Based on data preprocessing, digital analysis of the asphalt pavement construction process was conducted, and important construction processes and meteorological parameters affecting construction temperature were screened using the random forest (RF) algorithm. Based on the selected important parameters, the construction temperature prediction model was established by multi-layer perception (MLP). Based on feedback control theory, the control principle of the PID controller was analyzed, and a comprehensive and multi-stage temperature feedback control model was constructed in conjunction with the construction temperature prediction model. In order to solve the problem that the super-parameter cannot be self-tuning, the genetic algorithm (GA) is used to optimize the feedback control model to make the model adaptive. The feedback control model's construction process decision was compared and analyzed with the actual construction process parameters, and the robustness of the model's feedback control results was evaluated to effectively adjust the construction process parameters and achieve precise control of asphalt mixture construction temperature. The research results showed that the construction temperature prediction model could accurately predict the construction temperature. The comprehensive feedback control model could feedback control all parameters, while the multi-stage feedback control model could maintain the determined parameters and feedback control other parameters. In addition, the GA-PID feedback control model based on genetic algorithms had the performance of adaptive tuning of hyperparameters. Through analysis of the feedback control results, it was found that the construction process parameters obtained from the GA-PID feedback control model were evenly distributed within the effective range of actual process parameters, maintaining good consistency with the actual construction process parameters. The GA-PID control system had good robustness for different prediction models and different temperature control, and the proposed construction process decision was consistent with actual situations.

This study investigates the problem of V2R (Vehicle to Road Side Units,V2R) communication channel allocation at an intersection considering communication channel competition among each vehicles. This problem is formulated as a mixed-integer nonlinear program with equilibrium constraints. The object of this problem to minimize V2R communication delays of the whole system by optimizing the number of connected autonomous vehicles (CAVs) communicating with each RSU (Road Side Units, RSU). Complementary constraints based on User Equilibrium is introduced to guarantee each CAV can connect with RSU with their least delay in the competition. A piecewise linearization method is introduced to linearize and help solve the model. In the numerical experiment, the proposed model is compared with the models following System Optimum principle. By comparison, the results show that the proposed model can better achieve the balance between the benefits of the whole V2R system and each CAV individuals. The finding of this study can be applied to the situation where communication channel is crowded at the intersection.