The excavation of large-span triple tunnels using drilling and blasting method inevitably causes complicated load transfer effects and induces potentially damaging ground vibrations. In this study, the structural responses (including the surrounding rock pressure, normal-contact pressure between the primary and secondary linings, internal forces in the secondary lining) and the seismic responses (including peak particle velocity and corner frequency), are systematically recorded. It is found that the first-excavated left tunnel is influenced heavily by the excavation of the last-excavated middle tunnel, whereas it is hardly affected by the excavation of the second-excavated right tunnel. The load carried by the primary lining is approximately three times as that carried by the secondary lining. The middle tunnel was in the least desirable state due to the formation of the large Protodyakonov's equilibrium arch (PEA). Based on timely feedback of the comprehensive monitoring system, a series of vibration-reducing techniques were applied and effectively guaranteed safety during blasting construction. By referring to Chinese codes, the minimum safety factor of the secondary lining is 1.3; the maximum PPV (0.15 cm/s) is lower than the allowable value; and the corner frequency (40-140 Hz) will not cause resonant vibration of the Great Wall.

Estimating the tunneling‐induced responses of a soil–foundation system is crucial for safety control in urban underground engineering. In existing analytical research, the soil–foundation interaction is considered based on the Winkler soil model, with minimal focus on the continuum soil model. Hence, in this study, based on the continuum soil model, an approximate analytical solution is derived to predict the tunneling‐induced responses of a soil–foundation system considering the contact effect, where an approximation by replacing the surface of the complex variable solution for an elastic half‐plane with a tunnel with the mathematical expression of Sagaseta's ground loss settlement formula is adopted. A new strategy is proposed to optimize the derivation process, where the normal contact pressure after tunnel excavation is directly determined using the contact mechanics, and the proposed solution is obtained using the superposition principle. Subsequently, the approximation is proven to be accurate when the ratio of the buried depth to the tunnel radius is greater than 2.00. The proposed solution meets the given conditions and is in good agreement with numerical results, which verify the correctness of analytical solution. Furthermore, a parametric study is performed to investigate the influences of the key parameters on the mechanical responses. The results indicate that the proposed solution can quantitatively describe the nonlinear contact characteristics in the soil–foundation system; the contact effect is found to contribute to the discontinuous displacement and stress concentration when subjected to the significant effects of tunnel excavation.

No abstract

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.