A hydraulic antiseepage wall is an underground diaphragm wall built in an Earth and rockfill dam to prevent seepage. The quality of the wall directly affects the impermeable effect and structural safety. However, defects within the antiseepage wall are usually randomly distributed and relatively hidden, so it is crucial to timely and accurately capture the hidden defects within the wall. Crosshole ground penetrating radar (GPR) is an efficient geophysical method for detecting and locating inner defects in antiseepage walls without excavation. It involves inserting antennas into measurement pipes buried in the structure to conduct high-frequency electromagnetic signal (EMS) measurements. By analyzing and inverting the EMS data, an inference of the defect position, size, shape, and physical characteristics is achieved based on the differences in the electrical parameters of various media. Crosshole GPR has advantages such as high accuracy, high resolution, and sensitivity to water-containing materials, and it is not limited by penetration depth.

Herein, a teaching experiment was performed using crosshole GPR to detect concealed defects in an antiseepage wall. The experimental system comprises a visual water tank, a visual model box, and a stepped-frequency crosshole GPR system. The dimensions of the visual water tank and model box are 1.2 m × 1.0 m × 1.5 m and 0.6 m × 0.2 m × 1.0 m, respectively. The visual model box is placed inside the water tank, and the cavity between these two components is filled with water (permittivity of 78.28 and conductivity of 0.30 S/m) to simulate the surrounding backfill. The visual model box is filled with dimethyl malonate to simulate the concrete wall because the dielectric parameters of dimethyl malonate (permittivity of 15.88 and conductivity of 0.24 S/m) are similar to those of concrete wall. Two measurement pipes are placed vertically from the top to the bottom of the visual model box, enabling the antennas to move up and down in the pipes and facilitating the zero-offset profiling and multioffset gather. The stepped-frequency crosshole GPR system comprises a vector network analyzer (VNA), a pair of transmitting and receiving antennas, and a laptop. The VNA generates and collects electric signals (ESs). The transmitting antenna converts ES to EMSs, propagating through the medium between the antennas. Next, the receiving antenna receives EMSs and relays them back to the VNA.

Four cases are well-designed to simulate the different defects in a hydraulic antiseepage wall, including voids full of air, water, mud, and uncompacted stone. Crosshole GPR data are collected for all the cases, and electronic parameter inversion is performed using computed tomography. The physical characteristics of the defects can be accurately revealed, indicating that the experimental system can use crosshole GPR to effectively detect concealed defects within the antiseepage wall.

Using this experimental system, GPR images are easily acquired and the electronic parameter inversion of the medium is achieved, enabling an inference of the defects. Meanwhile, this system inspires students’ innovative thinking, enhancing their research capabilities and achieving the goal of promoting teaching through research and vice versa.

As a major part of water conservancy infrastructure, dams play an important role in economic construction and social development. Cracks are one of the most common types of damage to dams, destroying the overall structure and affecting the durability, strength, and stability of the structure. Therefore, regular and systematic crack detection of concrete dams is of great importance to ensure their safe and stable operation. However, the traditional concrete dam crack detection technology suffers from slow speed, low precision, and insufficient generalization performance, bringing difficulty in meeting the requirements of concrete dam crack detection. Therefore, the objective of this study is to develop an efficient, accurate, and real-time concrete dam crack detection technology.

Existing crack detection methods based on semantic segmentation algorithms run slowly and detect concrete cracks in real time with difficulty. In addition, the dam operation environment is harsh, resulting in complex image backgrounds and inconspicuous crack image features, increasing the difficulty of identification. This study proposes a real-time detection method for concrete dam cracks based on deep learning object detection method you only look once x (YOLOX), called YOLOX-dam crack detection (YOLOX-DCD), to address the problems of slow speed, low accuracy, and insufficient generalization of the traditional detection techniques for concrete dam cracks. This method improves the performance of YOLOX to detect concrete dam cracks. First, a lightweight convolutional block attention module (CBAM) is added to the network structure, which integrates the spatial attention mechanism with the channel attention mechanism. The CBAM makes the network pay more attention to crack features and improves detection performance. Second, a complete intersection over union (CIoU) is introduced to replace IoU as the loss function. The CIoU incorporates the normalized distance between the predicted box and the target box and summarizes three geometric factors in bounding box regression, i.e., overlap area, central point distance, and aspect ratio, thereby improving the convergence speed and detection performance of the algorithm.

The experimental evaluation was conducted on a self-made concrete dam crack dataset. Ablation experiments were performed on each improved module, and the results showed that the improved method proposed in this paper effectively improved the detection accuracy of the model and maintained a high detection speed. The proposed model had an AP_0.5 on the test set of 90.84% and an F₁ of 87.74%, which were higher than those of various existing object detection methods. The FPS of the model was 65, and the detection speed was faster. The model was small, with a size of 25.67 MB, and could be deployed on a mobile terminal for real-time crack detection.

In this study, a CBAM and the CIoU loss function are added to the YOLOX network, which make the network pay more attention to crack characteristics and improves the detection performance for concrete dam cracks. Experiments reveal that the method in this paper has fast speed, high precision, and few parameters and is obviously better than the classical object detection algorithms. Therefore, the proposed method meets the requirements of efficient, accurate, and real-time crack detection of concrete dams and is promising for providing a technical means for crack detection.