Highway Vehicle Research Articles

A multi‐perspective fusion model for operating speed prediction on highways using knowledge‐enhanced graph neural networks

AbstractThis study proposes a multi‐perspective fusion model for operating speed prediction based on knowledge‐enhanced graph neural networks, named RoadGNN‐S. By utilizing message passing and multi‐head self‐attention mechanisms, RoadGNN‐S can effectively capture the coupling impacts of multi‐perspective alignment elements (i.e., two‐dimensional design, 2.5‐dimensional driving, and three‐dimensional spatial perspectives). The results of driving simulation data show that root mean squared error, mean absolute error, mean absolute percentage error, and R‐squared values of RoadGNN‐S are superior to those of other classic deep learning algorithms. Then, prior knowledge (i.e., highway geometry supply, driver expectations, and vehicle dynamics) is introduced into RoadGNN‐S, and the models’ prediction accuracy and transferability are verified by field observation experiments. Compared to the above data‐driven models, knowledge‐enhanced RoadGNN‐S effectively avoids the fundamental errors, improving the R‐squared value in predicting passenger cars’ and trucks’ operating speed by 7.9% and 10.7%, respectively. The findings of this study facilitate the intelligent highway geometric design with multi‐perspective fusion and knowledge enhancement techniques.

Multimodal adversarial informer for highway vehicle lane-changing trajectory prediction

To enhance the perception of vehicle trajectory information and lane-changing decision-making capabilities in intelligent connected vehicles during multivehicle interaction scenarios, we propose a novel method based on a Multimodal Adversarial Informer (MAI) for highway multivehicle lane-changingrajectory prediction. This method achieves spatiotemporal features of target and surrounding vehicles through graph learning of temporal features and spatial adjacency matrices. Considering the heading angle and vehicle local X-axis displacement, the vehicle trajectory samples are categorized for training and validation of the multimodal Informer. A multi-criterion discriminator is utilized to judge whether the generated trajectory fits the requirements of accuracy and rationality. After adversarial learning, the optimal vehicle lane-changing trajectory prediction is obtained using the proposed MAI. Experiments conducted with the NGSIM dataset demonstrate the comparative performance of baseline models on three different noise-added testing datasets using MAE, RMSE, and R² metrics. The MAI model consistently outperforms the others, achieving the lowest MAE and RMSE and the highest R² values across all datasets, indicating superior predictive accuracy and fit. Furthermore, the results show that the proposed MAI framework maintains a relatively low prediction error over both short-term and long-term horizons compared to baseline models.

Effects of wind barriers on the aerodynamic forces and driving safety of vehicles on a wide bridge girder at various angles of attack

This paper presents the effects of angles of attack (AOA) on the windproof effect of wind barriers and the driving safety of highway vehicles on a wide bridge girder. The aerodynamic force coefficients of the vehicles were obtained using the force measurement technique. Computational fluid dynamics simulations were employed to investigate the mean wind velocity field on the upper surface of the girder. A comparison was made between the aerodynamic forces on a vehicle at various AOA on a bridge deck with guardrails and a deck with wind barriers. The windproof effect of wind barriers at various AOA was accessed by the safety factor of a vehicle. The results showed that the maximum of the aerodynamic forces of vehicles was not typically observed at a 0° AOA. The windproof effect of wind barriers became more pronounced as the magnitude of the AOA increased. As AOA increases, the height of the low wind velocity zone above the deck shows an upward trend. Compared to the deck with the guardrails, the height of the low wind velocity zone was much higher in the presence of wind barriers. The increase in the height of the low wind velocity zone will result in a decrease in the aerodynamic side force and an increase in the rolling moment acting on vehicles. It is also noteworthy that the installation of wind barriers can cause a reduction of overturning and side-slip safety factors of vehicles at specific AOA. This suggests that the wind barrier may potentially compromise driving safety at specific AOA.

A POV-Based Highway Vehicle Trajectory Dataset and Prediction Architecture

A POV-Based Highway Vehicle Trajectory Dataset and Prediction Architecture

Fatigue damage assessment of a large rail-cum-road steel truss-arch bridge using structural health monitoring dynamic data

Structural health monitoring (SHM) system provides valuable information for the fatigue assessment of existing rail-cum-road bridges. This paper aims to develop an effective fatigue assessment approach for the rail-cum-road bridge, Jiujiang Yangtze River Bridge, by utilising the SHM data, focusing on dynamic modal analysis, finite element model updating and fatigue assessment. First, the traffic load spectrum and modal characteristics of the bridge are investigated from the SHM data. A three-dimensional finite element model is constructed and then updated by using the measured modal data through the proposed regularised model updating method. Then, the updated numerical model is verified with the measured dynamic response data, which can be utilised for calculating stress response at critical structural components of the rail-cum-road bridge. Finally, an improved Corten-Dolan’s model is proposed to analyse the fatigue damage and structural reliability of the critical structural components of the bridge, taking into account the combined effects of train and highway vehicle loads. The results demonstrate that the proposed fatigue assessment method provides more reliable results for the rail-cum-road bridge by considering the combined effect of multi-level traffic loads and the non-linear fatigue damage accumulation. It is concluded that the short H-shaped suspender is identified as the most vulnerable structural member of the rail-cum-road bridge, and the remaining fatigue service life of the typical components of the bridge should meet the design requirement.

Catastrophic uterine rupture of an unscarred uterus following motor vehicle rollover – a case report

A 22 year old female at 6 months gestation with no history of prior abdominal surgery or previous uterine procedures presented via air transport after highway motor vehicle rollover. Due to hemodynamic instability, the only preoperative imaging that was able to be obtained was bedside sonography, which confirmed free fluid in the upper quadrants and unfortunately, fetal demise. In the operating room, source of bleeding was noted to be multiple large uterine ruptures. Uterine rupture in trauma in the absence of prior uterine surgery is a rare event and has never been reported in the third trimester, however it should remain in the differential for a pregnant trauma patient presenting with hemodynamic instability.

Analysis of Highway Vehicle Lane Change Duration Based on Survival Model

To investigate highway vehicle lane-changing behavior, we utilized the publicly available naturalistic driving dataset, HighD, to extract the movement data of vehicles involved in lane changes and their proximate counterparts. We employed univariate and multivariate Cox proportional hazards models alongside random survival forest models to analyze the influence of various factors on lane change duration, assess their statistical significance, and compare the performance of multiple random survival forest models. Our findings indicate that several variables significantly impact lane change duration, including the standard deviation of lane-changing vehicles, lane-changing vehicle speed, distance to the following vehicle in the target lane, lane-changing vehicle length, and distance to the following vehicle in the current lane. Notably, the standard deviation and vehicle length act as protective factors, with increases in these variables correlating with longer lane change durations. Conversely, higher lane-changing vehicle speeds and shorter distances to following vehicles in both the current and target lanes are associated with shorter lane change durations, indicating their role as risk factors. Feature variable selection did not substantially improve the training performance of the random survival forest model based on our findings. However, validation set evaluation showed that careful feature variable selection can enhance model accuracy, leading to improved AUC values. These insights lay the groundwork for advancing research in predicting lane-changing behaviors, understanding lane-changing intentions, and developing pre-emptive safety measures against hazardous lane changes.

Optimal design of sizing and allocations for highway electric vehicle charging stations based on a PV system

The world’s demand for fossil fuels has recently increased significantly for both transportation and electric power generating sectors. Using these resources not only results in high costs and depletion of them but also increases greenhouse gas emissions and pollution. The electric vehicle (EV) market is growing globally, aiming to face climate change due to greenhouse gas (GHG) emissions and to reduce reliance on fossil fuels. However, the long charging time of EVs and the shortage of charging outlets limits the global adoption of EVs, especially on highways where the problem of accessibility to the electricity distribution grid appears. These issues can be faced by the good planning of charging infrastructure. However, this planning is a multidisciplinary field that includes electricity generation, transportation networks, EVs’ characteristics, and driver behavior. A methodology to provide the optimal locations and sizing of electric vehicle charging stations with their own electricity generation and storage using photovoltaic (PV) and energy storage systems on highways considering different factors is proposed in this paper. This paper takes a section of the western desert highway in Egypt connecting Assiut and Cairo cities as a case study. Four scenarios are proposed for the design of EV charging stations’ locations and sizing which are centralized charging stations, two-way charging stations, utilizing oil stations’ locations, and distributed fixed sizing charging points with a comparison between them. The work also discusses the potential effects of highway slope, wind speed, and number of passengers on the location problem. The results can be used to optimize the design of EV charging stations along highways for a completely sustainable system.

Over 25-year monitoring of the Tsing Ma suspension bridge in Hong Kong

AbstractBridges in service are subjected to environmental and load actions, but their status and conditions are typically unknown. Health monitoring systems have been installed on long-span bridges to monitor their loads and the associated responses in real time. Since 1997, the Tsing Ma suspension bridge in Hong Kong has been the world’s first of the type equipped with a long-term health monitoring system. For the first time, this study reports the first-hand field monitoring data of the bridge from 1997 to 2022. The 26-year data provide an invaluable and rare opportunity to examine the long-term characteristics of the loads, bridge responses, and their relationships, thereby enabling the assessment of the bridge’s load evolution and structural condition over time. Results show that traffic loads have remained stable after 2007, highway vehicles kept increasing until the COVID-19 pandemic in 2020, the annual maximum deck temperature continued to increase at a rate of 0.51 °C/decade, typhoon durations increased by 2.5 h/year, and monsoon speeds decreased and became dispersed and variable. For the bridge responses, deck displacement is governed by the varying temperature. Natural frequencies in the past 26 years were almost unchanged. The overall condition of the bridge is very satisfactory. Current status and recent update of the health monitoring system are also reported. Lastly, prospects of bridge health monitoring are discussed. This study is the first to report the over one-quarter century status of a structural health monitoring system and the behavior of a long-span suspension bridge. This research provides a benchmark for many other bridge monitoring systems worldwide.

Sizing Methodology of Dynamic Wireless Charging Infrastructures for Electric Vehicles in Highways: An Italian Case Study

The necessity of pushing the road mobility towards more sustainable solutions has become of undeniable importance in last years. For this reason, both research and industry are constantly investigating new technologies able to make the usage of battery electric vehicles(BEV) as accessible and usable as traditional internal combustion engine vehicles (ICEV). One of the most limiting issues concerns the short range of electric vehicles, which complicates their use for long distances, such as for highway travels. A promising solution seems to be the “charge-while-driving” approach, by exploiting the inductive dynamic wireless power transfer (DWPT) technology. Nevertheless, such systems show different issues, first of all, high investment and maintenance costs. Furthermore, it is not clear how extensive a potential dynamic wireless charging infrastructure needs to be to make a real advantage for electric vehicle drivers. As a consequence, the aim of this paper is to introduce a new methodology to estimate the number and length of wireless charging sections necessary to allow the maximum number of electric vehicles to travel a specific highway without the need to stop for a recharge at a service area. Specifically, the methodology is based on a algorithm that, starting by real traffic data, simulates vehicle flows and defines the basic layout of the wireless charging infrastructure. This simulator can provide a decision support tool for highway road operators.

Variable Area Jet Impingement for Enhanced Junction Temperature Control of High-Power Electronics

Abstract Convective heat transfer by jet impingement cooling offers a suitable solution for high heat flux applications. Compared to techniques that rely on bulk conduction in series with convection, direct liquid impingement reduces the thermal resistance between power device hot spots and the coolant. Although capable of highly efficient cooling, static impingement devices must be designed for the worst-case cooling requirements for a transient power profile. This can result in wasted hydraulic performance. Aircraft, highway vehicles, and heavy machinery fall into this category where a substantial factor of safety is required. This work proposes a method for improving power electronics reliability by limiting temperature fluctuations at reduced coolant pressure requirements during transient power cycling using a variable area jet. Single phase jet impingement cooling is implemented in an active control scheme using a variable diameter iris mechanism as the primary nozzle architecture. In addition to pressure drop and temperature control, the active nozzle structure introduces the ability to create pulsating jet flows to further enhance the heat transfer compared to fixed-geometry nozzles. The key underlying fluid mechanics characteristic of pulsating flows is the effect of disrupting the thermal boundary layer on the electrical device surface. By introducing a variable diameter jet, eddy formation can be fine-tuned for optimal boundary layer disruption. Using the definition of the Strouhal number, vortex shedding created by the non-steady jet flows is directly correlated with the resulting Nusselt number as a function of the iris kinematics. An experimental apparatus for jet impingement thermal-fluid testing is used to evaluate the Nusselt number versus Strouhal number for a parametric study of variable diameter iris configurations. The apparatus utilizes a voice coil actuator to achieve sine and square waveforms, to vary the amplitude of actuation, and to vary the mean of actuation. Finally, power cycling with a single emulated hot spot is performed to estimate the reliability increase as a result of maintaining constant junction temperatures with the active jet impingement scheme.

Highway vehicle detection based on distributed acoustic sensing.

Distributed acoustic sensing systems can obtain the road vibration information caused by vehicle driving vibration on highways. By characterizing the vehicle driving vibration data, a distributed acoustic sensing system based highway vehicle driving vibration detection scheme is proposed. Firstly, the out-of-bag error criterion of random forest is used to select multiple features of the vibration signals to obtain the most suitable feature quantity to characterize the road vibration signals, then the root mean square value of the signal matched filtering is calculated and compared, and the threshold is used to distinguish between the vehicle vibration signals and the noise. Finally, the improved trajectory start algorithm is used to accurately detect the vehicles travelling on the highway to obtain the real-time information of the vehicles. The experiment verified that the method can effectively detect highway vehicles.

VegaEdge: Edge AI confluence for real-time IoT-applications in highway safety

Traditional highway safety and monitoring solutions, reliant on surveillance cameras, face limitations due to their dependence on high-speed internet connectivity and the remote processing of Artificial Intelligence (AI) algorithms. This reliance introduces latency, undermining the real-time detection and analysis crucial for highway applications. The fusion of AI with the Internet of Things (IoT) opens new avenues for highway safety and surveillance innovation. Yet, most existing solutions are confined to vehicle detection and tracking, hindered by edge-IoT platforms’ limited power and processing capabilities. Addressing these limitations, this paper presents VegaEdge, an AI framework optimized for edge-IoT devices capable of real-time vehicle detection and tracking, trajectory forecasting, and identifying anomalous driving behaviors, such as road departures, sudden stops, and hazardous merges. A novel lightweight anomaly detection algorithm based on trajectory prediction is used for identifying hazardous driving on highways. VegaEdge demonstrates its versatility and efficiency across various traffic conditions and roadway configurations and has been evaluated on platforms like the Nvidia Jetson Orin and Xavier NX. The Nvidia Jetson Orin processes up to 738 trajectories per second and detects up to 140 vehicles in a single frame. Additionally, the Carolinas Anomaly Dataset (CAD) an extension of the Carolinas Highway Dataset (CHD) is introduced. While CHD consists of standard highway vehicle videos and trajectories, CAD includes video data of anomalous driving behaviors, providing a crucial resource for enhancing anomaly detection algorithms. CAD is available at https://github.com/TeCSAR-UNCC/Carolinas_Dataset#chd-anomaly-test-set.

Study of Tunnel Vehicle GNSS/INS/OD Combination Position Based on Lateral Distance Measurement and Lane Line Constraint

The high-precision dynamic positioning of highway vehicles is the foundation and prerequisite for achieving intelligent connected transportation. To address the shortcomings of the GNSS/INS combination and GNSS/INS/OD combination in tunnel vehicle positioning, this paper proposes a tunnel vehicle positioning method for the GNSS/INS/OD combination based on lateral distance measurements and lane constraints. Firstly, a lateral distance measurement of vehicles inside the tunnel is conducted based on laser radar point cloud data. Secondly, map matching positioning is performed based on lateral distance measurements, odometer, and lane markings. Experimental results demonstrate that, for a 4.6 km tunnel, the average absolute error in the lateral positioning is 0.294 m, and the longitudinal positioning error is no more than 0.6 m, which can effectively meet practical operational requirements.

Traffic flow prediction for highway vehicle detectors through decomposition and machine learning

ABSTRACT Traffic flow prediction is of significant importance in traffic planning. Currently, traffic flow data are primarily collected through loop detectors. However, factors such as road conditions can affect the accuracy of these data. To address this issue, this paper proposes a traffic flow prediction method based on decomposition and machine learning. The improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) method decomposes the sequence into multiple intrinsic mode functions (IMFs). The complexity of each IMF is calculated using the sample entropy (SE), and then the IMFs are reconstructed. Parameters of the variational mode decomposition (VMD) are optimized using the whale optimization algorithm (WOA) for the secondary decomposition, and predictions are made using gated recurrent units (GRU). Finally, the prediction results are reconstructed to obtain the final prediction values. In the case study section, experiments are conducted using datasets from three detectors to explore different decomposition forms and methods.

A freeway vehicle early warning method based on risk map: Enhancing traffic safety through global perspective characterization of driving risk

In the era of rapid advancements in intelligent transportation, utilizing vehicle operating data to evaluate the risk of freeway vehicles and study on vehicle early warning methods not only lays a theoretical foundation for improving the active safety of vehicles, but also provides the technical support for reducing accident rate. This paper proposes a freeway vehicle early warning method based on risk map to enhance vehicle safety. Firstly, Modified Time-to-Collision (MTTC), a two-dimensional indicator that describes the risk of inter-vehicle travel, is used as an indicator of road traffic risk. This paper designs a transformation function to probabilistically transform MTTC into Risk Indicators (RI). The single-vehicle risk map is generated based on the mapping relationship between the risk values and the corresponding roadway segments. These single-vehicle risk maps of all vehicles on the road are superimposed to construct the risk map, which is used to describe the risk distribution in the freeway. Then, a vehicle early warning framework is built based on the risk map. The risk values in the risk map are compared with predefined early warning thresholds to alert the vehicle when it enters a high-risk state. Finally, VISSIM is used to carry out simulation experiments. The experiment simulates a freeway accident stopping situation. This scenario includes sub-scenarios such as unplanned stopping and lane-changing, continuous lane-changing, and adjacent lane overtaking. We analyze the risk map and vehicle warning results in different sub-scenarios, evaluate the risk changes of the vehicles before and after receiving the warning, and compare the warning results of the method in this paper with other alternative methods. The method is applied to 17 vehicles in the simulation to adjust their motion states. The results show that the total warning time is reduced by 29.6% and 73.3% of vehicles change lanes away from the accident vehicle. The overall results validate the effectiveness of the vehicle early warning method based on risk map proposed in this paper.

Optical fiber sensing and tensor AP clustering for high-speed road tunnel vehicle detection

Aiming at the problems of signal acquisition, feature extraction and vehicle recognition in highway tunnel vehicle detection, a new tunnel vehicle detection method is proposed by combining optical time-domain reflectometry distributed fiber sensing technology and tensor affine propagation clustering algorithm. Firstly, the distributed optical fiber system designed by optical time domain reflectometry was used to collect the running signals of tunnel vehicles and obtain the measurement data. Secondly, a high-order tensor sample set is constructed by using the spatial resolution of optical fiber as channel number and combining the feature number, time domain and frequency domain. Finally, tensor affine propagation clustering method and other clustering methods are used to test the accuracy. The test results show that the proposed method can better classify vehicles without destroying the original high-dimensional data structure. Meanwhile, the unsupervised clustering algorithm also reduces manual intervention in the identification process, increases the intelligence level of the whole vehicle detection model, and effectively improves the detection accuracy rate of tunnel vehicles.

Enhanced YOLOv5s + DeepSORT method for highway vehicle speed detection and multi-sensor verification

Addressing the need for vehicle speed measurement in traffic surveillance, this study introduces an enhanced scheme combining YOLOv5s detection with Deep SORT tracking. Tailored to the characteristics of highway traffic and vehicle features, the dataset data augmentation process was initially optimized. To improve the detector’s recognition capabilities, the Swin Transformer Block module was incorporated, enhancing the model’s ability to capture local regions of interest. CIoU loss was employed as the loss function for the vehicle detection network, accelerating model convergence and achieving higher regression accuracy. The Mish activation function was utilized to reduce computational overhead and enhance convergence speed. The structure of the Deep SORT appearance feature extraction network was modified, and it was retrained on a vehicle re-identification dataset to mitigate identity switches due to obstructions. Subsequently, using known references in the image such as lane markers and contour labels, the transformation from image pixel coordinates to actual coordinates was accomplished. Finally, vehicle speed was measured by computing the average of instantaneous speeds across multiple frames. Through radar and video Multi-Sensor Verification, the experimental results show that the mean Average Precision (mAP) for target detection consistently exceeds 90%. The effective measurement distance for speed measurement is around 140 m, with the absolute speed error generally within 1–8 km/h, meeting the accuracy requirements for speed measurement. The proposed model is reliable and fully applicable to highway scenarios.

Modeling and Comparing the Total Cost of Ownership of Passenger Automobiles with Conventional, Electric, and Hybrid Powertrains

<div>The global automotive industry’s shift toward electrification hinges on battery electric vehicles (BEV) having a reduced total cost of ownership compared to traditional vehicles. Although BEVs exhibit lower operational costs than internal combustion engine (ICE) vehicles, their initial acquisition expense is higher due to expensive battery packs. This study evaluates total ownership costs for four vehicle types: traditional ICE-based car, BEV, split-power hybrid, and plug-in hybrid. Unlike previous analyses comparing production vehicles, this study employs a hypothetical sedan with different powertrains for a more equitable assessment. The study uses a drive-cycle model grounded in fundamental vehicle dynamics to determine the fuel and electricity consumption for each vehicle in highway and urban conditions. These figures serve a Monte Carlo simulation, projecting a vehicle’s operating cost over a decade based on average daily distance and highway driving percentage. Results show plug-in hybrids generally offer the most economical choice. Due to the BEVs’ heavier weight and battery cost, they only become more cost-effective than plug-in hybrids after 160 km daily travel, associated with only a small percentage of drivers in the United States. Nevertheless, they remain cheaper than conventional vehicles for most distances. The study also investigates the effects of government subsidies, battery cost, and weight on overall expenses for each powertrain. It concludes that opting for less expensive, albeit heavier batteries would generally reduce EV ownership costs for consumers.</div>

Retracted: Anomaly Detection of Highway Vehicle Trajectory under the Internet of Things Converged with 5G Technology

Retracted: Anomaly Detection of Highway Vehicle Trajectory under the Internet of Things Converged with 5G Technology