Relatively low ground-penetrating radar antenna frequencies are usually selected for tunnel inspection due to the thickness of the lining, which causes the geometric features of voids in the image to be blurred and difficult to identify. Therefore, the boundary points of the voids are determined by combining reflection and attenuation coefficients, and the geometric features are constructed to identify the voids. Depending on the electromagnetic differences between the void and other mediums in the lining, when the electromagnetic wave propagates from the lining concrete to the void, the reflection coefficient is positive, and the phase of the reflected wave is the same as the incident wave. Conversely, the phase of the reflected wave is opposite to the incident wave. Therefore, the boundary point can be determined in the one dimension time-waveform diagram (A-Scan) based on the phase change. Moreover, the amplitude of the electromagnetic wave attenuates exponentially in the concrete, but it attenuates slowly in the void. Also, electromagnetic waves exhibit high-frequency characteristics in the lining but low-frequency characteristics in the voids. Boundary points that conform to the variation of amplitude and frequency characteristics in the void are screened. These boundary points are then constructed in two-dimensional scan data (B-Scan) to identify the voids by using the geometry of the voids. This method is applied to the Hu Sa Tunnel. The voids are successfully identified in the mileage section YK81+310–YK81+422 of the Hu Sa Tunnel, and the depth of cover and the area of voids are correctly estimated.

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.