To provide a deep insight into the significant factors that affect the severity of freeway crashes, this study took the crash data from the Dongguan section of the Guang-Shen Yanjiang Freeway in China from 2014 to 2019 as the research object. Crash severity levels were divided into three categories (i.e., no injury crash, minor injury crash, severe injury or fatality crash). Accounting for spatial correlation among adjacent crashes via conditional autoregressive priors, spatial generalized ordered Probit models with different correlation distance thresholds were developed, where the crash severity was used as the dependent variable and 13 potential influencing factors were used as independent variables. The research results show that there is significant spatial correlation among crashes; the spatial generalized ordered Probit models outperform the generalized ordered Probit model and multinomial Logit model; and the spatial model with 250-meters correlation distance threshold achieves the best performance. The results of model parameter estimation reveal that the type and registered province of vehicles, the time of crash occurrence, curvature of crash location, bridge section, and crash type have significant effects on freeway crash severity. The marginal effects of these factors indicate that: as compared with crashes with cars involved only, the involvement of bus, truck and other type vehicles will increase the probability of severe injury or fatality by 3.27%, 1.53%, and 4.11%, respectively; the involvement of vehicles from other provinces will increase the probability of severe injury or fatality by 1.02%; as compared with those occurring on weekend, spring, and bridge, crashes occurring on weekdays, summer, and non-bridge sections would increase the probability of severe injury or fatality by 0.87%, 2.38%, and 0.08%, respectively; the probability of heavy casualties caused by bicycle accidents is 1.64% lower than that of multi-vehicle accidents; the probability of severe injury or fatality will decrease by 1.54% for per 1 km^-1 increase in horizontal curvature of crash location.

During the "14th Five-Year Plan" period, China has entered a new stage of urbanization development. Cultivating modern metropolitan areas is an efficient approach to promote the development of urban agglomerations. Rapid transportation systems such as expressways and high-speed railways in the regional transportation network are the precondition for the formation and development of metropolitan areas. The regional heterogeneous spatiotemporal convergence effects caused by them profoundly affect the spatial pattern of metropolitan areas. Therefore, there is a urgent need to examine the interactive relationship between the spatial organization of metropolitan areas and different transportation network levels. In order to explore the development law of spatial variations on expressway and railway density caused by the dislocation of population aggregation and economic development in metropolitan area hierarchy, this paper constructed a city correlation strength model based on multi-source data. It took five metropolitan areas in the Yangtze River Delta urban agglomeration as examples and districts and counties as spatial units. Multidimensional scaling analysis and spatial distance elements were applied to identify the boundaries of the metropolitan area hierarchy, namely boundaries of core circle, tight circle, and planning range. Based on the five main indicators of population density, per capita GDP, land output rate, railway density, expressway density in each metropolitan area hierarchy, this paper discovered the correlation law between socioeconomic development and transportation network density. Results show that there are unbalanced population agglomeration and economic development in each circle of the metropolitan area, and the development curves of "population density-output per land" and "output per land-output per capita" are "S-shaped" and "logarithmic", respectively; the development laws of "population density-expressway density" and "land output rate-expressway density" both show a "logarithmic" curve, but those of the current railway density curves vary from those of expressway; when the population density is higher than 600 people/km2 and the land output rate is more than 80 million yuan/km2, the railway density in the core circle is insufficient. This study provides a new perspective for the research on integrated transportation network planning in the metropolitan area.

In order to improve the traffic efficiency and reduce the stops of tram in intersections, this paper proposes a coordinated signal control optimized method to realize the multimodal segmented green wave control of tram and general traffic. First of all, the signal cycle of each intersection along the arterial is determined. Based on the cycle length, the intersections are clustered and coordinated with the tram departure interval, and the influence of the station location on the tram green wave coordination is discussed. Secondly, constraints are established for general traffic green wave system and tram green wave system to avoid the tram stopping at the intersection. A mixed integer linear planning model is established based on the goal of optimizing the maximum variable green wave bandwidth of general traffic, so as to coordinate and optimize the multi-mode trunk green wave system of trams and general traffic. Finally, a comparative analysis is carried out by using the Nanjing Qilin tram line as a case study. The results indicate that this model can optimize the signal control scheme of arterial segmented green wave which guarantees the passive priority of tram in intersections and running efficiency of general traffic. VISSIM simulation results indicate that, as compared the current signal control scheme, the proposed model can reduce the vehicle delay of each intersection by 20.89%~35.24%; and that, as compared with the MULTIBAND model, this model reduced the delay of person by 6.94%, which improves the overall operation efficiency of the intersection.

The bike-sharing(BS) flow rate reflect the degree of surplus and shortage of vehicles in urban spatial environment. Understanding its changes and incentives is of great significance for urban BS scheduling. Due to the complexity and variability of travel purposes and external environmental factors, it is difficult to analyze the relationship between the BS flow rate and the characteristics of the built environment through a statistical model with linear assumptions. Therefore, this study explored the contribution of the built environment to the BS flow rate and the nonlinear effects on the flow rate, as well as the changes of the nonlinear model of the BS flow rate on weekdays and weekends based on the data of BS in the downtown of Shanghai, through the extreme gradient boosting tree model (XGBoost) and the interpretive method partial dependence plot (PDP) of machine learning. The results show that the feature importance and nonlinear mechanism are significantly different in the two periods. The density of residential population, educational facilities and residential facilities has a high degree of explanation for the weekday BS flow rate, which is 19.18%, 13.16% and 12.92%, respectively, and has a significant threshold effect. The density of residential population and the density of educational facilities have a positive impact on the net BS outflow rate, reaching the maximum at 11 600 person per km² and 8 educational facilities per km² respectively; the density of residential facilities has a negative impact on the net BS outflow rate, and the corresponding threshold is 40 residential facilities per km².There is little difference in the explanatory degree of each variable to weekend BS flow rate, nevertheless the nonlinear relationship cannot be ignored. Specifically, the distance to the city center and bus line number density have a significant positive impact on the weekend net BS inflow rate, with the effective range of 18~23 km and 28~52 routes per km². The positive influence range of plot ratio on net BS outflow rate at weekends is 0.89~1.41. The above findings show that XGBoost model can effectively compensate for the bias of linear assumption of traditional regression model (MLR), and the disclosure of the contribution degree and influence scope of built environment characteristics also provides decision-making suggestions for the management department for BS dispatching in areas with different built environment levels.

In this paper, a cross-wind-train-bridge-tunnel model was established to conduct simulation calculation based on the unsteady characteristics of flow field under cross-wind action of high-speed trains. The accuracy of the numerical method was verified by 1∶8 dynamic model test. Then, the transient aerodynamic pressure, aerodynamic load changes and flow field characteristics inside and outside the tunnel were studied when the train broke out of the tunnel under cross-wind conditions, so as to reveal the interaction mechanism between cross-wind, train, bridge and tunnel. The results show that the pressure decreases gradually with the increase of cross wind speed, and the change law of pressure with time is similar. The cross wind has an obvious effect on the pressure gradient at the exit of the tunnel and outside the tunnel, but has almost no effect on the measuring point inside the tunnel. With the increase of cross wind speed, the peak value of the positive pressure on the leeward side outside the tunnel decreases slightly with the increase of wind speed, while the peak value of the positive pressure on the windward side basically remains unchanged. And the decrease rate of the peak value of the negative pressure on the leeward side is greater than that on the windward side. The cross wind has limited influence on the pressure fluctuation of train protruded tunnel. When the cross wind speed is 20 m/s, the scope of influence of the external flow field on the pneumatic pressure in the tunnel is less than 20 m. Under the same cross-wind condition, the pressure time-history variation rules at the measuring points on the windward side and the leeward side are different, and the position of the peak value of the pressure gradient is also different. The closer the measuring points on the same side of the train are to the ground, the greater the peak value and the absolute value of the peak value of the pressure gradient are. Under cross wind, when the airflow passes through the vehicle-bridge system, obvious flow separation occurs at the bottom of the bridge, the top and bottom of the leeward side of the train, resulting in the pressure difference on both sides of the train outside the tunnel is greater than that on both sides of the train inside the tunnel.

For the research on the mechanical properties of single perforated plate connector or shear stud connector, international scholars have carried out a lot of numerical analysis and experimental exploration, and obtained the mechanical behavior of single perforated plate connector or shear stud connector. However, the interior of the steel-concrete composite section of the actual hybrid bridge tower is composed of a large number of perforated plate connectors and shear stud connectors. At present, the research on composite connectors in steel-concrete structures is relatively scarce, and there is no clear numerical model and theoretical derivation to study the force transfer law of composite connectors. And the influence of the design parameters of the composite connector itself on the compressive performance also needs to be further clarified. Therefore, taking a composite shear connector in the steel-concrete composite section of the bridge tower of Shunde bridge as an example, this paper studied the contributions of the perforated plate connector and the shear stud connector to the compressive stiffness of the single-layer composite shear connector during the elastic loading stage. Then it established the spring model and derived the formula for calculating the elastic stiffness of the single-layer composite shear connector. Using ABAQUS finite element software, the load simulation analysis of single-layer composite shear connectors was carried out. In the elastic loading stage, the load displacement curve shows a strong linear relationship. After fitting, the results are compared with the elastic stiffness calculation results of the derived formula. The results show that the error between the analytical solution and the numerical solution of the compressive stiffness of the single hole perforated plate connector is 4.87%, the error between the analytical solution and the numerical solution of the compressive stiffness of the single shear stud connector is 0.903%, and the error between the analytical solution and the numerical solution of the compressive stiffness of the single-layer composite shear connector is 11.54%. The calculated results of the derived elastic stiffness formula are in good agreement with the results of the finite element simulation analysis.

Due to the continuous development of connected and automated vehicles, there will be a mixed traffic flow in which intelligent networked vehicles and manual driving vehicles coexist in the future. Therefore, the study of mixed traffic on the road can effectively solve traffic congestion and other problems, so it has certain practical significance. In order to explore the relationship between the flow, density and speed of this type of mixed traffic flow, this paper established a fundamental diagram model of the mixed traffic flow in an autonomous driving environment based on the comprehensive consideration of the degradation of intelligent networked vehicles and the delay between vehicles. First, it determined the types of vehicles in the traffic flow and the proportion of different types of vehicle, and considered the vehicle functional degradation when connected intelligent vehicles follow artificial vehicles. Then, the delay time of each type of three vehicles was determined and the following model of each vehicle was improved. On this basis, considering both the vehicle delay and the vehicle function degradation, the fundamental diagram model of traffic flow balance was derived, and the sensitivity analysis of free flow speed parameter in the model was carried out. The research result shows that connected and automated vehicles have a positive impact on the maximum flow and optimal density of mixed traffic flows, while vehicle delays have a negative impact; the free flow speed has a positive impact on the maximum flow and a negative impact on the optimal density of mixed traffic flow. The SUMO simulation results show that the simulated flow-density distribution points in different scenarios conform to the theoretical curve, which verifies the accuracy of the theoretical model in the paper.

Rutting depth is an important indicator for the evaluation of pavement conditions and road maintenance. The existing rutting depth measurement method fails to consider the influence of potholes, raveling, cracks and bridge joints under complex road conditions, and its effectiveness and applicability are limited, and the authenticity of the measurement results remains to be further verified. In view of this, an abnormality detection and correction method based on semantic segmentation model is proposed. The road cross section elevation data is collected by three-dimensional line laser technology, and the rutting depth is extracted by the envelope algorithm. For cross-section of the maximum rut to more than 10 mm, this paper builds a semantic semantic division framework based on deep learning, proposes an improved DeepLabV3+ network to automatically identify and pixel positioning of the disease type, and designs a correction rule based on Lagrangian interpolation to correct the abnormal rut by combining the maximum rut depth elevation points. The results show that the improved DeepLabV3+ model can more accurately identify and locate pavement distress causing rutting abnormality, and its comprehensive detection accuracy of five pavement characteristics and distress reaches 81.63%. Its performance in Mean Intersection over Union (MIoU) and Intersection over Union (IoU) is better than that of U-Net, PSPNet, and DeepLabV3+ models. The field validation results show that the method in the paper can not only automatically analyze the causes of rutting abnormality, but also exclude the influence of other distress by correcting the abnormal rutting, so as to restore the actual rutting depth level to a greater extent. The research results in this paper can provide scientific data support for pavement preventive maintenance.

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.

Seepage is a key factor that causes the loss of fine particles in soil-rock mixture fillers and leads to changes in soil structure and subgrade deformation and instability. In this paper, the self-developed particle loss test device was used to carry out the seepage test of soil-rock mixture fillers with different gradations. The change process of permeable quality, fine particle loss and settlement of fillers under seepage was monitored, and the evolution process of soil structure was analyzed. Particle Flow Code in 3D (PFC^3D) was used to simulate the process of fine particle loss, and the dynamic change characteristics of soil porosity and filler particle size were analyzed. The results show that the permeability quality and fine particles loss rate can reflect the sensitivity of soil-rock mixture fillers structure to water. The lower the sensitivity of filler skeleton structure to water, the less the damage of the seepage to the structure, because the water can be discharged timely and effectively. The structural evolution process of soil-rock mixture fillers under seepage conditions can be divided into three stages, namely, stage of rapid loss of fine particles, skeleton remodeling stage, and relatively stable stage. The skeleton remodeling stage is the key stage to cause structural damage. In the stage of rapid loss of fine particles, the growth rate of per hour permeable quality is fast, a large number of fine particles are lost, and the settlement is small. In the skeleton remodeling stage, the change rate of per hour permeable quality slows down, and the loss of fine particles decreases. However, the reorganization of skeleton structure leads to obvious relative displacement of particles, and the settlement increases rapidly. In the relatively stable stage, the per hour permeable quality changes slowly and the settlement remains basically unchanged. The process of particle loss numerical simulation shows that the migration of fine particles causes the change of porosity of fillers, resulting in the change of soil structure. The results show that, among the studied fillers, the soil-rock mixture fillers with n=0.55 has the most stable skeleton structure and the weakest sensitivity to water.

In order to solve the problem that drivers cannot accurately recognize the roadside information at expressway due to high speed in rainy day, this study firstly selected vehicle speed, clarity degree of drivers’ visual field pictures, line-of-sight angle and fixation distribution percentage as the attention distribution indicators in rainy day based on the attention distribution theory. And Fisher discrimination analysis method was used to establish the quantitative model of visual search ability. Secondly, a simulation driving software UC-win/Road was used to build an experimental platform. Rainfall intensity and vehicle speed were selected as the influencing factors, the change rule of driver’s attention distribution indicators under the cooperation of the two factors was studied, the relationship between rainfall intensity, speed and visual search ability was established, and the matching scheme between rainfall intensity and speed limit was proposed. The results show that the increase of vehicle speed and rainfall intensity would make it difficult for drivers to observe roadside information. To reduce the driving risk, the driver would change the visual search strategy and increase the focus on the front of the road, which reducing the visual search efficiency of the observation target. Therefore, drivers need to spend more efforts to transfer attention when the matching between rainfall intensity and vehicle speed is unreasonable, resulting in the inability to find roadside information in time. In addition, the overall correct percentage of classification of the model is 85.94%, which indicates that the model can evaluate drivers’ visual search ability. Finally, the speed limit schemes based on stopping sight distance and that considering drivers’ visual search ability of roadside information were compared. The results show that the speed limit calculated based on stopping sight distance is higher. To avoid that drivers cannot accurately identify the roadside information due to the high speed, the speed limit of light-rainy day, moderate-rainy day and heavy-rainy day should not exceed 100, 70 and 50 km/h, respectively.

This paper aims to explore and quantify the spatio-temporal propagation mechanism of freeway traffic crashes and address the defect of traditional traffic wave theory considering single dimension in such problems. Firstly, the speed changing before and after the traffic crash was analyzed based on the dynamic traffic flow data collected by microwave radar detectors. Furthermore, the speed changing rate was introduced as a measure of the impact of a crash, the bilinear interpolation method was adopted to construct the speed changing rate curve, and the Savitzky-Golay filtering fitting method was applied to fit the outer contour of the spatio-temporal region affected by the crash. Finally, the indicators of spatio-temporal impacts of traffic crash were figured out and analyzed under the condition that the speed changing rate threshold is 20%, 30% and 40%, respectively. The indicators include the beginning time of the crash effect, the end time of the crash effect, the duration of the crash effect, the closest distance of the crash effect, the furthest distance of the crash effect, the spatial range of the crash effect, the propagation speed of the crash effect and the dissipation speed of crash effect. The results indicate that the smaller the threshold of speed changing rate is, the earlier the crash influence starts, the later the crash influence ends, the longer the duration and the longer the distance of the crash influence has; the higher the speed changing rate threshold is, the later the crash influence starts, the earlier the crash influence ends, the shorter the duration and the shorter the distance of the crash influence have; additionally, under various speed changing rate threshold, the changing trend of propagation speed generated by the traffic crash varies with time. The approach adopted in this paper has strong operability and high identification of results, which can provide theoretical support for real-time traffic control and guidance after freeway crashes.

To efficiently collect and digitally model road facility information, this paper constructed a method framework for automatic extraction of road geometry information by using vehicle-mounted laser point cloud data. For the disorder and redundancy of laser data, grid drop sampling and radius filtering were used to simplify the size of the point cloud and remove noise points. The point cloud is organized and indexed by grid cell division, and the spatial locality of the point cloud is rationally utilized to reduce the scale of operation. Using the hierarchy of road elements on elevation and the continuity and smoothness of pavement structure, elevation filtering, local normal vector filtering based on the principal component analysis framework, and DBSCAN clustering methods were designed to achieve accurate segmentation from the original point cloud to the pavement point cloud. The road direction was obtained by collecting vehicle trajectory information, and the road cross section was divided by its direction vector and normal vector. The cross-section was cut and projected onto a two-dimensional plane, and the road width and horizontal and horizontal parameters were extracted by sliding window and least square algorithm. By comparing the extraction algorithm with the manual measurement results, in the two experimental data sets of complex blocks and suburban roads, the accuracy of point cloud segmentation is more than 87%, the integrity is more than 97%, and the extraction quality is more than 86%. The average relative error of geometric information is small, indicating that the algorithm has good extraction quality. Under the condition of finite computation, the processing time of two data centralized point clouds is 6.864 and 10.078 s/km, respectively, and the extraction time of geometric information is 1.732 and 0.843 s/km, respectively. The proposed method can give a good balance between extraction efficiency and accuracy, and has good applicability in complex blocks and suburban highway environments. It can provide a reference for the health assessment and three-dimensional reconstruction of road facilities.

In order to realize the high-throughput calculation of meso-contact for asphalt mixture skeleton, this paper firstly put forward two contact calculation methods, the neighbor list method and the improved window search method, and then four asphalt mixtures AC13, AC16, OGFC13 and SMA13 were used to compare the difference in calculation accuracy and efficiency among two new methods and exhaustive method, window search method and iPas software, and the range of image resolution that can achieve the balance of calculation speed and accuracy was investigated using virtual specimens. Finally, the applicability of the high throughput calculation method was verified. The results show that neighbor list method can avoid the redundant contact calculation of contact aggregate pairs with the exhaustive method, and the improved window search method can accomplish the purpose of a one loop sweep of the traditional window search method by morphological expansion processing. Neighbor list method, exhaustive method, window search method, improved window search method and iPas software have the same accuracy although there are differences in calculation principles. The order of computational efficiency of different calculation methods is: neighbor list method > exhaustive method > Improved window search method >iPas software > window search method. The decrease of image resolution will improve the speed of contact calculation but reduce the accuracy of contact point calculation results. Considering the requirements of both accuracy and efficiency, a balance of calculation speed and accuracy can be realized when the image resolution range is 0.05~0.075 mm/pixel. The neighbor list method can effectively realize the high throughput characterization of meso-contact of asphalt mixture skeleton.

Reasonable setting of tunnel traffic signs can alleviate the “spatial-temporal tunnel effect” caused by the special environment of tunnels to a certain extent. This paper studied the influence of traffic signs (speed limit signs and exit warning signs) on driving behavior in highway tunnels. Firstly, it selected long tunnels as experimental sections, obtained fine-grained microscopic behavioral data of drivers through driving simulator, and constructed a linear mixed effect model considering the influence of random effects to reveal the influence characteristics and mechanism of traffic signs on driving behavior in tunnels. The results show that: there are differences in the effects of traffic signs on driving behavior in different influence zones; installation of speed limit signs inside the tunnel can reduce the probability of accident risk to a certain extent and the repeated setting of speed limit signs can improve drivers’ maneuvering ability to a certain extent; the setting of speed limit signs and exit distance warning signs inside the tunnel can help improve drivers’ spatial control ability and driving comfort. Among them, the installation of tunnel exit distance warning signs in the impact zone of less than 1km from the tunnel exit helps to improve the driving comfort of drivers; the installation of tunnel exit distance warning signs in the impact zone of 2 km and 1.5 km from the tunnel exit can improve the vehicle control ability and at the same time make drivers have a higher driving speed. In addition, driving behavior under the effect of tunnel traffic signs is influenced by driver’s gender, age, driving experience and other characteristic attributes, with male drivers having a lower driving risk.

The track scale of high-speed railway intermediate station is an important factor affecting the line carrying capacity and transportation efficiency. In the planning stage of the high-speed railway line, it is difficult to predict the long-term passenger flow. Therefore, after a period of operation, it is often necessary to update the track scale of intermediate stations along the line by building side tracks or platforms. For high-speed railways, the trains running on their lines are all electric multiple unit trains, with short track intervals, high departure densities and no long dwell time at intermediate stations. Therefore, high-speed railways generally operate in fast-in and fast-out operation mode. At the same time, the construction and operation of high-speed railways have a high cost attribute. The article constructed a comprehensive optimization model with the renovation construction cost and total travel time as the evaluation objectives and the coupling relationship between the train timetable and the number of intermediate station tracks as constraints. On the basis of linearizing the constraints, the model was solved with the help of commercial optimization software GAMS with CPLEX solver. The results of the calculation example show that the comprehensive optimization of the track configuration of the intermediate stations and train timetable can not only determine the stations for train overtaking and turning back in the timetable but also meet the future passenger demand to the greatest extent at the lowest construction cost.

At present, the freight car overload phenomenon is coming from bad to worse, in order to improve the efficiency of freight car control on the highway and the level of safety in the freight transport, a freight transport risk level identification model based on user portrait of freight risk was proposed. Firstly, based on highway toll data, taking freight car as the research object, a user portrait system for freight transport risk identification was developed from the aspects of driving behavior and operation status. Then，the sample data was cleaned and the label index was extracted and analyzed. Then, K-means++ algorithm was applied to obtain the classification results of freight transport risk feature portraits. Next, the entropy weight method was used to score the freight risk of all kinds of freight car to determine the risk level of all kinds of freight car. Finally, by combining with the relevant indicators of various types of vehicles, the vehicle portrait was completed. Based on the trucking toll data of the entire highway network in Guangdong Province from March to May 2022, the proposed model was used to divide the trucking vehicles into five categories. Among them, “the freight car of high risk and high workload” accounted for 5.42%, the freight car of higher risk and night-driving and overloaded ”accounted for 19.12%, “the freight car of medium-risk and overspeed” accounted for 12.85%, “ the freight car of low risk and low-frequency” accounted for 37.00%, and “ the freight car of low risk and high-frequency ” accounted for 25.61%. The validity of the model was verified by the data of an accident database in Guangdong Province in the same period. The data showed that the relative risk coefficient of high risk vehicles is much higher than that of low risk vehicles. The research shows that the proposed model can effectively identify trucks with high freight risk characteristics. Based on the results of risk grade identification, traffic management departments can carry out high-risk vehicle identification, key inspection of overload and over-limit, and specific message push to guide vehicle driving safety, so as to improve the safety management level of the industry.

At present, there are relatively few studies on the settlement prediction of shield tunnels crossing existing roads in parallel. To accurately predict the influence of different factors on the settlement of existing parallel roads in the shield process, this study proposed a support vector regression prediction model based on the improved particle swarm optimization (IPSO-SVR), which was applied to the surface road settlement prediction of actual subway tunnel engineering. Based on the Changchun Metro Line 6 under-crossing Feiyue Road section project, combined with the shield boring parameters, formation information and road settlement monitoring during the construction of the shield tunnel, this paper used the grid search method of libsvm to reduce the range of hyperparameters, and improved the change of inertia weight and acceleration factor in particle swarm optimization algorithm by combining the nonlinear decline strategy. Finally, IPSO-SVR prediction model was established to achieve the settlement prediction of subsequent sections in the interval. The results show that, comparing the changes of the objective function (mean square error) in the grid search method and in the conventional particle swarm optimization training, the convergence speed of the improved particle swarm optimization is greatly improved; the convergence effect of the objective function is better, and the minimum value is reduced by nearly 15%. The mean absolute error (MAE) of IPSO-SVR prediction of road settlement proposed in this paper is 0.287, the fitting coefficient R² is 0.884, and the average relative error is only 8.91%, which has better performance than back propagation (BP) neural network, support vector regression (SVR) and particle swarm optimization support vector regression (PSO-SVR) prediction models. It can be seen that IPSO-SVR has high precision for nonlinear prediction of multi-factor coupling under complex conditions, and its prediction method is feasible and generalizable. IPSO-SVR can provide a reliable basis for effective control of road settlement and is of great significance for ensuring the normal operation of roads and the safety of shield construction.

In the regional highway network, there are numerous toll stations generating massive amounts of data on a daily basis. However, due to equipment and network issues, there may be delays in data transmission for some stations. In such cases, the transmitted data may not be sufficient to meet the requirements for real-time traffic flow prediction. To achieve real-time traffic data imputation and dynamic traffic flow prediction, this paper firstly proposed a method for data imputation of highway traffic flow data based on self-supervised learning, which adopts time series model based on attention mechanism (Seq2Seq-Att). Then the self-supervised learning method was used to train the model. Finally, the reliability of the method was verified by taking 80 toll stations in the highway network of Guangdong province as an example. The results show that the method in this paper can flexibly capture the missing pattern in traffic data and give a reasonable value according to the internal correlation of the data. This method is generally superior to other methods and has good performance under different missing rates. The overall MAPE is about 17.7% and the WMAPE is 12.8%. In the case of high missing rate, this method has obvious advantages over other methods. The results of traffic volume prediction indicate that the prediction accuracy of traffic flow prediction using the data completed by this method is close to the situation of using complete data.

Based on the dynamic damage characteristics of concrete material, this paper established an elastoplastic damage constitutive model, which was applied to a tunnel project with large section in a strong earthquake area. It analyzed the seismic response and dynamic damage law of tunnel structure under different incident directions of seismic waves, seismic wave intensity and surrounding rock conditions, and discussed the seismic damage characteristics and failure mechanism of large section tunnel structure. The results show that the principal stress and acceleration responses of the lining are similar under vertical and horizontal incidence conditions, but the stress and acceleration responses of the lining structure under horizontal incidence conditions are more intense than that under vertical incidence conditions. The dynamic damage of the lining at horizontal incidence is much greater than that at vertical incidence, and the dynamic damage is mainly concentrated at the arch waist and the foot of the wall. The surrounding rock conditions have significant influence on the tensile principal stress response and dynamic damage of the tunnel lining structure. The maximum tensile stress of the lining structure under V-level surrounding rock is 5.7 times of that under IV level surrounding rock. The seismic response and dynamic damage characteristics of tunnel structure are also affected by the intensity of seismic waves. With the increase of seismic wave intensity, the peak value of stress, acceleration response and the maximum amount of dynamic damage show a nonlinear increase trend, and the dynamic damage intensifies and gradually expands outward from the waist and the foot of the wall. In the seismic design of soft rock tunnel in strong earthquake area and the post-earthquake reinforcement and repair during operation, attention should be paid to the parts where the dynamic damage is concentrated.

In order to improve the anti-roll ability of vehicle, this paper designed a hydraulic motor-driven active stabilizer control system, and proposed a hierarchical control strategy based on particle swarm optimization (PSO) algorithm. The upper active disturbance rejection controller (ADRC) calculates the anti-roll torque required by the whole vehicle, and the anti-roll torque required by the whole vehicle is distributed to the front and rear axles through a distributor. The lower three-loop proportional-integral-differential (PID) controller receives the anti-roll torque to be provided, calculates the control current and inputs it to the servo valve, so as to drive the motor output shaft to rotate and generates the active torque through the stabilizer bar to realize the active anti-roll control of the vehicle. In order to make the controller has better control effect, the PSO algorithm was used to optimize the upper and lower control as a whole, and the optimized ADRC and PID parameters were input into the vehicle model. In order to make the simulation close to the actual effect, the torsional stiffness of the lateral stabilizer bar measured by the experiment was also brought into the model. The serpentine and double lane shifting conditions were used for simulation on Class C road surface, and the simulation verification was carried out by comparing PSO-optimized ADRC system with passive system, PID control system and unoptimized ADRC system. The simulation data show that the roll angle directly affects the vehicle’s roll stability, the hierarchical control strategy optimized by PSO algorithm can significantly reduce the vehicle’s roll angle, and effectively suppress the instability caused by excessive body roll motion. The active control stabilizer can better provide the required anti-roll torque for the vehicle than the traditional passive stabilizer, and improve the anti-roll ability of the vehicle. The optimized ADRC controller has better active control effect than the passive system and the unoptimized ADRC controller. Under the same working condition, the roll angle is smaller, the anti-roll ability is stronger, the optimized three closed-loop PID response speed is faster, and the tracking performance is better.