基于改进K-means十十聚类算法的汽车行驶工况构建

打开文本图片集

中图分类号：U467；TP311 文献标识码：A

Construction Vehicle Driving Cycles Based on an Improved K-means+ + Clustering Algorithm

CHEN Junjie¹，ZHAO Hong1，LUO Yong1  DING Xiaoyun1，TIAN Jiahao1，ZHANG Zeqian²

Abstract： To optimize trafic management reduce environmental pollution through scientific methods，a method for constructing vehicle driving conditions based on an improved K-means ++ clustering algorithm is proposed. Combined with Markov chain theory，this method analyzes constructs vehicle driving conditions. The collected vehicle driving data are preprocessed， including data cleaning feature extraction. Dimensionality reduction was performed using Principal Component Analysis（PCA）， a K-means++ algorithm based on cosine similarity is introduced. The optimal number clusters is determined using the elbow method. The results show that four driving conditions effectively simulate real driving scenarios. The comparison average silhouete coefficients from the clustering results demonstrates that the improved algorithm significantly outperforms traditional methods in clustering performance. Using the Markov chain model，the transition relationships between the driving condition states are validated， the final vehicle driving conditions are constructed. According to the comparative results the relative error key characteristic parameters，the average relative error is only 4.726% ，indicating that this method has high rationality accuracy in simulating actual road conditions. This provides a solution for trafic data analysis model construction in complex traffic environments.

Keywords： clustering algorithm; driving cycles; principal component analysis；markov chain

随着城市化进程的加速，交通拥堵和环境污染成为全球多数大城市面临的主要问题。（剩余8860字）