Detecting buried objects using ground-penetrating radar (GPR) profiles typically requires manual interaction and considerable time. To resolve this problem, first, this research used gprMax to model the void defect more realistically and study its GPR image features. The team employed 3D radar to collect 2400 data points of voids from the test road and expressway and used data augmentation to augment the data. Then, convolutional neural network (CNN) algorithms such as Faster R-CNN, RetinaNet, YOLOv3, and YOLOv5, are improved based on the Swin Transformer. In this study, the Swin_YOLOv5 model performed the best with an F1 score of 98.5%, a recall rate of 98.4%, and a precision of 98.7%, and correctly recognized voids while the other three models had false positives (FP). Finally, this research group used a combination of Multiple Screen Shots(MSS) and Swin_YOLOv5_to recognise asphalt pavement voids in real time and achieved an accuracy rate of 89.5% in a field survey to achieve the purpose of real-time detection and identification of voids by GPR.

Polyurethane grouting materials, a type of expansible grout, has played a significant role in the rehabilitation of public infrastructures, such as lifting the slab in a road and reinforcing the broken wall rocks in a tunnel. Due to the unique expansion characteristic of polyurethane materials induced by the chemical reaction, its diffusion mechanism in rock fracture is rather complicated. Based on a numerical method presented in a previous paper, the diffusion law of expansible grout in a single fracture is studied considering the time-varying density and viscosity of the grout tested by experiments. The grout diffusion radius, pressure distribution and velocity field are calculated by the numerical model combining the finite volume method (FVM) and volume-of-fluid (VOF) method. Taking the gel time into account, the characteristics of flow field distribution during the grout movement process are investigated on five different cases and the influences of grouting quantity and fracture aperture on grout diffusion behavior are analyzed, which can reveal some diffusion law of expansible grout in a single water-free fracture.

Polyurethane grouting material (polymer) has been widely used in rock mass fracture grouting. The previous test of polymer slurry grouting in planar fracture did not consider the influence of temperature; therefore, in this paper, a test of polymer slurry grouting in planar fracture was firstly conducted in order to explore the diffusion characteristics of polymer slurry. The results show that the preheating temperature of polymer slurry has a great influence on the diffusion of slurry in fractures, which should be considered in the research of polymer fracture grouting. In addition, the slurry temperature is related to the chemical reaction of the polymer itself. However, the existing polymer fracture grouting models ignore the influence of temperature and the chemical reaction of the polymer slurry itself, which lack the rationality to reveal the diffusion behavior of the polymer slurry in fracture. Therefore, in this paper, a chemical reaction-fluid dynamic (CF) model was established. In addition, the Particle Swarm Optimization (PSO) algorithm was used to obtain the chemical reaction kinetic parameters of the polymer slurry. Based on the CF model, the diffusion characteristics of the polymer slurry during the fracture diffusion process were calculated. The applicability of the CF model was verified by comparing the experimental data with the calculated results. Finally, the influence of polymer preheating temperature and ambient temperature on slurry fracture grouting behavior was explored by the CF model. The research in this article provides some theoretical reference for the design of grouting parameters in fracture grouting engineering.