Abstract: In order to effectively evaluate road operation condition,an evaluation method based on Two-Stage Kmeans clustering (TSKC) is developed by analyzing variation of vehicle operating state.First,aiming at the arbitrariness in the choice of K-means cluster number and the randomness of selection of cluster center,a K-means clustering method based on traversal is proposed.The cluster number and initial centers are determined by class attractiveness,and used as the initial condition of the second stage K-means clustering to explore the traffic pattern.The pattern attractiveness,the road evaluation indices,and the distribution equilibrium are proposed as indices to evaluate road operation condition.Beichen East Road of Chaoyang district in Beijing is taken as a case study.The results show that the proposed method is more detailed,comprehensive,and intuitive than the traditional evaluation method when describing the evolution of vehicle state and the distribution of traffic patterns.The results also indicate the great practicability of the method.