This paper presented a station-subpath metanetwork-based approach for modeling and solving the optimal charging infrastructure location problem. Specifically, this paper proposed a two-phase mixed linear integer programming model, and accordingly developed a two-phase algorithm powered by the branch-and-bound method, decomposing any individual routing-charging decision into two phases. The first phase aimed to find the distance-constrained minimum-cost subpath between each charging station pair in the original network, which was handled by the bi-criterion label-correcting algorithm; while the main algorithmic step of the second phase was to, in the branch-and-bound framework, repeatedly identified the minimum-cost path between each origin-destination pair in the metanetwork, which can be efficiently solved by the classic single-criterion label-setting algorithm. The numerical results from applying the developed metanetwork-based approach for the Yangtze River Delta network reveal that the construction budget limit of charging stations and driving range limit of electric vehicles play important roles in charging station location decisions and individual route-and-charge choices. When applied to three different sizes of numerical networks, the metanetwork-based approach proposed in this paper exhibits dominantly higher computational efficiency than the conventional network-based approach for this type of problems of large size.

To promote the deep decarbonization of public transport, a feasible method is to deploy solar-powered bus-charging facilities integrated with energy storage (SBCFES) to reduce the charging cost and carbon emissions of public transport. First, the objective of the SBCFES location problem is proposed. Second, considering the effect of global climate change on the output of PV power-generation facilities in the near future, a budget uncertainty set is constructed for the PV power-generation output and a two-stage robust location model is proposed. The decisions in the first stage include the locations and types of charging stations (conventional charging depot and SBCFES). The decisions in the second stage involves the joint dispatching of PV power generation and energy storage. Finally, considering 17 bus lines in Beijing as an example, the performance of the constraint and column generation (C&CG) algorithm is tested, the structure of the optimal solution is investigated, and sensitivity analyses pertaining to solar-energy resource, the construction cost of PV power-generation facilities, and the on-grid recycling price are performed. Results of numerical examples show that the C&CG algorithm performs well. The SBCFES can significantly reduce the total cost, operating cost, and carbon emissions of the bus system. Compared with the construction cost of PV power-generation facilities, the model results are more sensitive to the change in solar-energy resource. The on-grid recycling price of PV power generation can significantly affect the economic and social benefits of photovoltaic power generation.

Restricted by various conditions, such as fixed vehicle capacity, conventional electric transit systems are struggling to cope with spatially and temporally uneven station demands through flexible dispatch. To overcome this bottleneck, we proposed a station-based demand responsive model for formation and scheduling optimization based on electric modular vehicle technology that enables dynamic capacity adjustment via coupling/decoupling actions. Taking a single bus route as the modeling object, the model optimizes the vehicle capacity reformation and trip sequences for electric modular vehicles to minimize the total cost, including the vehicle dispatch cost, charging cost, and other items. Considering the low battery capacity of modular vehicles, individual energy constraints and charging plans were emphasized in the scheduling model. Because the proposed model is a mixed-integer nonlinear programming problem, auxiliary variables were introduced to further transform the nonlinear part covered in the constraints into linear constraints to improve the tractability of the model. Using the parameters extracted from real operation data of electric buses in Zhengzhou City as model inputs, a variety of optimization indicators with respect to the number of vehicles employed, total system costs, penalty costs for unserved passengers, and charging costs were compared with the other two scheduling strategies. The results show that compared with the traditional electric bus, the modular vehicle scheduling strategy considering station-based demand-response can reduce the total system costs by approximately 26.6%. In particular, the dynamic capacity advantage among stations allows for a 95.4% reduction in the number of stranded passengers, increasing the accessibility of public transport services. In addition, the total cost is reduced by approximately 7.3% compared to that of the non-station demand-responsive modular vehicle scheduling mode, achieving the most significant savings in operating and charging costs. Sensitivity analysis provides a decision-making basis for actual operations regarding vehicle-type selection, battery capacity configuration, and supply/demand balance between passenger services and vehicle scheduling.

As a future sustainable transportation mode, shared autonomous electric vehicles combined with the construction of charging and noncharging parking spaces (mixed parking spaces) at stations effectively reconcile the contradictions between urban travel, parking, and charging supply and demand. This paper considered the joint optimization of mixed parking space allocation, dynamic pricing based on the logit-based elastic demand, and vehicle scheduling. Based on the single-commodity space-time-battery network, a mixed-integer nonlinear programming model was constructed with the number of parking spaces, travel pricing, and space-time-battery flow as the decision variables and the maximization of operational profit as the objective. Due to the difficulty of obtaining high-quality solutions for this model, this paper fitted the logit function using an outer-inner approximation method. Then, using a quadratic-based integer variable decomposition and a parking constraint relaxation method, the original model was reconstructed as a mixed-integer linear programming model and solved using the GUROBI engine. A comparison of the configuration and operational joint optimization results before and after the reconstruction shows that the proposed method effectively improves the solution efficiency. The results of the Chengdu case study indicate that compared to using only charging spaces, mixed parking space allocation increased charging space utilization by 10.59% and decreased charging space rent by 28.87% while reducing relocation costs by 4.15% under the same order fulfillment rate. Compared with fixed pricing for trips, dynamic pricing effectively reduces fleet size by 16.03% while increasing operational profits. The range of dynamic pricing is inversely proportional to the number of vehicle relocations and the actual demand for origin-destination. Higher parking costs led to a sharp decrease in the leasing of noncharging parking spaces. A decrease in the charging rate can reduce the operational revenue by 12.35%, which contributed to an increase of 14.75% in charging parking spaces and 12.34% in noncharging parking spaces.

The planning of electric vehicle (EV) charging station has significant impacts on facility construction costs, long-term profitability, and user satisfaction. In this paper, an optimization location model of multilevel charging stations is proposed, which contains two noninterchangeable optimization objectives, minimizing the total cost of charging station construction and vehicle driving cost, to consider the construction cost and service capacity of different levels of charging stations. By analyzing the big data of the existing vehicle trajectories, various vehicle parking states and durations were retrieved, and the potential charging demand of EVs was obtained based on an improved K-means clustering algorithm for the initial location of charging stations. A multilevel EV charging station location model was constructed to analyze the charging demand, which was solved based on the Tabu Search algorithm to evaluate the secondary locations of charging stations. A charging equipment capacity optimization model was established based on the queueing theory. Global Positioning System trajectory data of electric taxis in Chengdu, China were used for an empirical analysis. The charging station locations were determined based on K-means clustering and multilevel location model. The two schemes were compared based on service capacity, economic performance, as well as convenience issues. The location schemes obtained by the two methods are feasible. The coverage of the 2.5 km service radius of the multilevel locations is 91.2%, slightly worse than that of the K-means clustering scheme (93.6%), while both are above 90% coverage rate. In terms of economic benefits, the scheme based on the location model is significantly better than the K-means clustering scheme. The total profit is increased by 14.4%, while the profit rate is increased by 23.4% based on the multilevel modeling scenario with a relative reduction of 11.7% in construction cost. The proposed location and capacity scheme of EV charging facilities can effectively reduce the construction cost of charging facilities, and improve the profitability and user charging convenience, and thus has social benefits.

The electrification of urban public transportation represents an imperative trend in the development of the public transit sector, offering a means to effectively mitigate air pollution caused by fuel-powered vehicles and reduce dependency on fossil fuels. In this study, we integrated the replacement of electric bus fleet and the layout of charging facilities, aimed at formulating a holistic solution for urban public transportation electrification. To minimize the combined life-cycle costs of the electric bus fleet and the layout costs of charging facilities led to the development of an integrated optimization model. This model coordinates the replacement of electric bus fleet and the layout of charging facilities, taking into consideration both temporal and spatial dimensions. Leveraging the characteristics of the model, the collaborative optimization model was transformed into a mixed-integer linear programming model using equivalence-linear transformation. To validate the applicability of the collaborative optimization model, numerical experiments with different parameter values were conducted using the public transportation network in Jiangyin City, Jiangsu Province as a case study. The research results indicate that under the specified parameter configuration, the collaborative optimization solution yields a reduction of 467 044.3 RMB in the total cost of the combined bus fleet replacement and charging facility layout compared to separate optimization strategies. This demonstrates better cost-effectiveness of the collaborative optimization method. When budget is limited and emission restrictions are not strict, public transportation operators tend to purchase fuel-powered buses that have a price advantage. As battery technology advances, the anticipated decrease in the purchase price of electric buses is poised to drive a gradual decline in the procurement of fuel-powered and hybrid buses. This shift reflects a growing preference for more environmentally friendly electric buses. Furthermore, the electrification process of the bus fleet must be coordinated by deploying charging facilities to ensure that the charging demands of electric buses can be satisfied. The government can encourage operators to accelerate the electrification process of the bus fleet by increasing the social cost of carbon dioxide. The results provide decision support for operating and managing urban bus fleet, as well as deploying charging facilities, and offer policy recommendations for promoting the electrification of urban public transportation.

The physical essence of traffic flow is the energy-driven displacement of matter. To explore the relationship between traffic flow and energy, this study developed a four-factor diagram that included flow, speed, density, and energy based on the power distribution. In this context, the energy/(kJ·km^-1·h^-1) was mathematically described as the product of the energy factor/(kJ·km^-1·veh^-1) and the flow/(veh·h^-1). First, the energy factor curve varying with the average speed was established based on the power distribution of the traffic flow at each spatial average speed under equilibrium conditions. Subsequently, the relationship between the speed and the flow was obtained based on four classical traffic flow fundamental diagram models: Greenshields, Greenberg, Underwood, and Van Aerde. Finally, a flow-speed-density-energy diagram was established by combining the flow and energy factors. When the energy conversion efficiency was 100%, the following results were obtained. For speed-energy, as the speed increases, the energy first increases and then decreases because the flow plays a dominant role in the energy changes. For density-energy, the energy exhibits a pattern similar to that of the speed-energy relationship as the density increases; however, the changing pattern is the opposite, as the density is negatively associated with speed. For flow-energy, the energy increases with the flow. A flow value corresponds to two energy values under congestion/non-congestion conditions. Accordingly, the energy factors have two states as the flow increases: The energy factor is increasing or the decreasing rate of the energy factor is lower than the increasing rate of the flow. This study represents a pioneering effort towards formulating refined policies for energy networks and optimizing the design of energy infrastructure.

With the promotion and application of electric vehicles, the scale of vehicles has exploded. Simultaneously, a series of problems have emerged on the product side, operation side, and service side of electric vehicles:the effectiveness of product quality evaluation is low, the operation safety monitoring is inaccurate, and the service management is incomplete. These problems affect the safe and reliable operation of electric vehicles, restrict the development of the electric vehicle industry, and have become a significant issue for the industry. In the era of automobile digitalization, where big data serves as the core, advancing the development of key technologies in electric vehicle management and services is crucial. This not only ensures the safe, reliable, and efficient application of electric vehicles but also provides essential support and assurance in alleviating consumer safety concerns, ultimately fostering the industry's leapfrog development. To provide a comprehensive overview of technology and innovation in the field, this study extensively discusses the research status of key technologies in electric vehicle management and services. It delves into three aspects:electric vehicle quality assessment and traceability technology, safe operation control and charging service technology, and behavior analysis, identification, and carbon accounting technology. The focus centers on the technical system of 'operation big data +' in the electric vehicle 'quality evaluation-safety monitoring-service management.' Finally, summarizes the existing problems in product quality supervision, operation safety monitoring, and public service management of key technologies of new energy vehicle management and service. Outlook the "quality monitoring-operation control-service management" technology of new energy vehicles with big data analysis and mining as the core. This review can provide a reference for the further improvement of electric vehicle management and service-related technologies and also provide a reference for the future development direction of technology in this field.

Human-machine collaborative decision-making in intelligent vehicles refers to the process of information sharing, interaction, and collaborative decision-making between the driver and driving automation system. Therefore, it is necessary for enhancing the safety, comfort, and traffic efficiency of intelligent vehicles. Currently, studies on human-machine collaborative decision-making technology are fragmented, and relevant review studies are lacking. Therefore, this study primarily reviewed the current research status and future development trends of human-machine collaborative decision-making technology in intelligent vehicles. First, based on a review of the current research status in human-machine collaborative driving, human-machine collaborative decision-making methods are classified based on driving authority and human-machine interaction. The former includes three decision-making modes:human-centric, human-machine driving authority switching, and machine-centric. The latter comprises two decision-making forms:direct and indirect interactions between humans and machines. Furthermore, based on the hierarchical differences in human-machine collaborative decision-making within intelligent driving systems, human-machine collaborative decision-making technology is divided into two key domains:human-machine collaborative behavior planning and human-machine collaborative motion planning. The former encompasses technologies such as driving-authority arbitration, driving-intent coordination, and human-in-the-loop learning. The latter focuses on two categories of methods:path planning and trajectory planning within human-machine collaboration. Finally, a summary and outlook on the development trends of intelligent vehicle human-machine collaborative decision-making technology are presented. The development of intelligent vehicle human-machine collaborative decision-making technology is not limited to the decision-making level but also relies on common technological progress upstream and downstream, and technologies such as multimodal human-machine interface (HMI) and deep reinforcement learning will become crucial driving forces for its further development. In the future, human-machine collaborative decision-making technology will rely on new decision-making intention transmission technologies and large language models to take it to the next level.

To develop a merging control algorithm for intelligent connected vehicles (ICVs) on freeway acceleration lanes interacting with human-driven vehicles (HDVs) on the mainline, we propose a merging control model (DQN-RF). This model integrates the deep Q-network (DQN) algorithm and the random forest (RF) algorithm. First, a roadside data acquisition platform was established to collect the naturalistic merging behavior data of HDVs at a typical merging zone with an acceleration lane on the G70 freeway in China. Second, a human-like merging decision model using RF was built using historical merging environmental contextual data and the merging urgency of the merging vehicle on the acceleration lane as input. We constructed a simulated merging scenario featuring an acceleration lane on the freeway using the simulation of urban mobility (SUMO) platform. Utilizing the Python language, we developed a testing script environment for the deep reinforcement learning algorithm. Additionally, we introduced a longitudinal acceleration control algorithm based on DQN. Finally, the DQN-RF merging control model, which embedded the RF merging decision algorithm into the DQN longitudinal acceleration control algorithm, was established to embrace merging decision control and longitudinal acceleration control in a comprehensive framework. The default lane-changing control algorithm in SUMO, known as "LC2013," was also combined with the proposed DQN algorithm to serve as a baseline model. The simulation results show that, with the same acceleration action value space[-1, 2] m·s^-2, compared to the DQN-LC2013 model, the DQN-RF model receives a higher total reward value. The average accelerations of the ICV for the DQN-RF and DQN-LC2013 models are 0.55 and 0.09 m·s^-2, respectively. Furthermore, the average speeds are 21.4 and 19.7 m·s^-1, respectively. There are no stop-and-wait phenomena observed when the DQN-RF model is adopted, while there are seven stop-and-wait events in 100 turns of simulation when the DQN-LC2013 model is adopted. The proposed DQN-RF merging control model can realize human-like merging decisions and improve the merging efficiency and success rate of the ICV. The DQN-RF model can be used for merging decision control and longitudinal acceleration control of the ICVs on the freeway acceleration lane.

Trajectory planning remains one of the key challenges in the large-scale application of autonomous driving technology. For instance, in autonomous driving, lane-changing trajectory planning algorithms are typically built as an optimization process targeting the cost function. However, manually adjusting the feature weights in the cost function to suit diverse traffic scenarios is a highly challenging task. To address this issue, our study proposed a new lane-changing trajectory planning method based on the heterogeneous edge-enhanced spatial-temporal graph attention network (HEST-GAT). Initially, we employed inverse reinforcement learning techniques to extract feature weight vectors of the cost function from a multitude of expert lane-changing demonstrations, thereby constructing an expert-level lane-changing demonstration dataset. Subsequently, traffic scenarios were modeled as heterogeneous directed graphs, where the locations of traffic participants were defined as node attributes, their relative positions as edge attributes, and the types of connections between them as edge types. These attributes and types were combined to form the edge feature representation. To capture the spatial and temporal information within traffic scenes, we utilized the HEST-GAT network for feature extraction, calculating the feature weights of the cost function for each scenario. We then constructed a cost function that integrates trajectory features and feature weights, generating the final lane-changing trajectory plan through an optimization process. To validate the practicality of our proposed method, multiple rounds of lane-changing trajectory planning tests and assessments were conducted on real driving datasets. The results demonstrate that, in comparison to spatial-temporal graph convolutional network methods, lane-changing trajectory planning based on HEST-GAT significantly reduces errors when emulating expert demonstration trajectories. Specifically, errors in longitudinal comfort, longitudinal efficiency, lateral comfort, and safety are reduced by 5.5%, 5.4%, 1.4%, and 6.0%, respectively. These outcomes prove that our method can generate lane-changing trajectories highly consistent with human driving behavior, exhibiting superior scene adaptability.

To address the problems of tracking accuracy degradation and stability deterioration when operating intelligent vehicles under changing driving conditions, a multi-objective control strategy based on reinforcement learning variable parameter model predictive control (MPC) algorithm was proposed in this study. The proposed method effectively realizes the parameter adaptive tuning of intelligent vehicle path tracking control system. The proposed linear time-varying MPC controller was designed based on a vehicle dynamics model to obtain the optimal front-wheel steering angle and additional yaw moment. Based on the Actor-Critic reinforcement learning architecture, the Deep Deterministic Policy Gradient (DDPG) and Twin Delayed Deep Deterministic Policy Gradient (TD3) agents were designed for control parameter tuning. The gain function was constructed with tracking accuracy and system stability as the goal, and two typical simulation scenarios of docking road and variable curvature road were constructed for the algorithm performance verification. For the docking road scenario, the prediction horizon and weight matrix of the controller were adjusted in time according to the changes in the road adhesion coefficient. Whereas for the variable curvature road scenario, the prediction horizon and weight matrix of the controller were adjusted in time according to the changes in the road curvature. Through joint simulation analyses conducted using MATLAB/SimuLink, CarSim, and Python, the reinforcement learning-tuned MPC was compared with fixed parameter MPC and Fuzzy-tuned MPC models. The results showed that the reinforcement learning methods yielded the best performance regarding the path tracking accuracy of intelligent vehicles under different road conditions, while guaranteeing the vehicle safety as much as possible. Under the docking road condition, compared with the fixed parameter MPC and Fuzzy-tuned MPC models, the average lateral deviation of the vehicle was reduced by 99.8% and 97.6%, respectively, when using the reinforcement learning-tuned MPC, and the average front-wheel angle change rate was reduced by 99.7% and 77.0%, respectively. Moreover, under the variable curvature road condition, the average lateral deviation was decreased by 79.6% and 90.8%, respectively, and the average front-wheel angle change rate decreased by 40.6% and 2.6%, respectively, compared with those obtained when using the fixed parameter MPC and Fuzzy-tuned MPC models.

Scenario-based virtual testing is a necessary approach to developing intelligent vehicles with high safety and reliability. Automatic scenario generation technology is valuable for constructing the test scenario library for intelligent vehicles. Therefore, a scenario generation method based on neighbor object region representation (NORR) and conditional variational autoencoder (CVAE) was developed for dynamic test scenarios with multivehicle to rapidly generate complex test scenarios and control the types of generated scenarios. First, the NORR method was developed to describe the highway scene situation, and the key information of vehicle objects in the test scenario was converted into grayscale images with uniform sizes. Next, the HighD dataset of naturalistic vehicle trajectories was used to extract many scene fragments, and the real-scene library was constructed after data normalization processing. Based on this, the CVAE-based generative model was trained with the number of vehicle objects in the scene as the conditional parameter, which could generate a dynamic test scenario containing eight vehicle trajectories. By calculating the matching error, coverage degree, and unreasonableness of the generated sample set, the performances of the generative model were analyzed in terms of sample authenticity, diversity, and rationality. The verification results show that ① compared with the random trajectory sampling method and generative adversarial network-based model, the quality of the scenario samples generated using the variational autoencoder model is the best. The average matching error of the generated samples is lower than 5.22, the coverage degree is up to 57.2%, and the proportion of unreasonable samples only accounts for 1.7%. ② The proposed NORR method helps improve the scenario generation effect of generative models. ③ The CVAE model can establish the correlation between the conditional input and the generated results. By adjusting the conditional parameter, the number of vehicle objects in the generated scene can be varied.

To address the problems related to the limited perception ability of single sensors and complex late-fusion processing of multi sensors in intelligent vehicle road target detection tasks, this study proposes a multi-modal perception fusion method based on Transformer Cross Attention. First, by utilizing the advantage of cross-attention, which can effectively fuse multimodal information, an end-to-end fusion perception network was constructed to receive the output of visual and point cloud detection networks and perform post-fusion processing. Second, the 3D target detection of the point cloud detection network was subjected to high-recall processing, which was used as an input to the network, along with the target detection output by the visual detector. Finally, the fusion of 2D target information with 3D information was achieved through the network, and the correction of the 3D target detection information was output, yielding more accurate post-fusion detection information. The validation metrics on the KITTI public dataset showed that after introducing 2D detection information through the fusion method proposed in this study, compared with the four benchmark methods, PointPillars, PointRCNN, PV-RCNN, and CenterPoint, the comprehensive average improvements for the three categories of vehicles, cyclists, and pedestrians were 7.07%, 2.82%, 2.46%, and 1.60%, respectively. Compared with rule-based post-fusion methods, the fusion network proposed in this study obtained an average improvement of 1.88% and 4.90% in detecting medium- and highly-difficult samples for pedestrians and cyclists, respectively, indicating that the proposed method has a stronger adaptability and generalization ability. Finally, a real vehicle test platform was constructed, and algorithm validation was performed. A visual qualitative analysis was conducted on selected real vehicle test scenarios, and the detection method and network model proposed in this study were validated under actual road scenarios.

Bridges are crucial infrastructure for traffic and transportation. The inspection of bridge apparent defects is important for ensuring public safety, extending the lifespan of bridges, and identifying risks in a timely manner. They also contribute to improving the reliability and durability of bridges during their operational phases. In recent years, with the rapid development of technologies such as computer vision and artificial intelligence, machine vision has gradually emerged as a new approach for bridge apparent defect inspection. This study conducted a detailed analysis of relevant studies in recent years to review the key techniques for bridge apparent defect inspection based on machine vision, including inspection platform development, data acquisition, image processing, 3D reconstruction, defect localization, and defect parameter quantification techniques. By analyzing the inspection process of existing research, a technical framework for bridge apparent defect inspection based on machine vision was summarized, and the functions and connections between each process were analyzed. The above-mentioned review of key techniques and summary of technical frameworks provide a reference for researchers conducting inspection work on bridge structures. Finally, based on the different levels of automation in data acquisition and defect detection observed in existing studies, this study proposes a hierarchical classification for intelligent bridge apparent defect inspection based on machine vision. This classification includes six levels: manual inspection assistance, defect inspection and localization, partially automated inspection, globally automated inspection, high-degree automated inspection, and fully automated inspection. A comparison of existing literature reveals that although research has moved beyond the traditional stage of manual inspection, it still falls short of achieving fully automated inspection. Therefore, this field has strong research value and broad application prospects.

Recognition and monitoring of cracks is an important part of the current research on the structural health monitoring of bridges. In the field of inspection and monitoring of bridge structures, traditional crack recognition and monitoring techniques, particularly crack monitoring techniques, hardly meet the timeliness and accuracy requirements of practical projects. Crack recognition based on deep learning has greatly improved the efficiency and accuracy of crack detection; however, it can only obtain crack information at a specific moment, and the ability to monitor the process of crack generation and evolution, which is crucial for a more reasonable evaluation and safety quantification of concrete structures, is lacking. In view of this, a systematic study of crack recognition and monitoring methods based on deep learning was performed. In this study, we analyze and discuss the construction benchmark of a crack dataset, improve and optimize the crack detection and semantic segmentation algorithms, propose a real-time recognition algorithm for multitask integration, establish an evaluation method for the model inference effect, and optimize the calculation method of crack parameters, ultimately forming crack recognition and automatic real-time monitoring algorithms for crack dynamic expansion. The results show that the proposed method for intelligent recognition and monitoring of cracks can effectively track the generation of new cracks and the global evolution of existing cracks, and the monitoring data can provide support for a reasonable and quantitative assessment of the current service performance of bridge structures.

The urban multimodal transportation system is a highly complex and diverse transportation network designed to efficiently meet the mobility needs of people, goods, and services within a city. Its complexity originates from many factors including the coupling between different transportation modes, complex interactions between transportation demand and supply, and intrinsic stochasticity and self-organization of an open, heterogeneous, and adaptive system. Therefore, understanding and managing such a complex system is a nontrivial task. However, with the increasing availability of multisource big data in multimodal transportation and other sectors, enhanced computational hardware capabilities, and rapid development of machine learning models, the concept of large models has been applied in various fields, including computer vision and natural language processing. In this study, a conceptual framework, multimodal transportation generative pretrained transformer (MT-GPT), of a data-driven foundation model for multifaceted decision-making in complex multimodal transportation systems was conceived. Considering the characteristics of different transportation modes, the core technologies and their integration methods were investigated to realize this conceptual framework. An expansive data paradigm is envisioned for a foundation model tailored to transportation, along with improvements in hierarchical multitask learning, hierarchical federated learning, hierarchical transfer learning, and hierarchical transformer framework. Application cases of MT-GPT within the “spots-corridors-networks” three-layer large model framework are discussed by constructing “task islands” and “coupling bridges”. MT-GPT aims to provide an intelligent support for tasks such as multiscale multimodal transportation planning, network design, infrastructure construction, and traffic management.

To overcome the limitations of existing wall-climbing robots in detecting apparent diseases in high pier and column structures, a climbing inspection operation robot system based on the ring belt vision scanning of high pier and column structures with apparent diseases was proposed. To meet the functional requirements of the climbing robot, a multi-legged cooperative climbing detection robot platform was designed. The operating parameters of the robot operation process can be set by the host computer, and the attitude information of the robot is collected in real time by using multiple inclination sensors installed on the ring frame. The climbing attitude and accuracy were corrected in real time by the designed system algorithm. A ring-shaped track and visual scanning vehicle that can be mounted on the operating platform was designed to carry an industrial camera, a lighting system, and a high-precision encoder to visually scan diseases in the track direction. Finally, the acquired images were used to recognize and measure superficial diseases, based on which a digital archive of superficial diseases was created. Using the constructed prototype, field tests were performed at Guangyun Bridge in Xi'an and Shouchun Bridge in Anhui Province. The results showed that the robotic system can achieve full-area scanning of the pier and column structure, obtain high-precision visual images of the apparent diseases of the pier and column structure, and accurately identify and quantify the diseases to realize their intelligent detection.

To achieve efficient, safe, and accurate quantitative identification of cracks in concrete towers of large bridges, this study proposes a crack recognition and detection method for bridge towers based on wall-climbing robots and transformers. This method uses a wall-climbing robot based on the negative-pressure adhesion mechanism as the equipment carrier to move quickly on a concrete bridge tower and collect high-resolution data from apparent diseases at close range. A crack quantification evaluation method, including image stitching, a Feature Pyramid Transformer (FPT) crack segmentation network, and quantitative dimension calculations, was established. The width data of the key positions of the crack were obtained, along with the visualization result of the global distribution of the crack. Additionally, the proposed method effectively improved the crack segmentation and boundary location accuracy of microcracks. The feasibility and recognition accuracy of the method were verified experimentally, and the method was successfully applied to the main tower crack detection project of a cross-sea bridge in Eastern China. The multi-scale cracks distributed in the width range of 0.1-3.3 mm on the bridge tower surface were detected, and the maximum error of width quantification was less than 10%. The results of this study have good application prospects and are expected to promote the intelligent development of existing concrete bridge structure detection technologies and equipment.

To fully leverage the advantages of the Transformer model in high-resolution (HR) bridge crack image segmentation, a refined cascaded segmentation method, Cascade CATransUNet, based on the Transformer and Coordinate Attention (CA) mechanism was proposed. Firstly, a TransUNet-based crack feature extraction module was introduced to preliminarily extract coarse-grained crack features at three scales from low-resolution (LR) crack images. The CA mechanism was incorporated into the skip-connection structure of TransUNet to enhance the representation of subtle crack features. Then, based on the extracted coarse-grained crack features at the three scales, two refined operation modules based on physical cascaded structures were designed to sequentially restore fine-grained pixel features of the crack body and edge region from both global and local dimensions. Additionally, to fully utilize the advantages of multi-scale features in the fine-grained representation of crack boundaries, a multi-scale cascaded loss with an active boundary regression term is introduced during the training process. Ablation experiments conducted on HR bridge crack images captured by the unmanned aerial vehicle (UAV) demonstrated the effectiveness of each proposed component. Finally, the comparative experiment conducted on 4 K-resolution bridge crack images revealed that the Cascade CATransUNet surpasses the state-of-the-art high-resolution (HR) refinement networks Segfix and CascadePSP, both of which rely on traditional convolutional neural networks (CNNs). Notably, the Cascade CATransUNet achieved significant enhancements of 5.04% and 7.10% in mean Intersection over Union (mIoU) and mean Boundary Accuracy (mBA), respectively, while retaining identical GPU memory requirements. By adopting the Cascade CATransUNet, it becomes feasible to perform fine-grained segmentation of HR crack images, enabling structural inspectors to obtain more comprehensive and accurate crack information. Consequently, this provides valuable technical support for bridge safety assessment and maintenance decision-making processes.

Superabsorbent polymer (SAP) has been developed as an optimum internal curing material for concrete owing to its superior absorption, storage, and water release behavior. To better understand the relationship between SAP water absorption-release behavior and concrete performance and increase the curing efficiency of SAP, three theories of SAP water absorption-release were summarized. The water absorption-release behavior in different solutions, water exchange mechanism between SAP and cement paste, and relationship between SAP and concrete internal humidity were systematically analyzed. The test methods of SAP water migration behavior were summarized, and the characteristics and applicability of each method were analyzed. The effects of the SAP particle size, dosage, and entrained water amount on concrete properties were discussed from the perspectives of cement hydration, pore structure, and micro-morphology. The results show that the ionic network, solution thermodynamic, and gel phase transition theories can explain the water absorption-release behavior of SAP in different solutions, and the amount of adsorbed and capillary water in SAP affects the water release time of SAP. The water absorption-release properties of the SAP determine the moisture distribution in concrete. The microstructure and macroscopic properties of SAP internal curing concrete are comprehensively influenced by SAP dosage, particle size, and entrained water amount. Appropriate parameters enable hydration products to fill the pores created by SAP, thus refining the concrete pore structure and improving compactness, mechanical properties, and durability. Additionally, the self-healing capacity, resistance to fire spalling, and algae cultivation of concrete are increased by SAP. To improve the design of the internal curing concrete of SAP, the morphological evolution of SAP and its water absorption-release behavior in concrete, as well as the relationship between SAP and water distribution, should be clarified.

Current road design standards consider the perception reaction time of human drivers and operational characteristics of vehicles. However, there are differences between automated vehicles and human drivers in terms of the perception reaction time, perception distance, and perception height. These differences may lead to challenges for automated vehicles under specific road conditions such as complex road geometries and irregular intersections. To understand the impact of road infrastructure on the operation of automated vehicles, it is necessary to study road readiness for automated driving. Quantitative studies on the effects of different road types, road geometry designs, traffic control facilities, and roadside infrastructure on the safe operation of automated vehicles are insufficient. This paper summarized the findings from three perspectives: road segments, intersections, and traffic signs and markings. The results indicate the following: ① Existing research has established a relationship between road geometry design, intersection geometry design, and the perception capabilities of automated driving. It was found that design parameters such as the horizontal curve radius, chord length, and curve deflection angle affect the sight distance in automated driving. ② Real-world testing showed that the road type, horizontal curve curvature, and lane width have a significant impact on automated driving failure events. ③ An increase in the market penetration of automated vehicles will lead to clearer rules for interaction among automated vehicles and enhanced road readiness. ④ The accuracy of automated driving perception and recognition is affected by the retroreflectivity and placement of traffic signs, whereas the failure probability is related to the size of traffic markings, retroreflectivity coefficient, and extension edge lines. To satisfy the future demands of automated driving applications, it is necessary to conduct tests on existing roads to assess the impact of various complex operating conditions on the operation of automated vehicles. It is necessary to examine the impact of road design on the performance and safety of automated vehicles on new roads.

To reduce the residual deformation of conventional frictional energy dissipation braces under severe earthquakes, a novel self-centering variable frictional energy dissipation brace (S-SCFB) based on a shape memory alloy (SMA) was developed. The S-SCFB mainly consists of an SMA plate ring self-centering system and frictional energy dissipation system. First, the configuration of the novel brace is described, and its working and self-centring principles were revealed. The mechanical properties of the SMA plates were studied by conducting material tests, and a simplified analytical model of the novel brace was established. Second, a solid numerical model of the brace was established using ABAQUS. The simulation results were compared with the calculation results of the simplified analytical model, and the hysteresis performance and influencing factors of the novel brace were studied systematically. Simultaneously, the restoring force model of the novel brace was developed using OpenSees software. Finally, owing to its excellent hysteresis performance, the novel brace was applied to the double-column bridge piers to improve the seismic resilience of the bridge piers. The results show that the constitutive model of the SMA plate has a “flag-shaped,” which has a high bearing capacity, good deformation capacity, and good self-centering ability. The assembled S-SCFB based on SMA plates exhibits stable energy dissipation capacity, excellent self-centering ability, and no residual deformation during unloading; the established simplified analysis model agrees with the finite element simulation results. The hysteresis performance could be effectively adjusted by changing the design parameters of the S-SCFB. An additional S-SCFB can effectively improve the strength and stiffness of bridge piers, reduce the residual displacement of the structure, and effectively improve the seismic resilience of the structure.

To investigate the impact of different factors on the structural response of segment loads in rock tunnel structures, this study employs a load structure theory model to obtain analytical solutions for the external load, internal force distribution, and displacement response of rock tunnel structures. Taking into account the structural characteristics of rock tunnel segment loads, this study investigates the impact of seven key influencing factors: overlying strata load, water head height, rock lateral pressure coefficient, equivalent bending stiffness coefficient, tunnel diameter, segment thickness, and concrete grade on the structural response of segment loads. The findings are validated through on-site monitoring tests conducted at the Jinxiu Tunnel in Chengdu. The research reveals that reducing overlying strata load and the coefficient of lateral pressure increases internal forces and displacements of tunnel segments. Increasing hydraulic head height has minimal effect on internal forces but significantly raises axial force levels. Increasing the equivalent flexural stiffness coefficient does not affect internal forces but slightly reduces radial displacement. A slight increase in segment bending moment, axial force, and radial displacement is observed with an increase in tunnel diameter. Segment thickness has a minor impact on internal forces, with thicker segments causing a slight increase in radial displacement. Changes in concrete grade have minimal effect on the tunnel's structural response to load. Comparison between field monitoring results and calculated model results exhibits similar patterns in the structural response under load, indicating a highly accurate analysis method proposed in the study.

Due to the particularity of their occupation, commercial vehicle drivers are prone to distracted driving behavior during driving, resulting in major traffic accidents. In order to improve the detection accuracy and generalization of distracted driving behavior of commercial vehicle drivers, we proposed a driver distraction behavior detection method based on the improved MobileViT network. Based on the natural driving real vehicle tests, we constructed a dataset of distracted behavior of commercial vehicles ，including safe driving, using phone, drinking, hair or makeup and talking to copilot. Then, the attention mechanism was introduced into the lightweight MobileViT network. And the optimal classification model MobileViT-CA was designed by selecting effective network backbone MobileViT, attention module CA, and network embedding position. The research results show that the MobileViT-CA classification model proposed in this paper can effectively improve the performance of the classification network, and the accuracy of the distraction behavior dataset of commercial vehicle drivers and the State Farm dataset under normal lighting conditions reaches 96.57% and 99.89%, respectively. Meanwhile the model has the advantages of small size, high detection accuracy, high reliability and generalization ability.

Decision-making and planning are the core functions of automated driving systems and the key to improving the driving safety, driving experience and travel efficiency of automated vehicles. The main challenges faced by decision-making and planning are how to meet the extremely high reliability and safety requirements for automated driving, and how to effectively deal with scenario complexity, environmental variability, traffic dynamicity, game interactivity, and information completeness, as well as how to generate human-like driving behavior, so that vehicles can integrate into the traffic ecosystem naturally. A systematic and overall review of the technical points of decision-making and planning is presented in this paper to gain a comprehensive understanding of their frontier issues and research progress. Firstly, the research progress of situational awareness-oriented behavior prediction is reviewed from three perspectives, namely data-driven driving behavior prediction, probabilistic model driving behavior prediction, and personalized driving behavior prediction. Secondly, behavior decision-making is summarized into reactive decision-making, learning decision-making and interactive decision-making, all of which are analyzed in turn. Thirdly, motion planning and its applications are compared and analyzed from a methodological perspective, including graph search methods, sampling methods, numerical methods, interpolation and curve fitting methods, etc. Additionally, the key scientific issues and major research progress of end-to-end decision-making and planning are summarized and analyzed. Finally, the significant impact of decision-making and planning on improving the intelligent level of automated vehicles is summarized, and the future development trends and technical challenges are prospected.

To further enhance the strength of the field of automotive engineering and promote the development of automotive technology in China, this study systematically analyzes the academic research status, cutting-edge hot issues, latest research results, and future development prospects in the field of automotive engineering at both domestic and international levels from six aspects:automotive electrification and energy saving, intelligent and connected vehicles, vehicle dynamics and control, automotive NVH (noise, vibration, harshness) control and lightweight control, automotive electronics and electrical (E&E) and software technology, and automotive testing and evaluation technology. Automotive electrification and energy saving constitute key aspects of pure and plug-in hybrid electric vehicles, hydrogen fuel cell vehicles, extended-range electric vehicles, and energy-saving vehicles. Intelligent and connected vehicles are objectives of the research on intelligent driving environment perception technology, autonomous driving positioning technology, intelligent vehicle decision-making and planning, motion control technology, vehicle-road coordination, intelligent safety technology, Internet-of-vehicles safety technology, and intelligent cockpit and human-computer interaction technology. Vehicle dynamics and control are addressed by the research on brake-by-wire, steer-by-wire, suspension-by-wire, and chassis-by-wire cooperative-control technologies. Automotive NVH control and lightweight control involves the prediction and optimization of automotive aerodynamic noise, NVH control of pure electric vehicle systems, acoustic metamaterials and automotive structural vibration control, automotive noise active control, and automotive lightweight and collision safety technologies. Automotive E&E and software technology is addressed by the research on automotive E&E architecture, automotive software technology and OTA (over the air) upgrade, chip and system function integration, etc. Automotive testing and evaluation technology is addressed by the research on testing and evaluation technology of fuel vehicles, new energy vehicles, and intelligent and connected vehicles. This review provides a reference for further development of automotive engineering research in China, and guidance for the innovation in key technologies of the automotive industry.

Historical earthquake damage reveals that tunnels crossing active faults suffer severe damage and are very difficult to repair and rebuild after the earthquake. Therefore, improving their seismic resilience is a key challenge for tunnel construction in active fault zones with strong earthquakes. This paper firstly summarizes and analyzes the lessons from earthquake damage and identifies the key aspects of seismic design of tunnels crossing active faults, including the assessment of the seismic hazard of the engineering sites, the seismic design strategies of tunnels crossing active faults, and the prevention and control measures. Secondly, based on the literature review, the paper presents the current state of the art of seismic research on tunnels crossing active faults, focusing on the seismic analysis methods, the tunnel structural failure mechanisms, and the seismic control measures. Then, the paper establishes a unified concept of seismic resilience of tunnels crossing active faults and a design framework based on the core idea of "pre-earthquake reserve, mid-earthquake stabilization, and post-earthquake restoration". The paper also proposes the objective of seismic resilience of tunnel structures, considers the strong earthquake-dislocation coupling effect of active faults, develops a zoning guideline of seismic defense for tunnels with "site zoning and structural segmentation" and a design concept of "resisting/mitigating, adapting, and inducing/avoiding/recovering". Finally, the paper discusses the key scientific and technological issues that need to be urgently addressed in the seismic research of tunnels through faults and outlines the future research directions in this field. This study aims to provide a unified concept of seismic resilience defense and design strategy for tunnel construction crossing active faults, and also to point out the focus areas for future seismic research.

With the rapid development of artificial intelligence, deep learning algorithms for nonlinear propose a new approach for solving the persistent dilemma of tunnels and underground engineering relying on empirical designs. In this study, by fusing multiple indices (mechanical and deformation control indices) with the correlation coefficient of the support system synergy degree, an evaluation standard for support systems, characterized by the degree of fit, was proposed. Using this evaluation standard, the data of 718 highway and 486 railway tunnel sections were collected to build a database for algorithm training. Eight attributes about the background information of tunnel engineering, including rock hardness degree, integrity degree, rock thickness, underground water volume, buried depth level, geological structure, construction method, and internal contour type, were considered input indicators. Eight attributes of the support system, including shotcrete+steel mesh, rock bolt, steel arch, secondary lining, and auxiliary measures, were considered output indicators. The input and output indicators were then quantified. After comparing the characteristics of the PSO-SVM, SA-PSO-SVM, and CLS-PSO-SVM in the application of the intelligent feedback model of the support system, the generated intelligent feedback model was tested. The results show that the evaluation method first eliminates the weak design scheme. The degrees of fit of the strong support and general support schemes are 4.28 and 4.68, respectively, which verifies that the method can evaluate the material utilization rate while ensuring structural safety. Among the three intelligent algorithms, the CLS-PSO-SVM algorithm, with the broadest search range, had the highest feedback accuracy but the longest time consumption, whereas the PSO-SVM algorithm had the shortest time consumption but the lowest accuracy. Finally, the accuracies of the five output labels designed using the CLS-PSO-SVM algorithm are 93.4%, 92.6%, 89.3%, 91.8%, and 94.3%. The collective accuracy of the five output indices is 81.1%.

Considering the limitations of the traditional resistance strain gauge method for on-site testing the strain of feet-lock pipe, a φ50 Fiber Bragg Grating (FBG) feet-lock pipe was designed and manufactured based on FBG sensing technology. A field test of the FBG method for testing the strain of feet-lock pipe was carried out. The stress features and supporting function of the feet-lock pipe in soft rock tunnel were analyzed. Then, a mechanical analysis model of feet-lock pipe in soft rock tunnel was established, and the formula for calculating the support stiffness of feet-lock pipe on the feet of primary support was derived. The influence law and sensitivity of each parameter of feet-lock pipe on the support stiffness were quantitatively analyzed. The results of this analysis show that the strain variation law at each measuring point of the feet-lock pipe was very complicated owing to the construction disturbance and connection method of the feet-lock pipe. From the overall strain distribution of the pipe, the strain of the feet-lock pipe near the steel rib significantly exceeds those of other parts of the pipe, and the change amplitude of the strain at the end of the pipe near the steel rib obviously exceeds that near the surrounding rock. The feet-lock pipe is primarily subjected to lateral bending deformation in the upper and lower directions, and is subjected to compressive load transmitted by the tunnel feet in the axial direction. As the angle of the feet-lock pipe increases, its axial compression characteristics become increasingly significant. The axial anchoring effect of the feet-lock pipe is very small, primarily exerting lateral bending and shear resistance to constrain the settlement of the tunnel feet, and the constraint effect on the horizontal convergence deformation of tunnel feet is limited. Increasing the diameter of the feet-lock pipe is the most effective way of enhancing the vertical support stiffness of tunnel feet. When the axial support condition of feet-lock pipe is poor, increasing its angle significantly reduces the vertical support stiffness of tunnel feet. At this time, the steel rib should be closely attached to the surrounding rock. As the length of the feet-lock pipe increases, the vertical support stiffness of the tunnel feet provided exhibit rapid growth initially, followed by gradual growth. Considering the stress characteristics of the feet-lock pipe and the engineering economy, a length of 2.5 m is recommended for the φ50 feet-lock pipe.

To improve the assembly accuracy and quality of super large diameter shield tunnel segments, the adaptive assembly and deviation correction curve calculation of the universal ring segment were studied. This study elucidates the interrelationships between the three axes of shield tunnels and the controlling factors influencing the adaptive assembly of tunnel segments. A comprehensive function that considers various controlling factors is established for the adaptive assembly of tunnel segments. In addition, the relative position between the shield machine and the tunnel design axis is classified. By considering factors such as shield tail gap control and the maximum stroke difference of the thrust jack, the minimum deviation correction curve radius is determined. A mathematical model for the corresponding shield excavation deviation correction curve is established, thereby presenting a rational design of the shield excavation deviation correction curve. Finally, using Python, a dynamic autonomous deviation correction system for shield tunnels capable of achieving multi-objective control is developed. Applying the system to a major engineering project can yield accurate, efficient, and information-based adaptive assembly of tunnel segments, the deviation of the shield excavation curve, and precise propulsion of the thrust jack throughout the process.

The steel shell immersed tunnel is prone to strength degradation, structural bearing performance degradation, and unstable failure under high temperature of fire. Therefore, carrying out basic research on the temperature field distribution of the steel shell immersed tunnel structure under high temperature is necessary. In this study, systematic research was carried out based on the national major project "Shenzhong Link Submarine Immersed Tunnel". First, a simplified analytical formula for solving the transient temperature field of steel shell-concrete structure under high temperature was derived. Second, based on local full-scale fire tests of tube structure, the contact thermal resistance of the steel shell-concrete interface at the engineering scale was fitted. The accuracy of the theoretical solution was verified by establishing a numerical model with an equivalent thin layer structure. Finally, the temperature field was calculated and analyzed. The following conclusions can be drawn from the analysis of three methods. ① Based on the fitting of theoretical analysis formulas to the fire test results, the approximate value of the contact thermal resistance of the steel shell-concrete interface is 0.01 m²·K·W^-1. The density, heat capacity, and thermal conductivity of the equivalent thin layer structure are 1.29 kg·m^-3, 1 005 J·(kg·K)^-1, and 0.1 W·(m·K)^-1, respectively, according to the fitting analysis of the numerical simulation results with the equivalent thin layer structure and the theoretical analytical solution. ② Through theoretical analysis methods, the fire temperature field was analyzed, and the analysis conclusion was basically consistent with the numerical simulation and model test results. The influence depth of fire high temperature on steel shell-concrete structure is primarily approximately 400 mm, and the temperature of the structure does not increase significantly after 400 mm. ③ Owing to the different thermal conductivities of the steel shell and concrete, as well as the interface contact thermal resistance effect between them, the temperature at the interface between the steel shell and concrete appears to suddenly decrease and increase at different stages of the fire curve. Moreover, the temperature field of the entire tube wall structure appears to be high outside and low inside during the heating, constant temperature, and early cooling stages, and low outside and high inside during the later cooling stage. The temperature field distribution law proposed in this study provides a basis for engineering design, and the determination and equivalent simulation method of interface contact thermal resistance may provide reference for similar engineering calculation and analysis.

Currently, China has a large stock of industrial waste materials (IWM) but a low recycling rate. The comprehensive utilization of IWM is of great significance for promoting the sustainable development of society. Owing to increasing environmental protection regulations and natural resource shortages, the application of IWM to treat poor subgrade soil has become an important approach to alleviate the road material shortages and accelerate green construction material development. This study used a typical IWM to provide a detailed overview of the entire subgrade soil modification process. The water washing method was used to process the red mud, slag, and fly ash, whereas the steam granulation method was employed to treat the steel slag. Subsequently, the preprocessed IWM was used to modify the engineering properties of the problematic soil subgrade via either the individual addition of IWM, joint addition of IWM and cement/lime, or alkaline activation of IWM. To address the different engineering properties of expansive soils, loess, and heavy-metal-contaminated soils, IWM is typically used to improve expansive soils and loess, and compound addition methods are used to treat heavy-metal-contaminated soil. Improved IWM technologies significantly reduce the liquid limit and plasticity index of problematic soils while improving their strength and durability and effectively suppress the migration of heavy metal ions. Thereafter, the macroscopic and microscopic physicochemical properties of the IWM-treated soil were summarized in terms of mechanical properties, microscopic morphology, chemical composition, and reaction mechanism. The mechanism by which IWM-treated subgrade soils improved was analyzed and improvement plans for different problematic soil subgrades was proposed. Currently, few studies consider the long-term performance evolution of IWM-modified problematic soil subgrades. Therefore, further extensive research in this field is recommended.

The development status and application prospects of intelligent motorway traffic application technologies are analyzed to promote the intelligent transformation and upgrading of motorways and realize the effective integration of new technologies and traffic applications. First, by combining local and international intelligent road development experience and technical achievements, an intelligent motorway system is defined by drawing on the technological evolution process of the intelligent vehicle highway system (IVHS). Furthermore, the positioning of the intelligent motorway demand is discussed based on traffic applications, functions and technologies. Subsequently, problem-oriented, demand-driven, and technology-supported, it focuses on the three aspects of precise perception of road network status, cooperative control of traffic operation, and intelligent service of user interaction to review traffic application technologies. Based on the review summary, the challenges in the development and application of related technologies and the research focus and development direction of the future field are discussed. It is found that the synergistic development and integration of these transportation application technologies is an essential condition for the coupled development of multiple fields, such as road network integration and perception, cooperative traffic management and control, safety demand management, infrastructure management and maintenance, and intelligent service interaction. In future technological developments, vehicle-road-cloud cooperative perception and multisource asynchronous heterogeneous data fusion are technological breakthroughs, and intelligent cooperative management and control, operation and maintenance, and service interaction are technological transformations. In engineering practice, specific experimental scenarios should be gradually transitioned to complex motorway scenarios. The traffic monitoring system should be synergized with intelligent terminals, and efficient traffic prediction, hybrid traffic synergy, and preventive intelligent maintenance are challenges of these applications. Through the review and analysis of this study, it can provide valuable references for technology research and development and engineering applications of local intelligent motorways, as well as the technology application transformation of future demonstration projects.

With the continuous acceleration of urbanization, urban functional zoning has shifted the emphasis from scale growth to quality improvement. Optimizing urban spatial layout, deepening multi-mode integration of traffic operation, and building an integrated travel service platform are the core needs of urban transportation's digital transformation. Urban traffic travel characteristic mining and behavior analysis are helpful in improving the urban multidimensional transportation service system, meeting diversified travel needs, promoting the rational development and utilization of the urban land, and guiding the urban decision makers to formulate reasonable planning measures. Cellular signaling data (CSD) has the advantages of wide coverage, large sample size, and long-term continuous monitoring. Cellular-network big data can analyze the origin-destination (OD) distribution and travel behavior pattern of individuals or large populations at a lower cost, thus being important for promoting the development of future urban intelligent transportation. In this paper, the existing traffic information collection methods, development constraints, and the importance of cellular signaling data are summarized, and the architecture of an intelligent transportation system based on cellular signaling data, key technology research progress, and future development direction are reviewed. First, according to its functional planning and development requirements, the architectural design and application framework of the CSD-based urban traffic big data system (C-UTBDS) are proposed. Second, from the perspective of cellular network travel chain construction, the structure of the cellular mobile communication network, travel chain characteristics, and extraction framework are summarized; the noise data of the travel chain, data optimization methods for track vibration, and the road network matching technology, when the travel chain trajectory is integrated with the actual road network, are expounded. Then, considering the needs of urban spatial structure optimization and multi-mode traffic development driven by cellular-network big data, the research status of urban traffic travel characteristics mining is introduced in detail, including population flow monitoring, travel pattern recognition, behavior analysis and prediction. Finally, the technical direction and development trend of future research are highlighted from the aspects of 5G optimization positioning, multi-source data processing and mining, fine-grained travel pattern recognition, and component-based system model architecture construction.

The innovation of engineering materials is a major driver of the development for civil engineering structures, and the reformation of engineering structures continually promotes the revolution for engineering materials. Ultra high performance concrete (UHPC) is a new class of concrete that has excellent mechanical properties including high strength, high ductility, high durability, high impact resistance, etc., which is suitable for the new generation bridges with long span, light weight, and high performance. To facilitate the UHPC bridge researches and implantations, this paper systematically summarizes the recent research progresses, cutting-edge highlights, current issues, corresponding solutions, and development prospect for UHPC bridges. The paper firstly summarizes the research achievements for UHPC materials, including mix design, mechanical properties, and development of UHPC for bridges; then concludes the design theories for UHPC structures, including the contributions of fibers in flexural and shear design, impact and blast resistance, fatigue design, etc. The achievements of structural system innovations, such as UHPC bridges without stirrups, steel-UHPC composite bridges, UHPC columns for seismic resistances, UHPC bridge overlay, UHPC for bridge retrofit. In lights of the current research and applications, the major challenges and technological path for large-scale application of UHPC in bridge engineering are proposed, aiming to provide new visions and references for UHPC academic researches and large-scale applications in bridge engineering.

With the implementation of the "dual carbon" strategy by the country and the arrival of the era of industrial construction, bridges as lifeline node projects are being developed toward assembly and industrialization. As a high-performance composite structure bridge type, the concrete-filled steel tubular (CFST) composite truss bridge has bearing capacity, disaster resistance, and assembly advantages. Integrating the concepts of "industrial construction" and "green building materials" effectively achieves the green construction of CFST truss bridges. Therefore, regarding high transmission systems, high-bearing-capacity structural constructions, and high-bearing-capacity joints, a rectangular concrete-filled steel tubular (RCFST) composite beam bridge is a high-performance bridge structure. Further, considering high resilience and economy, the advantages of the RCFST composite truss bridge are discussed, and the seismic performance and economy of a conventional concrete beam bridge are compared. Subsequently, the concept of the industrialized construction of RCFST composite truss bridges was elaborated from the perspective of fully prefabricated assembly units and on-site rapid assembly of prefabricated parts, and structural measures suitable for rapid assembly were proposed. Applying alkali-activated UHPC concrete, which has the advantages of green and high strength, to CFST composite beam bridges was conceived and envisaged. Finally, typical engineering practices confirmed that CFST composite truss bridges are lightweight and high-strength, have clear force transmission, and exhibit efficient assembly and construction performance.

Conditionally automated driving systems, though advanced, are not universally adept at managing all driving scenarios and require driver intervention when necessary. The efficacy of driver take-over is paramount for the safety, user experience, and broader acceptance of such automated vehicles. A plethora of recent studies rigorously examined driver take-over performance, but certain challenges persist. This study presented a systematic review of extant literature concerning driver take-over performance, encapsulating the influencing factors, the models, and the various evaluation methodologies employed. The determinants influencing take-over performance span driver-specific factors, traffic environment parameters, and features of the automated driving systems. Concerning the modeling of take-over performance, distinctions were drawn between classical statistical models, machine learning approaches, and structural equation models. The study further encapsulated prevailing evaluation indices specific to take-over performance, alongside holistic evaluation methodologies. Findings from the review pinpoint that current indicators for influencing factors lack comprehensiveness. Additionally, a discernible imbalance between interpretability and predictive accuracy is observed in the existing models. Furthermore, the present evaluation methods for take-over performance necessitate refinement. As a roadmap for future inquiries, this study advocates for the initiation of comprehensive measures of take-over performance based on subjective evaluation of human drivers. Then, there is an imperative to develop quantitative indicators of the influencing factors of take-over performance from human-machine-environment aspects. Conclusively, calls are made for crafting high-precision predictive models for take-over performance that duly recognize the intricate interdependencies of myriad influencing factors. Pursuing such avenues of research is vital to provide theoretical support for elevating driver take-over performance, thus propelling the evolution of conditionally automated driving.

As vehicle-infrastructure collaboration technologies gain traction in the transportation sector, traffic control is increasingly characterized by automation, proactiveness, and cooperative functionality. In this evolving landscape, Trajectory based Traffic Control (TTC) has been introduced as an avant-garde traffic control approach. TTC orchestrates the amalgam of connected and automated vehicles (CAV) and human-driven vehicles (HV) by fine-tuning the trajectories of CAVs to optimize traffic flow efficiency. Despite its global recognition as a pivotal research area in transportation, TTC remains embryonic in its theoretical stages with fragmented research content. This study offers a comprehensive review of extant literature on TTC, elucidating its foundational concepts and distinguishing features. A tripartite analytical structure is employed, delving into the TTC framework, local coordination control system, and the global coordination control system. The advancements and modular intricacies within the TTC framework are explored. A salient observation from this review is that, while TTC theoretical research has matured, many foundational assumptions in studies remain robust. Factors, such as swarm characteristics, operational risks, and the inherent heterogeneity of semi-automated and connected traffic in tangible traffic scenarios, have been marginally addressed. Consequently, transitioning this theoretical knowledge into large-scale, practical applications remains challenging. Highlighting prospective avenues for further exploration, the study emphasizes the significance of traffic group game theory, consensus mechanisms, robust TTC approaches addressing diverse risks, and the rigorous testing and validation of TTC within large-scale heterogeneous traffic environments. These types of recommendations aim to shepherd future TTC research endeavors towards more pragmatic and holistic outcomes.

Complex wind environments, nonlinear aerodynamics, and wind-structure interactions are the main challenges in wind-engineering research. During the past several decades, the number of data accumulated from wind tunnel tests, numerical simulations based on computational fluid dynamics, and structural health monitoring has become massive, providing valuable resources for addressing these challenges. With the development of deep-learning technology, machine learning (ML) has achieved great success in nonlinear science and engineering problems owing to its nonlinear representation capabilities, powerful optimization algorithms, excellent generalization performance, and flexible network architecture. Emerging data-driven approaches based on ML algorithms have helped address these challenges in wind engineering and increased physical and engineering knowledge based on the available wind-engineering data. The application of ML in wind engineering involves all aspects of the wind-engineering field, such as the wind environment, aerodynamic and aeroelastic forces, wind-induced vibrations, aerodynamic optimization and control, and wind disaster assessment. The purpose of this paper is to introduce the research progress and state-of-the-art technologies in ML and artificial-intelligence applications for bridge wind engineering.