Numerical analysis of the influence of a river on tunnelling-induced ground deformation in soft soil

When tunnels are constructed in coastal cities,they will inevitably undercross a river.Exploring the influence of rivers on tunnelling-induced deformation in costal soft soil is of great significance for controlling excessive settlement and protecting surrounding buildings.This paper presents a case study of twin tunnels undercrossing a river in soft soil in Hangzhou,China.The soft soil of Hangzhou refers to cohesive soil in a soft plastic or fluid plastic state with high natural water content,high compressibility,low bearing capacity,and low shear strength.Considering the influence of the river,the research region was divided into two parts,inside and outside the river-affected area,based on monitoring data of the Zizhi Tunnel.The development law of surface settlement is divided into three stages.In the first and second stages,the surface settlement within and outside the river-affected area showed a similar trend:the settlement increased and the growth rate of settlement in the second stage was smaller within the river-affected area.In the third stage,the surface settlement continued to increase within the river-affected area,while it converged outside the river-affected area.Within the river-affected area,there was an asynchronization of the sinking rate and stability of vault settlements and surface settlements.A numerical model was established by simulating different reinforcements of the tunnel.The numerical model revealed that the ground movement is influenced by the distribution and amount of the excess pore water pressure.The excess pore pressure was concentrated mostly in the range of 1.0H_(t)-3.0H_(t)(H_(t) is the tunnel height)before the tunnel face,especially within the river-affected area.Inside the river-affected area,the dissipation of excess pore water pressure needs more time,leading to slow stabilization of surface settlement.When undercrossing a river,a cofferdam is necessary to reduce excessive ground deformation by dispersing the distribution of excess pore water pressure.

Comprehensive evaluation of machine learning algorithms applied to TBM performance prediction

To date,the accurate prediction of tunnel boring machine(TBM)performance remains a considerable challenge owing to the complex interactions between the TBM and ground.Using evolutionary polynomial regression(EPR)and random forest(RF),this study devel-ops two novel prediction models for TBM performance.Both models can predict the TBM penetration rate and field penetration index as outputs with four input parameters:the uniaxial compressive strength,intact rock brittleness index,distance between planes of weakness,and angle between the tunnel axis and planes of weakness(a).First,the performances of both EPR-and RF-based models are examined by comparison with the conventional numerical regression method(i.e.,multivariate linear regression).Subsequently,the performances of the RF-and EPR-based models are further investigated and compared,including the model robustness for unknown datasets,interior relationships between input and output parameters,and variable importance.The results indicate that the RF-based model has greater prediction accuracy,particularly in identifying outliers,whereas the EPR-based model is more convenient to use by field engineers owing to its explicit expression.Both EPR-and RF-based models can accurately identify the relationships between the input and output param-eters.This ensures their excellent generalization ability and high prediction accuracy on unknown datasets.