Abstract With the increasing development of intelligent detection devices, a vast amount of traffic flow data can be collected from intelligent transportation systems. However, these data often encounter issues such as missing and abnormal values, which can adversely affect the accuracy of future tasks like traffic flow forecasting. To address this problem, this paper proposes the Attention-based Spatiotemporal Generative Adversarial Imputation Network (ASTGAIN) model, comprising a generator and a discriminator, to conduct traffic volume imputation. The generator incorporates an information fuse module, a spatial attention mechanism, a causal inference module and a temporal attention mechanism, enabling it to capture historical information and extract spatiotemporal relationships from the traffic flow data. The discriminator features a bidirectional gated recurrent unit, which explores the temporal correlation of the imputed data to distinguish between imputed and original values. Additionally, we have devised an imputation filling technique that fully leverages the imputed data to enhance the imputation performance. Comparison experiments with several traditional imputation models demonstrate the superior performance of the ASTGAIN model across diverse missing scenarios.

Abstract The study of Reynolds number (Re) effects is crucial for optimizing train aerodynamics, enhancing safety and reducing energy consumption of high-speed trains. In this paper, a wind tunnel test was carried out to investigate the influence of Re on the train aerodynamic performance considering the shift of the air compressibility, which has not yet been explored to date. The test was conducted in a low-speed and large-scale tunnel with a stationary floor and the vehicle model was based on a 1/8th scaled train with three units. The Re ranges from 0.75 × 106∼3.12 × 106 by accelerating the uniform wind speed from U = 27.8 m/s to U = 115 m/s with zero-yaw. The Mach number (Ma) of the maximum speed scenario has exceeded 0.3, indicating that the airflow can be considered as being in the compressible range. The results show that the aerodynamic characteristics of high-speed trains exhibit a self-similarity region of Re, which is dependent on the flow velocity. The aerodynamic loads change little when Re ≥ 1.51 × 106, which corresponds to U ≥ 55.6 m/s. Therefore, the compressibility of the airflow within the range up to U = 115 m/s has a negligible effect on aerodynamic loads, and can thus be disregarded. However, the surface pressure significantly decreases when the incoming flow surpasses 0.3 Ma and transitions into a compressible state. While the compressibility has a relatively minor impact on macroscopic aerodynamics, it cannot be overlooked when considering detailed flow field, such as surface pressure.

Abstract To analyse the vertical dynamic characteristics of the aircraft towing system under different constraints on the nose landing gear wheels of the aircraft during the towing slip-out mode, a dynamic model of the towing system considering the constraints between the clamping mechanism and the aircraft nose landing gear wheels was established based on the general towing system dynamic model. On this basis, an analysis was conducted to determine whether considering the aircraft wheel constraints affects the vertical vibration acceleration of the towing vehicle and the nose landing gear in low-speed (10 km/h) and high-speed (40 km/h) operating conditions. With the consideration of constraints at both ends of the aircraft wheels, the vertical acceleration of the towing vehicle's centre of mass increased by 153% and 172% at low speed and high speed, respectively, compared to not considering the aircraft wheel constraints. Additionally, with the consideration of constraints at both ends of the aircraft wheels, the vertical acceleration of the nose landing gear's centre of mass decreased to 20% and 57% at low speed and high speed, respectively, compared to not considering the aircraft wheel constraints. An analysis of the vertical vibration acceleration of the towing vehicle under different wheel constraint conditions found that the Root Mean Square (RMS) value of the vertical vibration acceleration of the towing vehicle's centre of mass was minimized when the clamping angles of the clamping mechanism to the nose landing gear wheels were 63° and 64°, respectively. Under this clamping angle, the influence of the clamping forces at both ends of the clamping mechanism on the vertical vibration acceleration of the towing vehicle was minimal. The research results provide valuable reference for the direct constraints between the clamping mechanism and the nose landing gear wheels in the aircraft towing slip-out system.

Abstract Variable speed limits (VSL) stands out as a well-established and effective strategy to alleviate traffic congestion and enhance traffic safety on motorways. It allows variable message signs (VMSs) to dynamically determine the speed limits according to real-time traffic states. This paper introduces an innovative online feedback control approach designed to regulate speed limit values on VMSs, addressing multiple bottlenecks while considering their spatiotemporal constraints. Moreover, we offline optimize the gain coefficients of this feedback control approach in the simulation-based optimization (SBO) framework. Specifically, with average and variance of space-mean speeds as bi-objectives, a stochastic SBO model considering uncertain traffic demands and compliance behaviours is established and solved by a bi-objective surrogate-based promising area search (BOSPAS) algorithm. Real-field experiments conducted in Edmonton, Canada, demonstrate the well-performing bi-objectives of the proposed approach, especially in handling uncertain compliance behaviours and traffic demands. Compared with the uncontrolled scenario, the feedback control schemes with the offline optimized gain coefficients improve the average and variance of space-mean speeds by up to 16.2% and 20.8%, respectively. Meanwhile, by the comparison of detailed performances, it is found that the optimized control schemes perform better than the uncontrolled scheme from the overall and local aspects. In conclusion, this study puts forward a general framework that applies an online feedback control approach with gain coefficients optimized offline by an SBO method to deal with real-time decision-making problems under uncertainties.

Abstract The imbalance of rural parking supply and demand has a great impact on traffic congestion and environmental pollution, which has attracted the attention of many scholars as well as policymakers. However, most of the current research on parking choice focuses on urban business and residential areas rather than on rural parking choice behaviour, and focuses on the analysis of observable factors, ignoring the internal relationship with potential variables. This study considers the heterogeneity of individuals and uses the random forest (RF) algorithm to construct a model of rural residents’ willingness to choose parking with both latent and explicit variables, to explore how much and in what ways individual characteristics and parking characteristics affect rural residents’ parking choices, and to explore parking planning programmes and strategies that are truly applicable to rural areas. The results of the study suggest that the safety and convenience of the parking environment are key factors influencing the parking choice behaviour of rural residents, and can greatly improve the predictive accuracy of the parking willingness model. Upon comparison, it is found that the application of the RF algorithm is also significantly better than the logit model in terms of prediction effect, indicating that there is a nonlinear effect among the factors influencing the parking choice behaviour of rural residents and that the RF model with the addition of latent variables provides a better explanatory ability for the study of the parking choice behaviour of rural residents.

Abstract Techniques for predicting the trajectory of vulnerable road users are important to the development of perception systems for autonomous vehicles to avoid accidents. The most effective trajectory prediction methods, such as Social-LSTM, are often used to predict pedestrian trajectories in normal passage scenarios. However, they can produce unsatisfactory prediction results and data redundancy, as well as difficulties in predicting trajectories using pixel-based coordinate systems in collision avoidance systems. There is also a lack of validations using real vehicle-to-pedestrian collisions. To address these issues, some insightful approaches to improve the trajectory prediction scheme of Social-LSTM were proposed, such methods included transforming pedestrian trajectory coordinates and converting image coordinates to world coordinates. The YOLOv5 detection model was introduced to reduce target loss and improve prediction accuracy. The DeepSORT algorithm was employed to reduce the number of target transformations in the tracking model. Image Perspective Transformation (IPT) and Direct Linear Transformation (DLT) theories were combined to transform the coordinates to world coordinates, identifying the collision location where the accident could occur. The performance of the proposed method was validated by training tests using MS COCO (Microsoft Common Objects in Context) and ETH/UCY datasets. The results showed that the target detection accuracy was more than 90% and the prediction loss tends to decrease with increasing training steps, with the final loss value less than 1%. The reliability and effectiveness of the improved method were demonstrated by benchmarking system performance to two video recordings of real pedestrian accidents with different lighting conditions.

Abstract The imbalance between supply and demand in urban settings poses a significant barrier to the sustainable advancement of urban transportation. Shared parking serves as a viable solution to mitigate these challenges. Nevertheless, for its sustained growth, a regulatory mechanism enforced by the government is imperative. To promote shared parking market diffusion, we construct an evolutionary game model that incorporates the government, enterprises and parking demanders. It explores stabilization strategies for these stakeholders and identifies multiple equilibrium states under different parameter conditions. The results show that the rate and stability of these evolutionary strategies are constrained by the mutual benefits derived by the three parties. Furthermore, such stakeholders are reciprocally influenced by their willingness to engage in shared parking to varying degrees. Government subsidies serve as a determining factor for the strategic choices made by both enterprises and demanders, albeit at different evolutionary rates. Demanders who have a higher value of time tend to park on-street, thereby influencing enterprise strategies. To foster the long-term growth of the shared parking market, the government must enact appropriate subsidy policies, maintain consistent regulations and advocate for increased subsidies for parking demanders to reduce the effect of temporal heterogeneity on parking behavioural choices.

Abstract Estimation of the sample position is essential for working process monitoring and management in the life science automation laboratory. Bluetooth low-energy (BLE) beacons have the advantages of low price, small size and low energy consumption, which make them a promising solution for sample position estimation in the automated laboratory. Several fingerprinting models have been proposed to achieve indoor localization with the received signal strength (RSS) data. However, most of the research depends on intensive beacon installation. Proximity estimation, which depends entirely on one beacon, is more suitable for sample position estimation in large automated laboratories. The complexity of the life science automation laboratory environment brings challenges to the traditional path loss model (PLM), which is a widely used radio wave propagation model-based proximity estimation method. In this paper, BLE sensing devices for sample position estimation are proposed. The BLE beacon-based proximity estimation is discussed in the framework of machine learning, in which the support vector regression (SVR) is utilized to model the nonlinear relationship between the RSS data and distance, and the Kalman filter is utilized to decrease the RSS data deviation. The experimental results over different environments indicate that the SVR outperforms the PLM significantly, and provides 1 m absolute errors for more than 95% of the testing samples. The Kalman filter brings benefits to stable distance predictions. Apart from proximity-based sample position estimation, the proposed framework turned out to be effective in position estimation between parallel workbenches and position estimation on an automated workstation.

Abstract Bogie is a pivotal system and plays a critical part in the safety and reliability management of high speed rail. However, the available bogie system reliability analysis methods lack the consideration of multi-state characteristics, and the common multi-state reliability analysis methods, being an NP-hard problem, lead to a low efficiency. In order to overcome the mentioned drawbacks, this paper proposes a novel multi-state rail train bogie system reliability analysis approach based on the extended d-MC model. Three different function interactions within the bogie system are considered to build the multi-state bogie system flow network model. Meanwhile, an extended d-MC model is established to remove unnecessary d-MC candidates and duplicates, which greatly enhances the computing efficiency. The bogie system reliability is calculated, and the examples are provided. Numerical experiments are carried out for the different operational conditions of the bogie system and are used to testify the practicability of the method projected in this article, and is is found that the proposed method outperforms a newly developed method in solving the multi-state reliability problems.

Abstract An enhanced optimal velocity model (EOVM) that considers driving safety is established to alleviate traffic congestion and ensure driving safety. Time headway is introduced as a criterion for determining whether the car is safe. When the time headway is less than the minimum time headway (THmin ) or more than the most comfortable time headway (THcom), the acceleration constraints are discussed to ensure the model’s safety and maintain the following state. A stability analysis of the model was carried out to determine the stability conditions of the model. The EOVM is compared with the optimal velocity model (OVM) and fuzzy car-following model using the real dataset. Experiments show that the EOVM model has the smallest error in average, maximum and median with the real dataset. To confirm the model’s safety, design fleet simulation experiments were conducted for three actual scenarios of starting, stopping and uniform process.