Songtao Hu

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.

Precast concrete block slope protection is widely used due to its advantages of easy detection and laying, ease of organization, and the limited time required for construction. In order to prevent the soil or gravel bedding of precast concrete from being subjected to wind and wave pressures, the joints between precast concrete blocks are usually filled with mortar. However, the existing standards do not specify the width or material of the joints. Furthermore, excessively wide mortar joints or shrinkage of the mortar can result in loss, a hollowed-out cushion, and damage to the slope, thus compromising the quality of slope protection engineering. To establish standards for controlling the quality of slope protection seams, this paper designed and conducted a physical model test of precast concrete block revetment seams. By embedding pore water pressure sensors in the cushion layer, changes in the pore water pressure were observed under varying conditions, including different water pore pressure sensor locations, water levels in front of the embankment, and different joint widths. Based on the test results, design standards for joint widths and recommendations for the treatment of joint mortar materials were proposed. After adding different amounts of a calcium oxide–calcium sulfoaluminate composite expansion agent (HME) into a joint mortar material, the paper also carried out a shear test on the contact surface between the joint mortar and the slope protection concrete after adding varying amounts of a calcium oxide-calcium sulfoaluminate composite expansion agent (HME) to the joint mortar material. Following a microporous structure test, recommendations for joint mortar construction treatment were proposed. The results indicate that the pore water pressure of the precast concrete slope protection cushion is closely related to the position of the cushion, the water level in front of the embankment, and the width of the paving seam. When the masonry seam width increased from 0.5 mm to 1 mm and from 1 mm to 1.5 mm, the variation ranges of the pore water pressure were 40–80% and 6–20%, respectively, with the latter being significantly lower than the former. Therefore, in practical engineering, joint treatment should take into account the impact of the cushion position, the water level in front of the dike, and the joint mortar width. Mortar shedding within the range of wave climbing height should be addressed promptly, and joint width should be controlled to below 1 cm as much as possible to effectively prevent damage to the cushion surface. The addition of an expansion agent can improve the bond strength of the concrete and mortar to a certain extent. The study found that an 8% content of the expansion agent resulted in the best mortar bond strength and the densest microstructure. These research findings can serve as a basis for the development of quality control standards for precast concrete slope protection.