The development of underground ring roads has become a new initiative to relieve traffic pressure in the urban core. In order to optimize the design of the underground ring road, the reasonable length of the weaving segment was studied with capacity and traffic simulation analysis. Firstly, considering several influencing factors, the calculation method for the length of underground ring road weaving segment was constructed, and each parameter was calibrated. Secondly, taking the underground ring road in the T5 station business district of Airport New City of Xi Xian New Area as an example, the results of Vissim simulation before and after the construction of underground ring road were compared, as well as the traffic conflicts between the original project design and the design obtained by the proposed method through Surrogate Safety Assessment Model (SSAM). Finally, the recommended value of the length of underground ring road weaving segment under general conditions was given. The results show that: a) the length obtained by the calculation method has a small error (less than 4.2%) with the simulation results, which proves that the proposed method could calculate the length efficiently; b) compared with the original design, the traffic conflict rate is reduced by 73.2%, which testifies that the length obtained by the method is more reasonable; c) with the construction of the underground ring road, the travel time is reduced by 39.6% maximum, the delay is shortened to within 2 s, and the maximum decrease of queue length is 88.1 m, which indicates that the construction of the underground ring road could improve the level of service using the calculation method. The design based on the proposed method can improve the traffic safety of the underground ring road and reduce the congestion in the urban core.

In order to realize the active prevention and control of rear-end collision on sharp curves, a dynamic prediction method of rear-end conflicts was proposed based on converged multi-source data. In this study, firstly, a model for distinguishing rear-end conflicts on sharp curves and a classification criteria of conflict level threshold were proposed by using the vehicle traveling data collected by drones and millimeter wave radar. The spatial distribution characteristics of such conflicts on sharp curves was subsequently analyzed. Then, 13 variables related to traffic flow characteristic such as vehicle type, ratio of large vehicle, and speed difference between sections were selected as input variables, and dynamic combined prediction models of rear-end conflicts on sharp curves with BP neural network, random forest and support vector machine algorithms were constructed based on particle swarm algorithm, respectively. The prediction performance of each prediction model was evaluated based on confusion matrix and area under curve, and the black box interpretation method was used to analyze the significant influence variables and the probabilities of rear-end conflicts occurrence. The results show that the TTC values of rear-end conflicts on sharp curves are smaller than those on flat or normal curved sections, and such conflicts are more serious on the gentle curve exit sections, and the conflicts risk on the inner side of the curves is the highest; the particle swarm algorithm-random forest model has the best performance in predicting the rear-end conflicts, with a sensitivity of 90.70%; the impact of average vehicle headway on rear-end conflict in sharp curve sections is the most significant. When the average vehicle headway is around 25 meters, the probability of conflict is the lowest. Factors such as mean centripetal acceleration and mean velocity also have a significant influence on it.