Numerical Simulation of Non-Stationary Parameter Creep Large Deformation Mechanism of Deep Soft Rock Tunnel

Section: Research On Deep Rock Mass Engineeringmentioning

confidence: 99%

Deep Rock Mass Engineering: Excavation, Monitoring, and Control

Fang

2022

“…XGBoost is excellent in parallel computing efficiency, missing value processing, control overfitting, and prediction generalization ability. The specific algorithm process of XGBoost and its calculation steps are detailed in reference [28]. The steps and key technologies of XGBoost algorithm are as follows [26]:…”

Section: Extreme Gradient Boosting (Xgboost)mentioning

confidence: 99%

“…Therefore, it is selected as the method used for tuning the hyperparameter of the XGBoost-based surrogate model. The specific hyperparameter tuning process for of XGBoost-based surrogate model was depicted in reference [28].…”

Section: Nsga-iii-xgboost-based Mcs Reliability Analysismentioning

confidence: 99%

NSGA–III–XGBoost-Based Stochastic Reliability Analysis of Deep Soft Rock Tunnel

Xu,

Sun,

Rui

2024

Self Cite

How to evaluate the reliability of deep soft rock tunnels under high stress is a very important problem to be solved. In this paper, we proposed a practical stochastic reliability method based on the third-generation non-dominated sorting genetic algorithm (NSGA–III) and eXtreme Gradient Boosting (XGBoost). The proposed method used the Latin hypercube sampling method to generate the dataset samples of geo-mechanical parameters and adopted XGBoost to establish the model of the nonlinear relationship between displacements and surrounding rock mechanical parameters. And NSGA–III was used to optimize the surrogate model hyper-parameters. Finally, the failure probability was computed by the optimized surrogate model. The proposed approach was firstly implemented in the analysis of a horseshoe-shaped highway tunnel to illustrate the efficiency of the approach. Then, in comparison to the support vector regression method and the back propagation neural network method, the feasibility, validity and advantages of XGBoost were demonstrated for practical problems. Using XGBoost to achieve Monte Carlo simulation, a surrogate solution can be provided for numerical simulation analysis to overcome the time-consuming reliability evaluation of initial support structures in soft rock tunnels. The proposed method can evaluate quickly the large deformation disaster risks of non-circular deep soft rock tunnels.

“…If its constitutive model represents the surrounding rock, then its mechanical parameters for zone i are updated with the updated mechanical parameters from step 3 through the zone command (zone property), if not, no mechanical parameters of zone i are updated. (6) Step 6: Executing step 2~step 5 for the next zone (i + 1). Until all zones of the finite element model are executing step 2~step 5, exiting of the traversal loop environment and traversal loop discriminant update procedure is completed.…”

Section: Improved Iteration Calculation Process Of Flacmentioning

confidence: 99%

“…To effectively address the large deformation problem of tunnels, there are two fundamental problems to solve in advance: the confining pressure influence on the soft rock mechanical characteristics and the displacement field prediction and evaluation of surrounding rock considering the confining pressure influence [4,5]. These two problems are the current research hotspots, which have significant meaning for the large deformation problem of tunnels [6,7]. Therefore, numerous scholars have focused on the abovementioned problems and have had many achievements in recent decades.…”

Section: Introductionmentioning

confidence: 99%

Numerical Simulation Method for Tunnel Excavation Considering Mechanical Characteristic Variation of Soft Rock with the Confining Pressure Influence

Dong

Zhang

Zhu³

et al. 2023

The accurate prediction and evaluation of stress and displacement fields of surrounding rock is the fundamental premise for the deformation control of soft rock tunnels under high geo-stress condition. However, due to the complicated mechanical characteristics of soft rock with confining pressure influence, the current numerical simulation method usually regards the mechanical parameters of surrounding rock as constant and ignores the variation of these parameters in the simulation process, which leads to results that cannot accurately reflect the mechanical behavior of surrounding rock. Therefore, this paper firstly investigates the effect of confining pressure on deformation and strength parameters for soft rock and proposes corresponding variable models for mechanical parameters with the confining pressure influence. Secondly, a transversal loop discriminant update procedure is proposed and introduced into the iteration calculation process of FLAC3D, thus forming an improved numerical simulation method. This improved method can integrally consider the mechanical parameter variation of surrounding rock with variable confining pressure and realize the automatic update for such a parameter with its variable stress state. Finally, as an application example, an improved expression of longitudinal deformation profile (LDP) for tunnels considering the confining pressure influence is proposed based on numerous simulation results for a soft rock tunnel obtained by this proposed method.