Evaluation of Void Defects behind Tunnel Lining through GPR forward Simulation

Wu, Xianlong; Bao, Xiaohua; Shen, Jun; Chen, Xiangsheng; Cui, Hongzhi

doi:10.3390/s22249702

Cited by 11 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu suggested a method for detecting voids using GPR and a forward model based on the FDTD method. It was observed that the response pattern of the voids depends on their width, and waterfilling expands the response range and produces virtual images (Wu et al, 2022). Despite the interference from rein-forcement bars, the central location of the voids can still be precisely located using 3-D GPR.…”

Section: Introductionmentioning

confidence: 99%

Deep learning–based inverse analysis of GPR data for landslide hazards

Qin,

Jiang,

Tian

et al. 2024

Front. Earth Sci.

View full text Add to dashboard Cite

In mountainous landscapes, the diverse geotechnical conditions amplify landslide susceptibility. Factors such as precipitation and seismic activity can trigger landslides, while inherent hazards such as voids, fissures, and compaction deficits jeopardize long-term slope stability. Detecting and forecasting these susceptibilities accurately is crucial. In this paper, the time-domain finite-difference approach and the gprMax software are used to conduct forward modeling of landslide susceptibility. An electrical model of subsurface aqueous structures is created, including water-filled and air-filled cavities, fracture zones, and fault lines. The distinctive radar signal responses within these environments are examined, and a dataset of B-scan images associated with their electrical models is constructed. By employing deep learning algorithms and the robust nonlinear mapping ability of convolutional neural networks in the Pix2Pix generative adversarial network, we accelerate the intelligent inversion of the geological radar data on landslide susceptibility. This innovative approach effectively reconstructs hazard models, offering a reliable basis for interpretation of radar signals.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning–based inverse analysis of GPR data for landslide hazards

Qin,

Jiang,

Tian

et al. 2024

Front. Earth Sci.

View full text Add to dashboard Cite

show abstract

“…With the primary objective of resolving the data signal-to-noise ratio and multi-path interference problems to offer assurances for data feature extraction, Lei et al [ 10 ] suggested an air-coupled geo-radar detection technique provided by F-K filtering and BP migration. A strong technical guarantee for single defect detection was provided by the GPR forward simulation model developed by Wu et al [ 11 ], but since tunnel defects are frequently made up of hollow, water-filling, and non-compactness, the model’s generalization ability is not ideal. Ali et al [ 12 ], using Faster-RCNN and YOLOv3 networks as well as conventional detection techniques, examined the performance of concrete structures; the findings revealed that the convolutional neural network-based detection strategy had greater detection accuracy and localization precision.…”

Section: Introductionmentioning

confidence: 99%

MFF-YOLO: An Accurate Model for Detecting Tunnel Defects Based on Multi-Scale Feature Fusion

Жу

Wang

Xie

et al. 2023

Sensors

View full text Add to dashboard Cite

Tunnel linings require routine inspection as they have a big impact on a tunnel’s safety and longevity. In this study, the convolutional neural network was utilized to develop the MFF-YOLO model. To improve feature learning efficiency, a multi-scale feature fusion network was constructed within the neck network. Additionally, a reweighted screening method was devised at the prediction stage to address the problem of duplicate detection frames. Moreover, the loss function was adjusted to maximize the effectiveness of model training and improve its overall performance. The results show that the model has a recall and accuracy that are 7.1% and 6.0% greater than those of the YOLOv5 model, reaching 89.5% and 89.4%, respectively, as well as the ability to reliably identify targets that the previous model error detection and miss detection. The MFF-YOLO model improves tunnel lining detection performance generally.

show abstract

“…During the process of tunnel construction, the lining may develop a variety of defects or diseases due to various reasons [ 2 , 3 , 4 , 5 , 6 ]. One of the more common problems is voids on the vault [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

Numerical Investigation of Longitudinal through Voids in Tunnel Secondary Lining Vaults and Steel Plate Strengthening

Shao

et al. 2023

Materials

View full text Add to dashboard Cite

This study investigates the influence of longitudinal through voids on vault lining. Firstly, a loading test was carried out on a local void model, and the CDP model was used for numerical verification. It was found that the damage to the lining caused by a longitudinal through void was primarily located at the void boundary. On the basis of these findings, an overall model of the vault’s through void was established using the CDP model. The effects of the void on the circumferential stress, vertical deformation, axial force, and bending moment of the lining surface were analyzed, and the damage characteristics of the vault’s through void lining were studied. The results indicated that the through void of the vault caused circumferential tensile stress on the lining surface of the void boundary, while the compressive stress of the vault increased significantly, resulting in a relatively uplifted vault. Furthermore, the axial force within the void range decreased, and the local positive bending moment at the void boundary increased significantly. The impact of the void increased gradually with the height of the void. If the height of the longitudinal through void is large, the inner surface of the lining at the void boundary will crack longitudinally, and the vault will be at risk of falling blocks or even being crushed.

show abstract

Evaluation of Void Defects behind Tunnel Lining through GPR forward Simulation

Cited by 11 publications

References 37 publications

Deep learning–based inverse analysis of GPR data for landslide hazards

Deep learning–based inverse analysis of GPR data for landslide hazards

MFF-YOLO: An Accurate Model for Detecting Tunnel Defects Based on Multi-Scale Feature Fusion

Numerical Investigation of Longitudinal through Voids in Tunnel Secondary Lining Vaults and Steel Plate Strengthening

Contact Info

Product

Resources

About