Fiberglass prepared from broken waste glass can be used in epoxy asphalt mixtures for performance enhancement and a toughening effect. There is no systematic study on the influence mechanism of the size and the amount of glass fiber on the properties of epoxy asphalt mixtures. The effects of fiberglass on the properties of epoxy asphalt concrete were evaluated using a tensile test, three-point bending test, four-point bending fatigue test and an SEM scanning test. The results verify that the tensile strength of epoxy asphalt mastic with a 6 mm length and 2% content increased the most. Compared with the nondoped glass fiber, it increased by 69.2%. Under the influence of the internal composition of the asphalt mixture, the optimal ratio scheme is different from that of epoxy asphalt mastic. A microscopic analysis showed that uniformly dispersed fiberglass in the epoxy asphalt mixture forms a spatial network structure, leading to reinforcement and the restraint of microcrack expansion. The addition of fiberglass with a length of 9 mm and at a concentration of 5% to the epoxy asphalt mixture resulted in the maximum road performance. The Marshall stability increased by 43.5%, and the flexural and tensile strength increased by 33.7%. The fiberglass length is the most important factor limiting the strength and toughening effects of epoxy asphalt mixtures.

Internal disease in asphalt pavement is a crucial indicator of pavement health and serves as a vital basis for maintenance and rehabilitation decisions. It is closely related to the optimization and allocation of funds by highway maintenance management departments. Accurate and rapid identification of internal pavement diseases is essential for improving overall pavement quality. This study aimed to identify internal pavement diseases using deep learning algorithms, thereby improving the efficiency of determining internal pavement diseases. In this work, a multi-view recognition algorithm model based on deep learning is proposed, with attention fusion mechanisms embedded both between channels and between views. By comparing and analyzing the training and recognition results of different neural networks, it was found that the multi-view recognition algorithm model based on attention fusion demonstrates the best performance in identifying internal pavement diseases.

The long-term performance trends of asphalt pavements are pivotal to the concerns of road maintenance authorities. However, predicting the longevity of asphalt pavement performance accurately is a complex challenge due to the multitude of factors influencing its deterioration. This paper constructs a predictive model for long-term behavior of asphalt pavements grounded in the mechanistic-empirical methodology. An extensive observation was conducted on highways, where data on the pavement condition index and the road quality index were meticulously gathered. Subsequently, the model’s life factor and shape factor parameters were corrected. The findings indicate that the predictive methodology derived from mechanistic-empirical methodology for asphalt pavement performance exhibits commendable accuracy and good generalization capabilities

Asphalt pavement distress detection plays a pivotal role in highway maintenance, providing an essential basis for optimizing maintenance strategies and allocating funding. Consequently, quick detection and efficient identification of distress are crucial for enhancing the quality of highway maintenance. This study aims to acquire high-precision distress data using 3D laser point cloud technology, identify distress types via the YOLO algorithm, and extract geometric features such as length and angle. Specifically, a recognition method based on 3D laser point cloud images is proposed, where point cloud data are converted into planar images for processing. Experimental results indicate that the laser point cloud detection achieves millimeter-level precision, the distress recall rate exceeds 85%, and the identification precision reaches 79.5%, demonstrating satisfactory detection accuracy and efficiency.