Aiming to solve the challenges of low detection accuracy, poor anti‐interference ability, and slow detection speed in the traditional tunnel lining defect detection methods, a novel deep learning‐based model, named You Only Look Once network v4 enhanced by EfficientNet and depthwise separable convolution (DSC; YOLOv4‐ED), is proposed. In the YOLOv4‐ED, EfficientNet is used as the backbone to improve the identification accuracy of indistinguishable defect targets in complex tunnel background and light conditions. Furthermore, DSC block is introduced to reduce the storage space of the model and thereby enhance the detection efficiency. The experimental results indicate that the mean average precision, F1 score, Model Size, and FPS of YOLOv4‐ED are 81.84%, 81.99%, 49.3 MB, and 43.5 f/s, respectively, which is superior to the comparison models in both detection accuracy and efficiency. Based on robust and cost‐effective YOLOv4‐ED, a tunnel lining defect detection platform (TLDDP) with the capacity of automated inspection of various lining defects (i.e., water leakage, crack, rebar‐exposed) is built. The established TLDDP can realize the high‐precision and automatic detection of multiple tunnel lining defects under different lighting and complex background conditions of the practical in‐service tunnel.

Automatic detection method of tunnel lining multi‐defects via an enhanced You Only Look Once network

Better understanding the failure modes of tunnels excavated in the boulder-cobble mixed strata by distinct element method

Failure analysis and treatments of a loess tunnel being constructed in ground fissure area

Predictive control of slurry pressure balance in shield tunneling using diagonal recurrent neural network and evolved particle swarm optimization

Studies show that lining cracks are one of the most common anomalies that occur in the operational tunnels. Therefore, investigating the performance of the cracked linings is of significant importance during the tunnel maintenance. In the present study, model tests and numerical simulations are performed to investigate the influence of the longitudinal cracks at the invert on the mechanical behavior of the tunnel linings. Obtained results show that (1) the pre-existing cracks at the invert aggravate the crushing failure at the back of the fracture zone, leading to the brittle instability of the tunnel; (2) the deformation process of the cracked tunnels initially develops linearly up to a drastic increase. Moreover, the magnitude and the growth of the deformation at the damaged area of cracked linings before the abrupt failure are larger than those of the intact linings; (3) the cracks result in a distinct decrease in the bending moment at the damaged area, whereas the thrust force is less sensitive to the number of cracks; (4) the pre-existing cracks in the invert weaken the lining's ability to resist the pressure of surrounding rock and increase the share of the arch foot in the contact pressure; (5) the pre-existing cracks at the invert reduce the bearing area of linings, thereby weakening the flexural stiffness and favoring the crushing failure at the invert, which is the main reason for the decrease in the bearing capacity of the cracked tunnels.

Influence of cracks at the invert on the mechanical behavior of the tunnel structures

Analyses of the defects in highway tunnels in China

Shield tunnel is widely adopted in the metro construction, and backfill grouting is the significant part. With power-law fluid grouts as the study object, a cylindrical infiltration diffusion model...

Displacement infiltration diffusion model of power-law grout as backfill grouting of a shield tunnel

The Lanzhou Yellow River Tunnel is the first metro shield tunnel that undercrosses the Yellow River in China. It was completed after successfully overcoming several construction challenges, including strata with a high proportion of large-sized sandy cobble stratum being saturated, large-scale sand pits along the bank of the Yellow River, and a combination of boulders and erratic blocks of rock. Given the difficulties in constructing the tunnel, this paper summarizes the scheme employed to transform the cutter and cutter head design to be applicable to sandy cobble stratum and the key technology used to form the slurry film to facilitate crossing the sand pits in a systematic way. The transformation scheme primarily involved the addition of an adjusting device to control the aperture ratio of the shield on the cutter head, a protective device for the hob hub, and a protective device for the piston rod in the oil cylinder of the crusher. The implementation of measures mentioned above guarantees the safe completion of the tunnel, which can provide a reference for similar projects.

https://downloads.hindawi.com/journals/ace/2019/8358013.pdf

Shield Equipment Optimization and Construction Control Technology in Water-Rich and Sandy Cobble Stratum: A Case Study of the First Yellow River Metro Tunnel Undercrossing

Under the combined impacts of the operation time, design concept, and construction technology, extensive damage has occurred in tunnels built in China during the early stages of rapid development. ...

Damage management and safety evaluation for operating highway tunnels: a case study of Liupanshan tunnel

Fractal theory demonstrates significant merit in the feature expression of forms of matter in nature. This study uses fractal theory to study the backfill grouting of a shield tunnel. The seepage p...

Nan Qin

Papers

Analyses of the defects in highway tunnels in China

Displacement infiltration diffusion model of power-law grout as backfill grouting of a shield tunnel

Shield Equipment Optimization and Construction Control Technology in Water-Rich and Sandy Cobble Stratum: A Case Study of the First Yellow River Metro Tunnel Undercrossing

Damage management and safety evaluation for operating highway tunnels: a case study of Liupanshan tunnel

Model study on backfill grouting in shield tunnels based on fractal theory