Image-based intelligent detection of road cracks with high accuracy and efficiency is vital to the overall condition assessment of the pavement. However, significant problems of continuous cracks interruption and background discrete noise misidentification are frequently observed in current semantic segmentation of pavement cracks, which mainly caused by traditional segmentation convolutional neural networks. This paper proposes a skip-level round-trip sampling block structure with the implementation of convolutional neural networks, thereby constructed a novel pixel level semantic segmentation network called CrackW-Net. After that, two datasets, including the widely recognized Crack500 dataset and a self-built dataset, were used to train two versions CrackW-Net, FCN, U-Net and ResU-Net. Meanwhile, comparative experiments are conducted among all these network models for crack detection. Results show that CrackW-Net without residual block performs the best in the task of pavement crack segmentation.

This study focused on the property characterization of asphalt and asphalt mixtures modified by different types of crumb rubber (normal and desulfurized). This characterization was based on chemical evaluation and property testing for rubber asphalt and on performance analysis for different rubber asphalt mixtures. Chemical fraction and gel permeation chromatography tests were used to identify rubber asphalt’s microstructures; conventional and Superpave property tests were performed to evaluate its macroproperties; and an isolation test was used to judge its storage stability. Also conducted were wheel loading tests, three-point beam bending tests, and Marshall tests along with splitting tests and four-point beam bending tests to evaluate rutting stability, thermal cracking resistance, water damage susceptibility, and fatigue cracking resistance in different rubber asphalt mixtures. The findings indicate that both normal and desulfurized crumb rubber have obvious positive impacts on the properties of neat asphalt and asphalt-rubber mixtures. Compared with normal crumb rubber asphalt (NCRA), desulfurized crumb rubber asphalt (DCRA) shows lower viscosity and better storage stability. Both the normal crumb rubber asphalt mixture (NCRAM) and the desulfurized crumb rubber asphalt mixture (DCRAM) exhibit good properties. However, whereas NCRAM production uses gap gradation along with greater asphalt content and higher production temperatures, DCRAM production uses dense gradation with less asphalt content and lower production temperatures, making it more similar to the Styrene-Butadiene-Styrene (SBS) modified asphalt mixture.

This study investigated the simulation of wheel tracking test and the high-temperature rutting behaviour of an asphalt mixture by using the discrete element method (DEM). Based on the DEM software named as Particle Flow Code in three dimensions (PFC3D), a micromechanical model of an asphalt mixture composed of coarse aggregates, asphalt mastic, and air voids was built and a two-dimensional virtual wheel tracking test was simulated. Based on the virtual wheel tracking test, the distribution of displacement and contact forces within test specimen were analysed. It is proved that the built virtual wheel tracking test can capture the rutting deformation caused by the combination of densification and lateral flow deformation. It is also indicated that, within an asphalt mixture, the aggregate skeleton is the main bearing body for the compressive forces, while the compressive and tensile forces between aggregate and mastic are severer than that within asphalt mastic. It is important to guarantee the stability of the aggregate skeleton and the bonding strength between aggregate and asphalt mastic to resist rutting deformation.

This paper investigated the modification mechanism of the desulfurized rubber asphalt, and compared its performances with those of crumb rubber asphalt. The microstructures of desulfurized rubber asphalt and crumb rubber asphalt were identified by using the scanning electron microscope technology, component analysis and infrared spectrum analysis. Conventional and Strategic Highway Research Program (SHRP) performance tests were conducted to evaluate the performances of desulfurized rubber asphalt and crumb rubber asphalt. Mixture performance tests were also performed to characterize the high temperature rutting resistance, low temperature cracking resistance, moisture stability and fatigue life of the desulfurized rubber asphalt mixture and crumb rubber asphalt mixture. It was found that the modification mechanisms of desulfurized rubber asphalt and crumb rubber asphalt are different. The desulfurized rubber can integrate into the asphalt while the crumb rubber mainly exists incompatibly in asphalt. This difference results in the various performances between the desulfurized rubber asphalt and crumb rubber asphalt. Both crumb rubber and desulfurized rubber can improve the performance of asphalt binder and mixture, but the desulfurized rubber asphalt has much lower viscosity and better storage stability than the crumb rubber asphalt. The preparing temperature of the desulfurized rubber asphalt mixture can be reduced by 10∼20°C compared to the crumb rubber asphalt mixture. Moreover, without the interference of solid rubber particles, the desulfurized rubber asphalt can be used in dense-graded asphalt mixture while crumb rubber asphalt mixture tends to use gap gradation with high asphalt content.

The routine maintenance and rehabilitation of road pavement is vital to keep up with the service level and bearing capacity. However, the current problem is that, with the continuous increase of the scale of maintenance data, the traditional decision-making cannot satisfy the requirements in terms of accuracy and efficiency. The objectives of this paper were to improve the accuracy and efficiency of the maintenance decisions, overcome the decision error caused by insufficient human experience, and develop the mapping process for decision plans. This paper presented a decision-making method for asphalt pavement maintenance using improved weight random forest algorithm (IWRF) based on the correlation analysis (CA) and the analytic hierarchy process (AHP). Firstly, appropriate features were selected through CA of road detection data, and then decision trees were constructed based on Bootstrapping. Finally, qualified decision trees were chosen and weighted by AHP to form a random forest. To examine the feasibility, the algorithm was applied in a maintenance decision of the 80 km highway in Jiangsu province. The results showed that IWRF had a decision-making accuracy of up to 90%. Comparing with the traditional random forest algorithm, the IWRF algorithm had a 4.35% higher accuracy and saved 75% computation time.

Daily road maintenance is essential to road safety and serviceability, particularly to highways. In daily road maintenance inspection tasks, the objectives include a variety of targets, such as pavement cracks, foreign objects, guardrail damages etc. There is a lack of rapid detection methods that allow for the uniform identification of multiple targets for road maintenance. This paper proposes an automatic multi-object detection method for road daily maintenance inspection assisted by unmanned aerial vehicles ( UAV). A dataset of multiple roadway anomalies ( UAVROAD) for daily road maintenance needs was constructed. UM-YOLO, an improved algorithm based on the YOLOv8n algorithm was created to better extract the features of multiple targets, as well as fuse features and reduce computation while maintaining accuracy. The improvements include adding EMA (Efficient multiscale Attention Module) in the C2f module in the backbone, employing Bi-FPN fusion mechanism in the neck and using GSConv, a lightweight convolutional network, for the convolution operation. Compared with the YOLOv8n, the proposed UM-YOLO improved mean average precision(mAP) by 4.6% and reduced the model computation by 14%.