Probabilistic Assessment for Concrete Spalling in Tunnel Structures

Yuan, Yong; Jiang, Xiang; Ai, Qing

doi:10.1061/ajrua6.0000912

Cited by 14 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leakage areas, also called moisture marks, are the most significant defects, ranked first among other structural problems faced by shield tunnels in Shanghai, China 2,3 . Besides, concrete scaling is a defect that should not be ignored in this respect 4 . If concrete scaling is not timely detected until it progresses, it may reach a certain level wherein rebar inside concrete structures is exposed and corroded, compromising durability and integrity of concrete lining structures.…”

Section: Introductionmentioning

confidence: 99%

“…2,3 Besides, concrete scaling is a defect that should not be ignored in this respect. 4 If concrete scaling is not timely detected until it progresses, it may reach a certain level wherein rebar inside concrete structures is exposed and corroded, compromising durability and integrity of concrete lining structures. Hence, from the maintenance viewpoint, inspection and quantitative analysis of leakage areas and scaling are essential.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Deep learning‐based classification and instance segmentation of leakage‐area and scaling images of shield tunnel linings

Zhao

Shadabfar

Zhang

et al. 2021

Struct Control Health Monit

View full text Add to dashboard Cite

This paper presents an approach for the integrated process of classification and instance segmentation of leakage-area and scaling images from shield tunnel linings. For this purpose, the previously established dataset of leakage-area images by the authors is enlarged by means of adding scaling ones. Afterwards, data augmentation is implemented to enrich the database in the classification dataset, and the augmented classification dataset contains 5776 images. The instance segmentation dataset is subsequently enlarged through original images without any data augmentation, including 1496 images. Then a residual net with 101 layers (i.e., ResNet-101) is applied to the classification dataset to obtain a model that can identify leakage-area and scaling images from those of shield tunnel linings. The ResNet-101 classification model achieves an accuracy of 93.37% in terms of testing classification dataset. Moreover, a mask region-based convolutional neural network (Mask R-CNN) is utilized to perform instance segmentation of leakage areas and scaling in the images classified by the ResNet-101 model. The segmentation results of the Mask R-CNN model show 96.1% and 95.6% average precision (AP) with intersection over union (IoU) of 0.5 for bounding box and mask predication, respectively. By using the proposed approach, the leakage-area and scaling defects can be automatically classified and quantified with an overall accuracy of 89.3%, which is quite promising compared to the inherent uncertainty in geotechnical engineering. Image mosaicing is finally applied to provide inspectors with the intuitive observation of the location and distribution information of defects on the tunnel lining.

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Deep learning‐based classification and instance segmentation of leakage‐area and scaling images of shield tunnel linings

Zhao

Shadabfar

Zhang

et al. 2021

Struct Control Health Monit

View full text Add to dashboard Cite

show abstract

“…Spalling is a small but non-negligible tunneling disease [2] , which is a surface defect that is deeper than the normal surface of the tunnel due to material shedding due to aging. Peeling off blocks is one of the most serious problems affecting tunnel performance and reliability [3] .…”

Section: Introductionmentioning

confidence: 99%

Research on detection of tunnel peeling off blocks based on 3D laser scanning system

Pan

Huang²

2023

International Conference on Geographic Information and Remote Sensing Technology (GIRST 2022)

View full text Add to dashboard Cite

The identification of peeling off blocks is an important part of tunnel disease detection. In order to effectively solve the problem of accuracy of the identification of peeling off blocks in tunnels, this paper focuses on the use of the threedimensional coordinates of the point cloud data obtained by the laser scanning system to realize the detection of peeling off blocks. A study of automatic detection of blocks. In the proposed automatic detection method for peeling off blocks, the original tunnel point cloud data is first filtered to remove outliers; then the point cloud data is coordinately transformed to convert the cylindrical point cloud into a rectangular point cloud; The cloud constructs a triangular mesh, and by calculating the area of the triangular mesh and the projected area of the triangular mesh, the specific position of the peeling block can be obtained; finally, the point cloud is converted into an image, and the Hough transform is used to mark the pipeline and tunnel joints. Get more intuitive detection results. This paper uses the real tunnel point cloud data to carry out the peeling off block detection experiment, and the results show the effectiveness and feasibility of the method.

show abstract

“…The results showed that the lining in the defective area was bent outward and that there was a tensile stress concentration on the outer surface and a compressive stress concentration at the edge. Yuan et al [25] proposed a model that can predict the structural life and safety based on the concrete spalling of a tunnel's lining. Lai et al [26] found more than 100 cracks in the lining structure of the Shitigou Tunnel due to lining defects found through an inspection.…”

Section: Introductionmentioning

confidence: 99%

Safety Evaluation of Plain Concrete Lining Considering Deterioration and Aerodynamic Effects

Wang

et al. 2023

Sustainability

View full text Add to dashboard Cite

With an increase in the service time of high-speed railway tunnels, various defects caused by construction-quality defects in the secondary lining begin to appear. How to evaluate the safety of such tunnels and take countermeasures is very important for the safe operation of tunnels. Based on the load-structure method and a numerical simulation, this paper studied the short-term and long-term safety of the missing section of anti-crack reinforcement mesh in the plain concrete lining of a high-speed railway mountain tunnel. The short-term safety evaluation considered the influence of negative pressure caused by aerodynamic effects. The long-term safety evaluation considered the combined influence of the surrounding rock and concrete deterioration and the negative pressure and concrete fatigue damage caused by aerodynamic effects. The results showed that under the negative pressure generated by aerodynamic effects, the minimum tensile safety factor of the lining in the defective section increased by 3.8%, while the minimum compressive safety factor of the lining decreased by 7.9%. The negative pressure generated by the aerodynamic effects had little impact on the short-term safety of the lining in the defective section. During the long-term safety evaluation, the overall safety of the defective section decreased significantly, and the minimum tensile and minimum compressive safety factors of the lining decreased by 59.4% and 66.8%, respectively. The calculation results for the initial design do not meet the long-term design requirements and cannot guarantee the long-term safe operation of the tunnel. Finally, two new strengthening methods of galvanized steel mesh-short bolts and galvanized corrugated steel plate-short bolts were proposed to strengthen the defective section of the concrete lining, so as to improve the ultimate bearing capacity and toughness of the plain concrete lining structure.

show abstract

Probabilistic Assessment for Concrete Spalling in Tunnel Structures

Cited by 14 publications

References 37 publications

Deep learning‐based classification and instance segmentation of leakage‐area and scaling images of shield tunnel linings

Deep learning‐based classification and instance segmentation of leakage‐area and scaling images of shield tunnel linings

Research on detection of tunnel peeling off blocks based on 3D laser scanning system

Safety Evaluation of Plain Concrete Lining Considering Deterioration and Aerodynamic Effects

Contact Info

Product

Resources

About