Automated extraction and evaluation of fracture trace maps from rock tunnel face images via deep learning

Chen, Jiayao; Zhou, Mingliang; Huang, Hongwei; Zhang, Dong Ming; Peng, Zheng

doi:10.1016/j.ijrmms.2021.104745

Cited by 89 publications

(25 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, photogrammetry has developed rapidly as a non-destructive inspection method for tunnel structure health monitoring [33][34][35]65]. By mounting high-resolution linear charge coupled device (CCD) cameras onto a movable inspection platform, photogrammetry can achieve continuous scanning imaging of the tunnel lining surface along the longitudinal direction.…”

Section: D Inspection Results Of a Testing Tunnel Sectionmentioning

confidence: 99%

“…have been proposed for detecting target objects to meet the needs of each specialized application. For inspection tasks during tunnel operation, scholars have conducted many studies into the automated detection of concrete spalling [3,26], lining cracks [27][28][29], water leakages [30][31][32], and rock mass evaluation [33][34][35] based on the DCNN models. Relying on the colour feature differences, the DCNN-based models show superior performance in distinguishing target objects from the context of the images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Approach to Automated 3D Spalling Defects Inspection in Railway Tunnel Linings Using Laser Intensity and Depth Information

Zhou

Cheng

Huang

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

The detection of concrete spalling is critical for tunnel inspectors to assess structural risks and guarantee the daily operation of the railway tunnel. However, traditional spalling detection methods mostly rely on visual inspection or camera images taken manually, which are inefficient and unreliable. In this study, an integrated approach based on laser intensity and depth features is proposed for the automated detection and quantification of concrete spalling. The Railway Tunnel Spalling Defects (RTSD) database, containing intensity images and depth images of the tunnel linings, is established via mobile laser scanning (MLS), and the Spalling Intensity Depurator Network (SIDNet) model is proposed for automatic extraction of the concrete spalling features. The proposed model is trained, validated and tested on the established RSTD dataset with impressive results. Comparison with several other spalling detection models shows that the proposed model performs better in terms of various indicators such as MPA (0.985) and MIoU (0.925). The extra depth information obtained from MLS allows for the accurate evaluation of the volume of detected spalling defects, which is beyond the reach of traditional methods. In addition, a triangulation mesh method is implemented to reconstruct the 3D tunnel lining model and visualize the 3D inspection results. As a result, a 3D inspection report can be outputted automatically containing quantified spalling defect information along with relevant spatial coordinates. The proposed approach has been conducted on several railway tunnels in Yunnan province, China and the experimental results have proved its validity and feasibility.

show abstract

Section: D Inspection Results Of a Testing Tunnel Sectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Approach to Automated 3D Spalling Defects Inspection in Railway Tunnel Linings Using Laser Intensity and Depth Information

Zhou

Cheng

Huang

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, the shape of cracks is arbitrary and hard to describe by a set of particular features, which yields poor performances of crack segmentation because of the complicated geoenvironment and working conditions. Furthermore, crack detection is heavily affected by noise and lights; existing methods rely on preprocessed approaches to distinguish known features between cracks and background noises, such as numerical features in segmented patches [29] and multiple greyscale filters [41]. However, the above methods require prior knowledge of different types of cracks, which means that the obtained features can be barely generalized to various types of cracks.…”

Section: Related Workmentioning

confidence: 99%

“…In this paper, we aim to carry out fine-grained identification and quantification of rock linear discontinuities (cracks) on various types of rock surfaces and segment each crack from the background at pixel level. Current batch-based segmentation methods have provided excellent pixel-wise segmentation methods for rock defect detection using deep learning, but they mostly consider simple weak interlayer segmentation or tunnel face defect identification [27][28][29]. These methods can barely handle the fine-grained segmentation problem of multiple linear discontinuities at the pixel level.…”

Section: Introductionmentioning

confidence: 99%

Multi-CrackNet: A Fast Segmentation and Quantification Combined Method for Rock Discontinuity Traces by Capturing an Image

Lan

Deng

et al. 2022

Geofluids

View full text Add to dashboard Cite

Discontinuity investigation and characterization onsite is a labor-dependent work because current techniques cannot precisely handle multiple discontinuity identifications automatically under different work conditions. This paper proposes the multi-CrackNet which enables us to identify and segment linear discontinuities (joints and cracks) for random types of rock surface. A modified feature extraction network called the multiscale feature fusion pyramid network (MFFPN) has been developed based on FPN to capture and fuse more sensitive texture features of cracks across different types of background. With the help of a new training scheme by setting up 3 stages of training to simulate the human-based learning process, the established model can learn more features steadily and robustly from well-labelled databases. Additionally, a hybrid pixel-level quantification method is proposed to automatically compute the length, width, and inclination of cracks. Results show that the proposed method can achieve a detection accuracy of 87.1% for 1 to 9 sets of cracks on the rock surface across different types of rock. Case studies in Anshan West are provided to verify the reliability and accuracy of our method in macrolinear discontinuity identification and quantification, which sees great potentials in site investigation by saving a large amount of labor force.

show abstract

“…Geosynthetic reinforcement exerts its tensile strength, improves the lateral modulus of soil, forms soil arch effects between each layer of reinforced material and restrains the lateral deformation of soil by the friction between reinforcement and soil, so as to improve the bearing capacity and shear strength of soil, and reduce the horizontal lateral pressure of soil. Especially for geogrids, the mutual friction between the geogrid and the soil and the special interlocking effects of the geogrid mesh limit the lateral deformation of the upper and lower soil, improve the shear strength of the reinforced soil, and enhance the stability of the soil [6,7]. Jelušič, P. and Žlender, B.…”

Section: Introductionmentioning

confidence: 99%

Centrifugal Model Test and Simulation of Geogrid Reinforced Backfill and EPS Interlayer on Bridge Abutment

Zheng

Fang

2022

Sustainability

View full text Add to dashboard Cite

In this paper, the use of geotechnical centrifuge and numerical modeling techniques to investigate the influence of geogrid reinforcement and EPS interlayer on the lateral earth pressure and the backfill surface settlements behind gravity abutment and pile-supported abutment is reported. According to the principle of equal strain, the abutment back structure, foundation, backfill material, grid and interlayer material were simulated, and the centrifugal model test for two types of abutments was carried out with a model scale of n = 62.5, 40, respectively. The tests showed that the reinforcement of the geogrid could reduce the surface settlement of backfill and the lateral earth pressure of the backfill on the back of abutment. After setting the EPS interlayer, the influence of abutment displacement on earth pressure could be eliminated, and the earth pressure of the backfill material on the abutment back was significantly reduced. The “interlayer + geogrid” structure further reduced the earth pressure of backfill material on the abutment back. The existence of the EPS interlayer adjusted the strain distribution of the reinforced material, significantly increasing the strain of the reinforced material near the abutment, which was conducive to the reinforcement effect. The above research conclusions could provide a basis for the design and practical application of abutment backfill materials.

show abstract

Automated extraction and evaluation of fracture trace maps from rock tunnel face images via deep learning

Cited by 89 publications

References 54 publications

A Novel Approach to Automated 3D Spalling Defects Inspection in Railway Tunnel Linings Using Laser Intensity and Depth Information

A Novel Approach to Automated 3D Spalling Defects Inspection in Railway Tunnel Linings Using Laser Intensity and Depth Information

Multi-CrackNet: A Fast Segmentation and Quantification Combined Method for Rock Discontinuity Traces by Capturing an Image

Centrifugal Model Test and Simulation of Geogrid Reinforced Backfill and EPS Interlayer on Bridge Abutment

Contact Info

Product

Resources

About