Research on Driving Cycle Construction Based on Sorting-Time Hybrid Method

In order to construct the driving cycle for the classification of road congestion degree, data preprocessing is performed on the driving data of the vehicle, and it is divided into 591 kinematics segments, and the characteristic parameters of each kinematics segment are extracted. Principal component analysis method is used to reduce the dimension of feature parameters, perform k-means clustering analysis, classify kinematics fragments into four categories, and analyze the congestion degree of each category. On the basis of the correlation coefficient method, representative kinematics segments are selected in descending order and time, and four types of driving cycle classified based on the degree of traffic congestion are constructed. Finally, the relative error method is used to verify the rationality of the construction of driving cycle.