
作者
徐淑萍
熊小墩
苏小会
张玉西
XU Shuping;XIONG Xiaodun;SU Xiaohui;ZHANG Yuxi(School of Computer Science and Engineering,Xi’an Technological University,Xi’an 710021,China)
出处
《西安工业大学学报》
CAS
2021年第3期338-344,共7页
Journal of Xi’an Technological University
基金
陕西省教育厅项目(17JK0381)
国家地方联合工程实验室基金项目(GSYSJ2018011)
陕西省大学生创新创业训练计划项目(S202010702109)。
关键词
行驶工况
主成分分析
改进全局K-Means聚类
特征参数
driving cycle
principal component analysis
improved global K-Means clustering
characteristic parameters
