A new type support structure introduction and its contrast study with traditional support structure used in tunnel construction

Xu, Fei; Li, Shucai; Zhang, Qian‐qing; Li, Liping; Shi, Shaoshuai; Zhang, Qian

doi:10.1016/j.tust.2016.11.012

Cited by 46 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…𝑐 = 𝐹 𝑐 𝑐 * 𝐼 (8) where 𝑥 is the input value at the current moment; ℎ is the output of the previous neural unit; 𝑊 is the weight value of the input parameter 𝑥 and the memory unit; 𝑊 LSTM is a special recurrent neural network (RNN) that is mainly used to solve the problem of gradient disappearance and gradient explosion during the process of long sequence training [46][47][48] . LSTM is mainly composed of a forget gate, an input gate and an output gate, as shown in Figure 11.…”

Section: Long Short-term Memory (Lstm)mentioning

confidence: 99%

“…Complex and changeable geological conditions, high in situ stress and other factors have caused great difficulties in tunnel construction. With high in situ stress, rock bursts and large deformations in the surrounding rock of a tunnel can easily cause construction difficulties, threaten the safety of workers, delay the project and have other adverse effects [5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning in Conventional Tunnel Deformation in High In Situ Stress Regions

Chen

Fang

et al. 2022

Symmetry

View full text Add to dashboard Cite

Deformation prediction of extremely high in situ stress in soft-rock tunnels is a complex problem involving many parameters, and traditional analytical solutions and numerical simulations have difficulty achieving satisfactory results. This paper proposes the MIC-LSTM algorithm based on machine learning methods to predict the deformation of soft-rock tunnels under extremely high in situ stress conditions caused by construction. The study first analyzed the difficulties of engineering construction and the construction plan; then, numerical simulation was used to verify the modified construction plan. To prove that the construction plan was reasonable, machine learning was used to analyze the correlation of the various parameters that cause tunnel deformation; then, the future deformation of the tunnel was predicted. The study found that: (1) the new construction scheme contains symmetrical arrangement of bolts and two support structures along the tunnel vault can effectively control the deformation of the tunnel, and meet the requirements of the specification; (2) the rock uniaxial compressive strength had the greatest impact on tunnel deformation, and the rock humidity had the least influence on tunnel deformation; and (3) the prediction curve based on the deep learning model had a higher similarity to the monitoring curve compared with the traditional numerical analysis software. The MIC-LSTM machine algorithm provides a new approach to predicting the deformation of extremely high in situ stress soft-rock tunnels.

show abstract

Section: Long Short-term Memory (Lstm)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine Learning in Conventional Tunnel Deformation in High In Situ Stress Regions

Chen

Fang

et al. 2022

Symmetry

View full text Add to dashboard Cite

show abstract

“…Therefore, in the first stage, an equivalent simulation method was adopted to simulate construction excavation, which would simplify the difficulty and computational complexity of the numerical simulation. The detail components of a steel arch model, including the primary lining [24] and rock bolt in surrounding mass [25][26][27], mainly consist of surrounding rock, primary lining, and secondary lining. The surrounding rock was divided into eight-node solid units, and the material properties were described by the elastoplastic model and the Mohr-Coulomb yield criterion.…”

Section: Introductionmentioning

confidence: 99%

Lining Fatigue Test and Influence Zoning of Tridimensional Cross-Tunnel under High-Speed Train Loads

et al. 2020

View full text Add to dashboard Cite

Tridimensional cross tunnels usually manifest the vulnerable components of a high-speed railway caused by the sophistication of the structural pattern and the continuous shock from the train. The frequent defect of tunnel lining at the intersection would affect the safe operation of the two rails. As a result, attention has been paid to fatigue damage caused by the long-term dynamic load from a running train, in order to ensure the safety and serviceability of the cross tunnel lining. However, an influence zoning method with respect to tunnel crossing for the direct estimation of whether the lining structure is damaged due to the train load, and to what extent, is unavailable. In this paper, a systematic study that consists of numerical simulation and fatigue damage experiment is conducted to develop an approximate method to enable practicing engineers to evaluate reasonable design parameters. The initial static stress, which corresponds to the static tensile stress of secondary lining under the stratum load, and the maximum dynamic stress, which refers to the maximum dynamic tensile stress under the train load, are estimated according to the numerical simulation. A simplified damage evolution model and its parameters are identified on the basis of a systematic fatigue damage experiment. Finally, the influence zoning method is conducted on the basis of two criteria, namely (1) that initial stress level should not exceed 0.6, and (2) that load cycles should not exceed N = 2 × 106 times. Thus, the practicing parameters during the cross tunnel design, such as surrounding rock mass, cross angle, rock pillar thickness between two tunnels, and train speed can be utilized conveniently by using the proposed calculation charts, according to the identification of initial stress level and the magnitude of dynamic stresses caused by the train load.

show abstract

“…Tunnels excavated in deep-buried and layered soft surrounding rock often encounter large deformation, accompanied by lining cracking and serious deformation of steel arch, such as Gushan Tunnel and Muzhailing Tunnel [1][2][3]. Unlike shallow tunnel, the deformation mechanism and stability of surrounding rock are difficult to control due to deep burial, high geo-stress, large span, and complex rock characteristics [4][5][6][7][8][9][10]. When excavating a tunnel in soft rock under squeezing stress, the ground slowly enters the opening without obvious cracks or loss of continuity.…”

Section: Introductionmentioning

confidence: 99%

Three-Dimensional Finite Element Modeling of Soft Rock Tunnel With Large Section: A Case Study

Zhang

2020

Front. Phys.

View full text Add to dashboard Cite

With deep-buried depth, large span, high geo-stress, complex geological conditions, and its large sections, the deformation behavior of the Gaopo Tunnel is a complex three-dimensional problem. To reveal the deformation behavior of the tunnel and evaluate the current support scheme, this paper establishes a three-dimensional model by benching tunneling method, and compares the monitoring data to analyze the deformation behavior of the surrounding rock and the variation of the stress field in the support structure. The results demonstrate that the rock inclination angle is 4 • to 10 • , the micro-dip layered structure, which is the main factor for the asymmetric deformation behavior of soft rock tunnel with large section passing through coal seams. The maximum displacement of surrounding rock and the maximum stress of the supporting structure are within the safe range in current scheme. Furthermore, some measures are summarized, which may provide some reference for similar engineering in the future.

show abstract

A new type support structure introduction and its contrast study with traditional support structure used in tunnel construction

Cited by 46 publications

References 13 publications

Machine Learning in Conventional Tunnel Deformation in High In Situ Stress Regions

Machine Learning in Conventional Tunnel Deformation in High In Situ Stress Regions

Lining Fatigue Test and Influence Zoning of Tridimensional Cross-Tunnel under High-Speed Train Loads

Three-Dimensional Finite Element Modeling of Soft Rock Tunnel With Large Section: A Case Study

Contact Info

Product

Resources

About