Ground-penetrating radar (GPR) detects a tunnel with relatively low-frequency electromagnetic waves, which can result in poorly characterized reinforced steel bar (rebar) hyperbolas and make it challenging to recognize rebar. Thus, the rebar is located by using attenuation and reflection coefficients, and the hyperbolic feature of the rebar is reconstructed for recognition. Due to differences in the electromagnetic properties of rebar and other media in the second lining, the position of rebar in the one-dimensional time wave diagram (A-scan) is determined by using the attenuation and reflection coefficients. The rebar is recognized at the peak point in the A-scan. This peak point is in the opposite phase of the incident wave. The amplitude of these peaks is smaller than the peaks of the adjacent points. Then, these negative peak points are reconstructed on the two-dimensional scanning data (B-scan). Finally, the rebar is recognized by using the hyperbolic feature of the rebar. The method is applied in the Husa Tunnel in Yunnan Province, China. Moreover, in the mileage section YK81+506–YK81+542 of the Husa Tunnel, the hyperbolic feature of the reconstructed rebar is evident, and the rebar appears in the region of 5–7 ns in the B-scan.

Due to the rebars layer’s shielding effect on Ground Penetrating Radar (GPR) waves, the hyperbolic clutter generated by the rebars interferes with the echoes from void beneath them. The overlapping waveforms of both signals result in attenuation and distortion of the void signals, making it difficult to identify void defects under the rebar. This study proposes an unsupervised generative network model based on Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). Through a shared latent space, mapping is achieved between two image domains, effectively eliminating the multiple reflection interference signals caused by the rebar while accurately reconstructing the void defects, generating GPR B-Scan images without rebar clutter. Additionally, the channel and spatial attention module (CSA) is implemented into the model to help the network to better focus on the essential information in GPR images. The proposed model was validated through ablation and comparative experiments using synthetic data. Finally, real GPR data from the Husa Tunnel were used to verify the model’s effectiveness in practical engineering applications. The results showed that this model is highly effective; it improves the visibility of void defects signals, thereby enhancing the interpretability of GPR data for tunnel lining inspections.

Fracture zones in front of tunnel faces can easily cause falling blocks and landslides during the construction process. Using seismic waves and ground-penetrating radar (GPR) data, we extracted the features of fracture zones and achieved the advanced prediction of tunnel fracture zones. The energy variation in the reflected waves propagated by seismic waves at interfaces with different impedances of contact waves was found to manifest as positive and negative reflections, and the amplitude of reflected signals within the fracture zone areas thus increased. We designed a superimposed velocity spectrum, divided the areas of variation in wave velocity, and constructed the three-dimensional spatial distribution of the tunnel fracture zones. Based on the phase change, increase in amplitude, and increase in the center-frequency characteristics of the one-dimensional time waveform of the electromagnetic waves in the fault zone area (A-scan), we located the characteristic points of the fracture zones and observed the occurrence of in-phase axis misalignment in two-dimensional scanning (B-scan). We then implemented the identification of fracture zones. This method predicted the fractured area in the rock surrounding the Liangwangshan Tunnel, and during the tunnel excavation, the fracture zones appeared in the recognition area.

Rebar constitutes a crucial element within tunnel lining structures, where its precise arrangement plays a pivotal role in determining both structural stability and load-bearing capacity. Due to the rebar’s high dielectric constant approaching infinity, radar signal reflections are intensified, manifesting as distinct hyperbolic patterns within radar imagery. By performing convolutional operations, these hyperbolic features of rebar can be effectively extracted from radar images. Building upon the feature extraction capabilities of the ResNet50 model, this study introduces a Deformable Attention to Capture Salient Information (DAS) mechanism, employing deformable and separable convolutions to enhance rebar localization and concentrate on hyperbolic features resulting from multiple reflections. Before the Region Proposal Network (RPN) and region of interest (ROI) pooling stages in Faster R-CNN, this study integrates a hyperbolic attention (HAT) module. Through refined distance metrics, the hyperbolic attention mechanism enhances the network’s Precision in identifying rebar hyperbolic features within feature maps. To ensure robustness across diverse conditions, this study utilizes a simulated public dataset for tunnel linings, alongside real data from the Husa Tunnel, to create a comprehensive ground-penetrating radar image dataset for tunnel linings. Experimental results indicate that the proposed model achieved an Average Precision of 94.93%, reflecting a 3.14% increase compared to the baseline model. Lastly, in a random selection of 50 radar images for testing, the model achieved a rebar detection accuracy of 93.46%, representing an enhancement of 0.94% over the baseline model.

The secondary lining of a tunnel is a critical load-bearing component, whose stability and structural integrity are essential for ensuring the overall safety of the tunnel. However, identifying lining structures and estimating their thickness using ground-penetrating radar (GPR) remain challenging due to several inherent limitations. First, the limited electromagnetic contrast between the primary and secondary linings results in weak interface reflections in GPR imagery, thereby hindering accurate delineation. Second, construction errors such as over-excavation or under-excavation often lead to complex interface geometries, further complicating the interpretation of GPR signals. To address these challenges, we propose an enhanced YOLOv8-seg network capable of performing pixel-level segmentation on GPR images to accurately delineate secondary lining regions and estimate their thickness. The model integrates a convolutional block attention module (CBAM) to refine feature extraction by emphasizing critical characteristics of the two interface layers through channel-wise and spatial attention mechanisms. The model is first pretrained on the COCO dataset and subsequently fine-tuned via transfer learning using a hybrid GPR dataset comprising real-world measurements and numerically simulated data based on forward modeling. Finally, the model is validated on real-world GPR measurements acquired from the Longhai tunnel. Experimental results demonstrate that the proposed method reliably identifies secondary tunnel linings and accurately estimates their average thickness.