Analytical model for the sealant performance of tunnel gasketed joints based on multi-scale contact and percolation theories

The localised leakage in shield tunnels that mainly occurs at segment joints may induce other defects,which threatens operational safety.To obtain a universal solution for the sealant performance of gasketed joints,we proposed a novel analytical model based on the multiscale contact and percolation theories,in which the obtained percolation pressure and interfacial separation can be utilized to derive the critical water leakage pressure and leakage rate.The evolutionary process of leakage was divided into three stages(i.e.,the percolation,leakage and breakdown),which explicitly reveal the progressive hydraulic deterioration of gasketed joints.The gaskets still own partial waterproof capacity until the end of the leakage stage due to the remaining contact pressure at surface asperities.The proposed model was first verified by several sets of experimental data,based on which the determination of three key model parameters(i.e.,self-sealing slope,sealing coefficient,and expel pressure)were discussed in detail.The parametric study indicates that the waterproof capacity is significantly affected by the joint opening,offset,and the surface roughness of the gaskets.The variation in waterproof capacity with joint opening is mainly due to the nonlinearity of the gasket’s modulus and self-sealing slope.The increase in joint offset can result in a lower waterproof capacity as well as a larger leakage rate.Gasket’s surface roughness affects the percolation pressure and interfacial separation,which contributes to the long-term sealant performance.

TBM performance prediction using LSTM-based hybrid neural network model:Case study of Baimang River tunnel project in Shenzhen,China

Accurately predicting tunnel boring machine(TBM)performance is beneficial for excavation efficiency enhancement and risk miti-gation of TBM tunneling.In this paper,we develop a long short-term memory(LSTM)based hybrid intelligent model to predict two key TBM performance parameters(advance rate and cutterhead torque).The model combines the LSTM,BN,Dropout and Dense layers to process the raw data and improve the fitting quality.The features,including the ground formation properties,tunnel route cur-vature,tunnel location and TBM operational parameters,are divided into historical/real-time time-varying parameters,time-invariant parameters and historical/real-time output prediction data.The effectiveness of the proposed model is verified based on a large moni-toring database of the Baimang River Tunnel Project in Shenzhen,south China.We then discuss the influence of the prediction mode,neural network structure and time division interval length of historical data on the prediction accuracy.The significance evaluation of input features shows that the historical output prediction has the largest influence on the prediction accuracy,and the influence of ground properties is secondary.It is also found that the correlations between input features and the output prediction are coincident with their interrelationships with the ground properties and ease of TBM excavation.Finally,it is found that the prediction results are most affected by the total propulsion force followed by the rotation speed of the cutterhead.The established model can provide useful guidance for construction personnel to roughly grasp the possible TBM status from the prediction results when adjusting the operational parameters.