Journal of Traffic and Transportation Engineering-English Edition最新文献

Deep learning has received a growing interest in recent years for detecting different types of pavement distresses and automating pavement condition assessment. A proper choice of deep learning models is key for successful pavement assessment applications. In this study, we first present a comprehensive experimental comparison of state-of-the-art image classification models to evaluate their performances on 11 pavement objects classification. Our experiments are conducted in different dimensions of comparison, including deep classifier architecture, effects of network depth, and computational costs. Five convolutional neural network (CNN) classifiers widely used in transportation applications, including VGG16, VGG19, ResNet50, DenseNet121, and a generic CNN (as the control model), are tested with a comprehensive pixel-level annotated dataset for 11 different distress and non-distress classes (UCF-PAVE 2017). In addition, we investigate a simple yet effective approach of encoding contextual information with multi-scale input tiles to classify highly random pavement objects in size, shape, intensity, texture, and direction. Our comparison results show that the multi-scale approach significantly improves the classification accuracy for all compared deep classifiers at a negligible extra computational cost. Finally, we provide recommendations of how to improve the classification performance of deep CNNs for automated pavement condition assessment based on the comparison results.

This work investigated the aging effects on the rheological properties of high viscosity modified asphalt (HVMA). First, the high- and low-temperature rheological properties were measured by a dynamic shear rheometer and a bending beam rheometer, respectively. The aging mechanism was then tested using an Fourier transform infrared spectroscopy and a scanning electron microscope. Besides, a study was performed to compare the aging effects on the rheological properties of HVMA, crumb rubber modified asphalt (CRMA), and neat asphalt (SK-90). The experimental results showed that the effects of the long-term aging on HVMA exceeded those of short-term aging. The complex shear modulus of the HVMA was improved by the aging in the whole frequency range. The complex shear modulus of the HVMA after the long-term aging was larger than after the short-term aging. Thus, the aging improved the high-temperature viscoelastic performance of HVMA. With a decrease in temperature from −12 °C to −24 °C, the low-temperature viscoelastic performance of HVMA decreased since its stiffness modulus and low continuous grading temperature increase. Both of the short- and long-term aging of HVMA were caused by an oxidation reaction, while modifier swelling also happened after long-term aging. Compared to CRMA and SK-90, aging had a limited influence on the high- and low-temperature rheological properties of HVMA.

The road is one of the most important civil infrastructures for serving society, where its service quality and life have direct impacts on the safety and comfort of users. Therefore, road construction, condition detection and monitoring, and timely maintenance are particularly important for engineers. Many engineering applications of industrial informatics approaches, like image processing technology, widely used computer-based algorithms, and advanced sensors, have been initially and gradually applied to roads. This state-of-the-art review first summarized the research on industrial applications of advanced information technologies in recent years, while analyzing and comparing the advantages and disadvantages of each technology. Especially, five topics were focused on road construction, road maintenance with decision strategy, road structure evaluation, smart sensing in the road, and cooperative vehicle infrastructure system. It is expected that advanced industrial informatics can help engineers promote the development of smart, safe, and sustainable roads.

High early strength (HES) concrete pavements are commonly opened to traffic within the first 24 h after construction, making early-opening decisions critical for pavement quality and traffic operations. Currently, most state departments of transportation rely on compressive strength testing for early-opening decision making. However, there laboratory tests are labor intensive, costly and not always representative of field strength development. In this study, non-destructive testing (maturity and ultrasonic tomography) was explored for faster and reliable in-situ strength estimations. An experimental section constructed using HES concrete was routinely monitored using compressive testing, maturity, and ultrasonic tomography in the first 24 h after construction. The shear wave velocity, measured using ultrasonic tomography, was able to capture the strength-gain variability within a single slab and between different slabs due to the ability to monitor several locations in a short period of time. Maturity results were consistently conservative in the first 24 h of monitoring. Results show that both maturity testing and ultrasonic tomography are able to replace or add to conventional strength testing for HES concrete pavements to facilitate making the opening decision within the first 24 h. Ultrasonic tomography proved more beneficial as a result of the device's portability, increased speed of testing, and accurate estimations of HES concrete strength for the entire pavement length.

The properties of asphalt binder play an essential role in the design life of asphalt pavement. Analysis of asphalt mechanical behaviors based on the chemical structures provides the theoretical basis for the improvement of asphalt performance in service life. Intermolecular interactions have a significant impact on the macroscopic properties of asphalt, a colloidal material, resulting in the parameters characterizing asphalt molecular structures fail to directly connect with mechanical properties of asphalt. This paper introduces the supramolecular theory, presents a brief review of existing supramolecular models and research methods of asphalt, aiming to explore a new methodology for the investigation between asphalt microstructures and macroscopic properties. Results showed the supramolecular theory focuses on the intermolecular interactions, providing more accurate indicators for the investigation on the asphalt supramolecules. Supramolecular analysis of asphalt has proposed feasible methods and established favorable connections with asphalt properties, giving a new view of understanding asphalt microstructure and a new approach to capture mechanical behaviors of asphalt.

To achieve automatic, fast, efficient and high-precision pavement distress classification and detection, road surface distress image classification and detection models based on deep learning are trained. First, a pavement distress image dataset is built, including 9017 pictures with distress, and 9620 pictures without distress. These pictures were captured from 4 asphalt highways of 3 provinces in China. In each pavement distress image, there exists one or more types of distress, including alligator crack, longitudinal crack, block crack, transverse crack, pothole and patch. The distresses are labeled by a rectangle bounding box on the pictures. Then ResNet networks and VGG networks are used respectively as binary classification models for distressed and non-distressed imagines classification, and as multi-label classification models for six types of distress classification. Training techniques, such as data augmentation, batch normalization, dropout, momentum, weight decay, transfer learning, and discriminative learning rate are used in training the model. Among the 4 CNNs considered in this study, namely ResNet 34 and 50, and VGG 16 and 19, for the binary classification, ResNet 50 has the highest Accuracy of 96.243%, Precision of 95.183%, and ResNet 34 has the highest Recall of 97.824%, and F2 score of 97.052%. For multi-label classification, ResNet 50 has the best performance, with the highest Accuracy of 90.257%, higher than 90% required by the Chinese standard (JTG H20-2018) for road distresses detection, F2 score −82.231%, and Precision −76.509%, and ResNet 34 has the highest Recall of 87.32%. To locate and quantify the distress areas in the images, the single shot multibox detector (SSD) model is developed, in which the ResNet 50 is used as the base network to extract features. When the intersection over union (IoU) is set to 0, 0.25, 0.50, 0.75, the mean average precision (mAP) of the model are found to be 74.881%, 50.511%, 28.432%, 3.969%, respectively.

An extensive experimental-mechanistic study was conducted to reveal the relationship between the light weight deflectometer (LWD) measured deflections and the degree of compaction of pavement base materials. Both laboratory experiments and test pits experiments were performed with different types of pavement base materials. The modulus based maximum allowable LWD deflections under different structural and compaction conditions were developed for the most commonly used pavement base aggregate in Indiana. The maximum allowable deflections are based on the equivalent subgrade modulus and the thickness of the layer to be compacted. It is emphasized that the LWD deflections must be measured as soon as the material is compacted or before the moisture content decreases beyond a specified range. Therefore, the maximum allowable deflections are specified in terms of the difference between the actual moisture content and the optimum moisture content. The maximum allowable deflection values provide a sound basis for compaction quality control using LWD devices.

Roadways in Wyoming are characterized by challenging horizontal profiles, vertical profiles, a combination of the two and adverse weather conditions, all of which affect vehicle stability. In this study, we investigated the impact of different operating speeds when negotiating combined horizontal and vertical curves under unfavorable environmental conditions on Wyoming's interstates via vehicle dynamics simulation software. The simulation tools provided the acting forces on each tire of the vehicle and the side friction (skidding) margins. This allowed for examining the interaction between vehicle dynamics and road geometry in such alignments. Also, linear regression analysis was implemented to investigate the skidding margins based on the simulation results to demonstrate when a vehicle is more likely to deviate from its desired trajectory. Specifically, this examines the contributing factors that significantly influence the skidding margins. The results indicated that: 1)the skidding margins are dramatically decreased by adverse weather conditions even with lower degree of curvature and gradient values of combined curves and more particularly at higher operating speeds conditions. Increasing the vehicle speed on the curve by 10%, the skidding margin dropped by 15%. 2) Compared to heavy trucks and sports utility vehicles (SUVs), passenger cars require the highest side friction demand. 3) The effect of applying brakes on vehicle stability depends on the road surface condition; applying the brakes on snowy road surfaces increases the potential of vehicle skidding especially for heavy trucks. This study assessed the curve speed limits and showed how important to assign safe and appropriate limits speed since the skidding likelihood is significantly sensitive to the vehicle speeds. This study is beneficial to Wyoming's roadway agencies since hazardous sections having combined horizontal and vertical curves are identified. Also, critical situations that require additional attention from law enforcement agencies are pinpointed. Finally, recommendations that are valuable to roadway agencies are made based on this study's findings.

Background

The deterrence effect of automated speed camera (ASC) is still inconclusive. Moreover, it is pointed out that ASC may have varying deterrence effects on different types of road users (e.g., taxis).

Objective

This study intends to investigate the distance halo effect of fixed ASC (hereafter called ASC) on taxis.

Method

More than 1.34 million taxis' GPS trajectory data were collected. A novel indicator, the delta speed (defined as the difference between the traveling speed and the speed limit), was proposed to continuously describe the variations in traveling speeds. The upstream and downstream critical delta speeds during each time period on weekdays and weekends were obtained by using K-means clustering method, respectively. Based on the critical delta speeds, the ranges of upstream and downstream distance halo effects of ASC during different time periods on weekdays and weekends were determined separately and compared.

Results

The downstream critical delta speed is smaller than the upstream one. The upstream and downstream distance halo effects of ASC on taxis are within a range of 8–2180 m and an area of 10–580 m to the ASC location, respectively. There are no obvious difference in the ranges of upstream and downstream distance halo effects of ASC on taxis between different time periods or between weekdays and weekends.

Conclusion

The present study confirms that the upstream and downstream distance halo effects of ASC on taxis have different ranges and the stabilities of time-of-day and day-of-week. Practical application: The findings of this study can provide a basic reference for reasonably deploying ASCs within a region.

Train dynamics and component fatigue assessments are important steps towards successful operations of long heavy haul trains. Longitudinal train dynamics (LTD) simulation is an effective and efficient approach in this regard. Draft gear friction has been known to have a strong stochastic feature. However, relevant train dynamics simulations have not been reported in open literature. This paper uses experimental data to extract the stochastic feature of draft gear friction. The stochastic feature is then introduced into LTD simulations. Coupler force and fatigue damage assessments were conducted by simulating a heavy haul train that has 244 vehicles and weighs nearly 30,000 tonnes. The results show that average in-train force variations due to stochastic friction were 55 and 40 kN for the traction and air brake cases respectively; maximum force variations were 207 and 98 kN for the traction and air brake cases respectively. Coupler fatigue calculations are even more sensitive to stochastic draft gear friction; the largest variations can be up to 700 times different due to the strong nonlinearity of fatigue calculation procedures. Stochastic friction is an unavoidable nature in friction draft gears. Simulations using stochastic draft gear friction can deliver results that are more robust and reliable.