Polymer anti-seepage walls have been widely used in the anti-seepage reinforcement projects of earth dams. Dam crest is always supposed to meet the requirements of traffic load which has significant influence on the dam body and anti-seepage wall. In order to analyze the coordination characteristics of the deformation between polymer anti-seepage wall and dam under traffic loads, a 3D finite element model of an earth dam that considers the coupling effect of seepage field and stress field was established. Besides, the influence of load amplitude, vehicle speed and driving position on the stress and deformation characteristics of polymer anti-seepage wall and dam was analyzed, with the displacement difference between dam and wall, wall Mises stress and wall subsidence as indicators. The results show that, compared with vehicle speed, the load amplitude and vehicle speed of traffic load exerted a greater impact on the coordination characteristics of the deformation of the dam. The variation range of the displacement difference caused by axial load change reached 87.1%, while that resulted from driving position change reached 90.3%. That is, when the passing vehicle has a light axle load and passes quickly over the anti-seepage wall, it has less impact on the dam.

The Ground Penetrating Radar (GPR) method is a commonly used method for earth dam disease detection. However, the major challenge is that the obtained GPR image data of earth dam disease mainly relies on human judgment, especially in long-distance earth dam disease detection, which may lead to misjudgments and omissions. The You Only Look Once v5s (YOLOv5s) algorithm is innovatively employed for GPR image recognition to address the current challenge. The YOLOv5s neural network model has advantages over the traditional convolutional neural network in terms of object detection speed and accuracy. In this study, an earth dam disease detection model was established based on YOLOv5s. Raw images from actual earth dam disease detection and GPR forward simulation images were used as the initial dataset. Data augmentation techniques were applied to expand the original dataset. The LabelImg annotation tool was employed to classify and label earth dam disease, thereby creating an object detection dataset that includes earth dam disease features. The model was trained within this dataset. The results indicate that the total loss function of the model trained on the custom dataset initially decreases and then stabilizes, showing no signs of overfitting and demonstrating good generalizability. The earth dam disease detection model based on YOLOv5s achieved average precision rates of 96.0%, 95.5%, and 93.9% for voids, seepage, and loosening disease, respectively. It can be concluded that the earth dam disease detection model based on YOLOv5s may be an effective tool for intelligent GPR image recognition in identifying earth dam disease.

Non-aqueous reactive polymer grouting technology has been widely used in the repair engineering of dikes and dams with shallow diseases. By using the finite difference time-domain method and perfectly matched layer boundary conditions, the calculation model of dikes and dams with shallow diseases such as water-filled cave, air-filled cave and incompact area is established. The propagation process of electromagnetic waves of ground-penetrating radar in dikes and dams with shallow diseases using polymer grouting repair is simulated, and the forward simulation profiles and single-channel waveforms are obtained. The propagation characteristics such as waveform amplitude, waveform shape, transmission time, and reflection time are compared and analyzed. The results show that the forward simulation profiles of dikes and dams with water-filled caves before and after polymer grouting repair present two clusters of hyperbolas, but three clusters of hyperbolas with different amplitudes were observed at 50% repair. The amplitude of the hyperbola and the single-channel reflected waves before repair and 50% repair of the cave and incompact area are greater than those of 100% repair. The propagation characteristics of ground-penetrating radar can effectively explain the degree of polymer grouting repair for dikes and dams with shallow diseases, and provide a theoretical basis for using the ground-penetrating radar to evaluate the effect of polymer grouting technology to repair dikes and dams with shallow diseases.