Traffic congestion is the most frequent, wide-ranging and influential problem among all the traffic problems. The key to this problem is to identify and analyze traffic congestion. This paper reviewed the methods of traffic congestion identification from the perspectives of traditional traffic flow theory and machine learning. Traditional traffic flow theory adopts models such as indicators, MFD, cellular automata, CTM and dual-flow models, using the theory of physics and mathematics to describe the traffic behavior characteristics. The models are reasonable and simple, with clear physical meaning and also with many restrictions. The probabilistic graphical model and machine learning model are practical and not constrained by fixed structures. This paper discussed the research ideas, solutions and existing problems of different congestion identification methods by combining the specific model methods. It summarized the existing traditional traffic flow theory methods and machine learning methods, and pointed out the future development direction.

To meet the need of mass testing scenarios and high-risk scenarios for the autonomous vehicles safety testing and verification, and based on the accident data of 641 cases involving road section in the National Automobile Accident In-Depth Investigation System, five scene elements were selected according to traffic environment elements and test vehicle basic information elements. Then the vehicle accident data was analyzed by one-hot coding and cluster analysis methods. The dangerous accident characteristics were identified and analyzed by combining the vehicle accident data with the typical vehicle collision dangerous scenarios obtained by clustering. And 15 test scenarios of autonomous vehicles involving road section type were extracted, including 6 test scenarios involving common sections and 9 test scenarios involving intersections. Research shows that Chinese traffic environment has unique characteristics. In the test scenario, 53.3% of the target vehicles involved powered two-wheeler (including motorcycles and electric mopeds) and 40.0% involved M1 passenger vehicles. The proposed dangerous accident characteristics can better describe and clarify the test scenario.The research results can provide a test scenario with Chinese traffic environment characteristics for virtual testing of autonomous cars and a basis for the development and testing of vehicle active safety products.

To solve the problem of low recognition efficiency and accuracy of Convolutional Neural Network (CNN) in automatic detection of gray image cracks in two-dimensional pavement, this paper proposed a three-stage road crack extraction algorithm based on feature fusion between layers of transposed CNN. The algorithm includes area judgment, image segmentation, multi-layer feature fusion and other modules. Then this study constructed a classification segmentation network and trained several transposed convolution networks of multi-fusion classification network intermediate layer and divided network output layer. Their operation effect was compared with that of CrackNet. The results show that when the minimum recall rate of CNN-Ⅰ is set to 0.95, the accuracy is 0.497, and the threshold value is 0.003152. According to the training results of CNN-Ⅱ, the accuracy of classification segmentation network is 0.78, recall rate is 0.73, F-1 score is 0.75, and the time for calculating a picture is shortened to less than 0.79 ms. The crack information extracted by multi-layer feature fusion method is more accurate because this method retains the continuity of the crack and realizes the optimization of automatic recognition and extraction of pavement cracks based on CNN.

As compared with traditional vehicles，four-wheel steer/drive vehicles have very good active dynamics control performance，ensuring that the four-wheel steering /torque is independently controllable． This article proposed a time-varying LQR control system based on genetic algorithm for the coordinated control of the steering angle-torque of four-wheel steer/drive vehicles． Different from the traditional linearized tire reference model，it established a linear time-varying system considering the variable stiffness characteristics of the tire，and the control weight matrix of the state quantity was optimized with the genetic algorithm． The simulation results show that under a given corner step input，the time-varying LQR control considering the non-linear characteristics of the tire is better than the linearized model control system in zeroing the center of mass sideslip angle，and the tracking accuracy of the yaw rate with ideal value is improved by 3. 01% ． The simulation of the double line change under high speed and low road conditions shows that the time-varying LQR control system based on genetic algorithm ensures a better trajectory tracking ability of the vehicle，and the maximum lateral displacement error control effect is improved by 44% ，compared with that of front-wheel steering vehicles．

To effectively define the spatial scope of urban agglomeration considering traffic conditions and urban economic links so as to assist the transportation planning and spatial integrative development of the Guangdong-Hong Kong-Macao Greater Bay Area, firstly, the spatial pattern of raster grid highway traffic accessibility, road network density and economic connection intensity for the Guangdong-Hong Kong-Macao Greater Bay area were calculated and analyzed based on geographic information system (GIS) spatial analysis technology and modified gravity model. Then, different scales of urban hinterland were extracted and divided basing on highway traffic accessibility and urban connection degree. The research shows that the urban traffic accessibility of Guangdong-Hong Kong-Macao Greater Bay Area increases in a circle of “ core-periphery ” with Guangzhou-Foshan, Shenzhen-Guanzhou and other central cities as the center, while the traffic accessibility in  counties presents a distribution pattern of “ high in the middle and low at both ends”. The overall traffic accessibility of Guangdong-Hong Kong-Macao Greater Bay A-rea is at a high level, but all the cities in the Greater Bay Area have not yet achieved 1h access. Under the special development background of “one country, two systems and three customs zones” , the traffic linkages and coordination mechanisms between cities and within cities in the Bay Area are still relatively weak, and the traffic bottleneck problems in the inter-provincial and inter-city administrative boundaries are still prominent. The spatial network trend of economic connection intensity in the research area is significant. The leading cities such as Shenzhen, Hong Kong, Guangzhou, Foshan and Dongguan have obvious radiation effects, while the low value areas are distributed in the marginal areas with poor traffic accessibility. The urban hinterland area considering traffic conditions and economic scale in the Guangdong-Hong Kong-Macao Greater Bay Area does not match the corresponding administrative area. The urban hinterland of the two-wings in the Greater Bay Area is gradually “nibbed” by the central core cities. It is suggested to promote the internal space linkages between the central core cities of the Guangdong-Hong Kong-Macao Greater Bay Area urban and to promote the population flow and traffic flow. Thus can give full play to the intermediary role of the secondary center in cross-regional cooperation, and ultimately achieve the regional traffic planning and management of the super-large area without administrative constraints and realize the sustainable and balanced development of the Greater Bay Area.

In order to overcome the shortcomings of the existing prediction methods, such as short prediction steps and insufficient utilization of spatial-temporal characteristics of road networks, and to predict the freeway travel time accurately, five commonly used prediction models, namely RF(Random Forests),XGBoost(Extreme Gradient Boosting),LSTM(Long Short-Term Memory),KNN(K-Nearest Neighbor), and SVR(Support Vector Regression), were taken to carry out multi-steps prediction of freeway travel time based on the origin and destination data set. A fusion model based on Bayesian linear regression method was proposed. The Long-gang to Bu-long section of Shui-guan Expressway in Guangdong province was taken as a case study. We predicted the travel time of every 15 minutes in the next 2 hours. The results show that the prediction performance of RF model and XGBoost model is stable under multi-steps; the LSTM model has superior prediction performance in the case of short prediction steps; the fusion method integrates the advantages of various prediction methods and has higher accuracy and robustness. The experiments also demonstrate that it has the best prediction performance.

Aiming at the usually reported accidents induced by soil massively stacked in the bridge side，a numerical simulation for the behavior of pile foundation of a highway ramp bridge subjected to surcharge load was carried out． A computational model of bridge，foundation soil，stacked soil was constructed through the finite element software ABAQUS，and variables such as varied structural forms of bridges and pile dimensions were selected． The effects of soil squeezing，deformation of foundation soil，pile-soil coupling relationship，overall displacement and internal force of the bridge were modeled to assess the safety status of the bridge． The influence of dimensions of the pile on the stability of bridge structure was discussed according to the deformation law of the foundation soil，and the safety status of different bridge structures under asymmetric loading were comparatively analyzed． The results show: when mass earth is heaped laterally on the bridge，the bending moment and axial force of the bridge increase by 177. 7% and 27. 3% ，respectively; the internal forces of the main pier and upper structure has no obvious change，indicating that the ramp bridge is safe; the deformation，moment change and the lateral displacement of the bridge pile foundation are consistent with the existing conclusions; the lateral displacement mainly occurs in the layer of soft soil，which may exceed the allowable value under large loading; decreasing the height of the stacked soil and increasing the space between soil piles can prevent the deformation of the foundation soil and reduce the displacements of the bridge structure; the width of the stacked soil has significant influence on the lateral displacements of the foundation soil and little influence on the sink of the foundation soil; clearing the soil near the bridge can effectively control pile foundation deformation and horizontal displacement; the bridge is prone to greater structural deformation under the influence of massively stacked soil after setting expansion joints and supports; linear curvature and load position also have an effect on expansion joint of bridge deformation．

Underactuated ships are facing problems of interference of time-varying multi-source disturbance and sudden changes in control force at the turning points during path following. Aiming at the above two problems, this paper proposed an optimal control method by combining the extended state observer with model predictive control. Firstly, the ESO extended state observer was designed to compensate for time-varying multi-source disturbance and provide low-frequency control input. Secondly, a nonlinear MPC controller was designed to optimize the control force. Finally, the stability of the ESO-MPC cascade controller was proved based on the nonlinear separation principle. The simulation comparison with active disturbance rejection control method and MPC control method verified the effectiveness of the proposed ESO-MPC cascade control method.

Single-vehicle crash, as a common crash type of freeway crash, leads to great loss to society every year.  To reduce the negative impact brought by this type of crash, this study took freeway single-vehicle crash severity as dependent variable and constructed a econometric model to investigate the major influence factors. And some engineering and management countermeasures were put forward. The single-vehicle crash data of Guangdong Kaiyang freeway in 2013—2015 was collected. To describe the weather condition at the time when crash occurred more comprehensively, specifically and accurately, real-time weather data was matched to each crash according to the crash time and location. In terms of methodology, considering that the crash severity was ordered and there might exist heterogeneity in crash data, random parameter ordered logit model was established to fit the data. The results show that, the impact of vehicle type and humidity on crash severity has significant heterogeneity. The significant variables also include driver type, emergency medical services (EMS) response time, wind speed and crash time. Compared to non-professional driver, professional driver has a 6.22% higher probability for severe crash. Compared to other vehicles like coach, truck has a 0.59% lower probability for severe crash. Compared to daytime, the probability of severe crash at night decreases 0.31%. When the EMS response time increases 1min, the humidity increases 1%, and the wind speed decreases 1m/s, the probability of severe crash would increase 0.01%, 0.02% and 0.10% respectively. Finally, according to the results, some safety countermeasures were put forward.

Aiming at the multi-objective optimization ( MOO) problem of the range-extended electric vehicle regenerative braking control strategy，a real-time adaptive regenerative braking control strategy was proposed based on the MOO model and optimal optimization theory． Firstly，the vehicle simulation model was established on AVL / Cruise and Matlab /Simulnk software，and a MOO model was built with the system braking performance ( BP) ， regenerative braking loss efficiency ( RBLE) and battery capacity loss rate ( BCLR) as the objective functions based on NSGA-Ⅱ algorithm． Then Parato optimal solution was obtained through off-line optimization under the comprehensive regenerative braking performance． Combined with the optimization results，a real-time adaptive fuzzy controller was designed． The controller considers the road adhesion and the state of battery，and can adjust the distribution of the regenerative braking work-point online． Simulation results on WLTP driving cyclic conditions show that the adaptive regenerative braking control strategy can effectively balance the relationship among BP，RBLE and BCLR，and it can effectively reduce BP and RBLE while maintaining a small BCLR．

The public transport space is a high-risk environment for the spread of the epidemic because of the dense flow of people and the narrow and closed internal space of the vehicles． The characteristics of customized bus “one person，one seat”and “one stop direct”are just in line with the requirements of epidemic prevention and control． Therefore，considering the advantages of conventional bus and customized bus，this paper proposed a collaborative optimization method of urban conventional bus and customized bus under epidemic prevention and control． It established a total cost minimization model considering risk cost，operation cost and travel cost，and designed an improved column generation algorithm to solve the model． The results show that: the collaborative optimization scheme proposed in this paper is significantly better than the independent conventional bus scheme and customized bus scheme，and ensures the service level of passengers; with the decrease of risk level，the number of conventional bus lines increases，the number of customized bus lines decreases，and the total number of service increases with the decrease of epidemic level． The study confirms the beneficial effect of customized bus on epidemic prevention and control and provides a theoretical guidance for the optimization of public transport system under the situation prevention and control．

The aim of this paper is to explore the influence of the cooperative vehicle-infrastructure system in foggy highway on the driver's visual information processing mode． Firstly，based on the driving simulation platform，a cooperative vehicle-infrastructure system in foggy highway ( CVIS-HF) was designed to obtain the driver's visual behavior parameters． Next，the road ahead was defined as area of interest，and the driver's fixation，saccade and other explicit visual behavior indexes at the global level and area of interest were extracted and analyzed． Finally，three common factors，information extraction factor，perceptual density factor and information search，were obtained by using factor analysis method to characterize the driver's visual information processing mode under the effect of CVIS-HF． The results show that the application of CVIS-HF significantly affects the driver's scanning behavior and the allocation of visual resources for the road ahead． The original information distribution is changed by the intervention of cooperative vehicle-infrastructure system information，which improves the efficiency of information extraction and information search，but reduces the perceptual information density． The research results can provide theoretical reference and technical support for the design and safety application of human machine interface ( HMI) in cooperative vehicle-infrastructure system．

Coastal expressways usually show a certain degree of differential settlement resulted from under-consolidated soft soil, eroding sea salt and excavated fish pond and other factors, which has caused serious safety hazards to high-speed vehicles. To explore the deformation law in soft soil subgrade, the relationship among the surface settlement, horizontal lateral displacement and subgrade cracks was analyzed. Based on the measured settlement data, two variable-weight combination forecasting models on the basis of the reciprocal value in square sum and absolute value of error were established. The engineering examples shows that when the cumulative surface settlement difference was larger than or equal to 60mm and the horizontal cumulative displacement was larger than or equal to 30mm, respectively, the reflective cracks are likely to appear on the soft soil subgrade. Moreover, the variable-weight combination forecasting model by using statistical principles to reasonably allocate the forecast errors from the four growth curve models has better fitting effect and robustness than the single forecasting model. And it can meet the actual engineering requirements and provide a practical and effective method for the post-construction settlement prediction in the soft soil subgrade of coastal expressway.

Ｒejuvenator adjusts the components of the aged asphalt through diffusion and miscibility，so as to restore its road performance and make it meet the application requirements． Therefore，the diffusion of rejuvenator is the main technical problem influencing the regeneration effect of aging asphalt． Firstly，an analysis method of rejuvenator diffusion coefficient was established by using Fourier transform infrared spectroscopy technique and taking the characteristic absorption peak area as the measurement standard． Then，using CTBN as a tracer，a self-designed diffusion test was used to quantitatively analyze the diffusion amount of the rejuvenator with the characteristic absorption peak intensity，and calculate the rejuvenator diffusion coefficient． The results show that the characteristic peak at 1739cm － 1 of the infrared spectrum of the rejuvenator change significantly after CTBN labeling，and the peak area shows a linear relationship with the change of CTBN content． The diffusion amount of rejuvenator in aged asphalt can be effectively reflected by establishing a standard curve． Taking the peak area ratio D1739 /D1458 as the measurement standard，the established theoretical analysis method of the rejuvenator diffusion coefficient has certain reliability． The diffusion coefficient is closely related to the concentration change，and can effectively reflect the degree of aging asphalt regeneration． The diffusion coefficient and the cumulative diffusion amount are proportional to the temperature change，and the growth rate of the two is basically the same． The diffusion rate at the same temperature shows a decreasing trend with the increase of the vertical depth． It is consistent with the change trend of the rejuvenator diffusion amount，and is in compliance with Fick’s second law．

Demand response transit ( DＲT) serves is a new type of public transportation service mode． In order to make DＲT theory more suitable for practical application in low-density population areas，a flexible bus scheduling model considering multiple vehicle types and multiple operating modes was proposed． First，dual decision variables for vehicle type and route were set up，and then a flexible bus dispatch model that considers multiple vehicle types as well as multiple operating modes was built． Then，a hybrid genetic ant colony algorithm HGACO，which is composed of nearest neighbor search algorithm，2-opt method，destination dimensionality reduction operator，genetic algorithm and ant colony algorithm，was designed using the hybrid model of“large loop and small loop”． Finally， taking the three sections from the southwest part of the city to the city center as an example for scheduling，the results show that the flexible bus dispatch model considering the multi-vehicle and multi-ple operation mode is practical and operable，and it can make DＲT in low-density areas more scientific and economical． The improved hybrid algorithm HGACO is superior to the original algorithm in solution ability，accuracy and stability，and can stably obtain a better solution to the DＲT flexible scheduling problem．

A crash risk prediction model for freeway was developed with crash data and real-time traffic flow data to improve road active traffic management. The experimental sample sets were designed in matched case-control study and then the most significant traffic variables that have a crucial impact on the crash were selected by random forest algorithm. Based on the selected variables, the crash risk prediction model was developed in the support vector machine algorithm, and the performance of SVM models in the different kernel functions was compared. Meanwhile, in order to explore the effect of case-control matching ratios on the model performance, multiple sample sets with the different matching ratios were designed for the experiment. The results show that the model can effectively eva-luate the crash risk model according to the real-time traffic flow data. At the same time, the results show that increasing the case-control matching ratio has a particular effect on improving the models performance, and the ratio could be set explicitly according to traffic management needs.

A new coupling thermodynamics analysis method based on the ADAMS and MATLAB joint simulation was proposed for ascent stage of stratospheric airship in complex external environment and multi-physical coupling conditions. An accurate thermal-mechanical coupling mathematical model for ascent of airship was built by using MATLAB in this method. Based on this method, the discrete time-domain method and Newton iterative algorithm were used to decouple the model to obtain relevant parameter curves. The model of airship was established in dynamic environment of ADAMS and a CONSUB subroutine which is available to retrieve the variable data of the airship mass in real time was developed. The visualized simulation control for the ascent stage of variable mass stratospheric airship was realized by applying the decoupled load and calling the subroutine. The coupling thermodyna-mics analysis of a certain stratospheric airship was performed using the above method to obtain the rules of trajectory, attitude and air temperature in air bag. The results show that the design minimum of the pressure difference between the inside and outside of the airbag is not significant for real-time control of airship speed, and the temperature of gas in the air bag rises during the stratosphere stage. The analysis indicates that this method can efficiently and accurately simulate the ascent of stratospheric airship with variable mass under the coupling of complex multi-physical conditions and obtain thermodynamic parameters. This method is of great reference value for the parameter control and optimization design of airship.

In order to solve the problem of coordination dispatching optimization between metro and bus transit network，the bus transit network associated with the metro was divided into collaborative transfer subnetwork and cooperative transport subnetwork． And based on the idea of achieving bus transit network optimization through optimizing subnetworks，the two-objective coordination dispatching optimal model was established． It takes the maximization of the total coordination times in bus transit network as the first object，and takes the maximization of the coordination opportunity of multiple buses and the metro in the collaborative transfer subnetwork and the minimization of the coordination opportunity of multiple buses and the metro in the cooperative transport subnetwork as the second object． Then a heuristic algorithm was developed to solve the model． The results of example analysis show that the model proposed in this paper is correct and the algorithm is effective． The model can set the bus transit timetable which is coordinated with the metro．

A foreground detection method based on semantic segmentation and background reference was proposed to solve the problem of foreign objects detection in the space between platform screen doors and train doors in metro stations． This method used a depth neural network—DifferentNet to detect foreign objects region in images． Firstly， the background image and the image to be detected were obtained during a metro stop at the platform． The feature pyramid was obtained by extracting the feature information of the images through the encoding part of the network， and feature maps of the two images were merged by concatenation． Then the foreground heat map of the image to be detected was obtained by calculating the feature difference in the decoding part． Finally，the heat map was thresholded and filtered to get detection results． The results show that this method can achieve a high foreground IoU of 81. 2% and F1-score of 89. 5% ． Furthermore，it reached 30 fps in speed． The proposed method performed better than traditional methods and other image segmentation networks without background reference．

A numerical prediction method of rolling damping was established for asymmetric catamaran with computational fluid dynamics ( CFD) method and overset grid technology． Firstly，the study simulated the rolling decay curves with different rolling angles and ship speed under different transverse and longitudinal space，and analyzed the rolling damping characteristics． Then based on 3D potential flow theory and considering the correction of the nonlinear rolling damping and nonlinear restoring，the rolling motion response of asymmetric catamaran in regular waves was calculated，and the characteristics of rolling motion under different wave directions were analyzed． Finally， model tests were carried out to verify the numerical prediction methods of rolling damping and rolling motion． It is showed that the model test results are close to the numerical prediction，and the transverse wave disturbance in the side body leads to greater rolling response than that in the main body of the asymmetric catamaran．

Numerical simulation of the resistance and sailing state of high speed amphibious vehicle in still water was conducted with the finite volume method based on Reynolds averaged equation to obtain the resistance characteristics of high speed amphibious vehicle in water. The mesh convergence of mesh was discussed by comparing the resistances of different mesh densities, and the numerical calculation method was validated by comparing the simulation results with model test results. In addition, the different resistance components of the amphibious vehicle were analyzed based on the calculation results of the multiple molding. Then, the changes of resistance and sailing states of the amphibious vehicle model with openings were calculated and analyzed. The results show that, for the amphibious vehicle in transition stage, the proportion of wave-making resistance to the total resistance increases with the increase of velocity (the maximum rate can reach over 60%), the proportion of viscous pressure resistance to total resistance is 30%~40%, and the proportion of friction resistance to total resistance is less than 10%. The resistance increases when the amphibious vehicle added with openings, and the resistance increases by about 11% and the draft increases by about 5% when Fr▽ is 1.297. Compared with the amphibious vehicle model with non-openings,  the amphibious vehicle model with openings shows changes in proportions of different resistance components to the total resistance: the proportion of wave-making resistance decreases and the proportion of viscosity-pressure resistance increases.