The basic requirements for the expansion devices of highway bridges have been determined in the Bridge and Structural Engineering Conference, one of which is the noise reduction and vibration reduction. Our country's expansion device needs to be innovated based on this. In order to study the impact of a new bridge expansion device structure on noise and optimize its structure, the max A-weighted sound pressure level (SPLA) was taken as the optimization target. First, 60 groups of test points were selected using Latin hypercube sampling (LHS), and the model was reconstructed. Then, the finite element method (FEM) was combined with boundary element method (BEM) to simulate the vehicle driving through the expansion device to obtain the far-field max SPLA. A novel BP neural network based on genetic algorithm (GA) and simulated annealing (SA) algorithm optimization is proposed to solve the BP neural network's susceptibility to random initial weights, threshold interference and GA easy to fall into premature. Then, training improved BP neural network to obtain the relationship between structural parameters and the max SPLA. Subsequently, the orthogonal experimental design (OED) method is used to design test points and predict their max SPLA to determine the optimal structure. The results show that the optimized expansion device reduces the max SPLA of the original structure by 12.27dBA, and the optimization rate reaches 13.07%. This research method can provide theoretical guidance for structural optimization of bridge expansion devices, has practical engineering significance, and the results are reliable.

Physical Cell Identity (PCI), as a significant network configuration parameter, is a key factor in the process of User Equipment (UE) accessing to the cell. There are more cells than the number of PCIs, as cell density grows in the ultra dense network, unreasonable PCI configuration will cause conflicts, confusions and Mod- $k$ conflicts (CCM) between cells. However, there is still a lack of work related to the effect of the Mod- $k$ conflict during PCI configuration. In this paper, we propose a PCI configuration scheme that can reduce the occurrence of CCM among cells by using PCIs Grouping and Cells Clustering (named as PGCC). First, a CCM graph is established based on location and handover rate among cells. Second, PCIs are divided into different groups according to Mod- $k$ conflicts, and cells are clustered by the number of groups. Then, the graph coloring algorithm is used to configure the PCI based on the grouping and clustering. Finally, the effectiveness of the scheme is verified by numerous simulation experiments. Compared to other schemes, the PGCC scheme can reduce CCM between cells.

To achieve the economy, green, and high efficiency, the platoon of autonomous vehicles on the highway is a key service for the autonomous transportation system (ATS). At present, there have been few works related to the service components and the cooperation relationship in service architecture of platoon. Therefore, this paper first abstracts the basic services and operational processes based on the literature analysis. On this basis, the platoon service architecture is constructed and then it is divided into three generations, where the evolution of service component subset, then the cooperation relationship is analyzed. Third, the subset of the required service components and their cooperation relationship are analyzed for the typical driving obstacle encounter scenario, according to whether the roadside can facilitate the out-of-team awareness through communication. In addition, an example is used to verify that the intergenerational improvement of service architecture can improve system performance brought by technological progress.

In order to better predict ultimate bearing capacity of perfobond leiste shear connection (PBL), the six specimens were designed for push-out test, and the prediction models were built based on an Improved Adaptive Genetic Algorithm (IAGA) and Back Propagation neural network (BPNN) algorithm. With the finite element model established, it was found that the effects of different parameters on the ultimate bearing capacity of PBL vary greatly if using a single parameter method. The calculation results showed that transverse reinforcement diameter, hole diameter of steel plate, the thickness of steel plate and the strength grade of concrete were the four key factors affecting the ultimate bearing capacity of PBL. In order to overcome the disadvantages of BPNN, such as slow convergence speed and easy to fall into local optimization, an improved adaptive genetic algorithm is used to optimize the initial weights and thresholds of BPNN. The comparison shows that the algorithm is superior to the standard genetic algorithm and other heuristic algorithms, in terms of convergence speed, global search ability and robustness. The IAGA-BPNN prediction model was established. Using the experimental data obtained from both the fatigue test and the references as samples to train the prediction model, the results show that the IAGA-BPNN algorithm proposed in this article can accurately predict the ultimate bearing capacity of PBL, with an average error of 1.69%. The comprehensive sensitivity analysis (CSA) method adopts to explore the relative contribution of each key factors and the interaction between the key factors, and the analysis results show that the ultimate bearing capacity of PBL increases significantly with the increase of the thickness of steel plate and hole diameter of steel plate. The accuracy and stability were better than formulas for calculating the ultimate bearing capacity and the BP neural network prediction algorithm.

Close interaction between vehicles is prone to traffic conflicts and fluctuations at intersections. We propose an autonomous intersection traffic management scheme based on segmented dynamic programming. The main purpose of the study was to make sure that autonomous vehicles can pass through intersections without traffic lights safely and smoothly. A mixed-integer nonlinear programming is formulated to model the microscopic behavior of autonomous vehicles and ensure the collision-free among them. In a given period of time, the maximum average speed of vehicles passing through the intersection is the optimization objective of the model. Our experimental results confirm that the proposed model can effectively maximize the average vehicle speed and completely avoid accidents at intersections.