Prediction of TBM jamming risk in squeezing grounds using Bayesian and artificial neural networks

作     者：Rohola Hasanpour Jamal Rostami Jürgen Schmitt Yilmaz Ozcelik Babak Sohrabian Rohola Hasanpour;Jamal Rostami;Jürgen Schmitt;Yilmaz Ozcelik;Babak Sohrabian

作者机构：Institute for Tunneling and Construction ManagementRuhr-University BochumBochumGermany Department of Mining EngineeringColorado School of MinesGoldenUSA Department of Civil EngineeringDarmstadt University of Applied ScienceDarmstadtGermany Department of Mining EngineeringHacettepe UniversityAnkaraTurkey Faculty of Mining and Metallurgical EngineeringUrmia University of TechnologyUrmiaIran 

出 版 物：《Journal of Rock Mechanics and Geotechnical Engineering》 (岩石力学与岩土工程学报（英文版）)

年 卷 期：2020年第12卷第1期

页      面：21-31页

核心收录：

学科分类：081406[工学-桥梁与隧道工程] 08[工学] 0814[工学-土木工程] 082301[工学-道路与铁道工程] 0823[工学-交通运输工程] 

基　　金：Alexander von Humboldt-Stiftung 

主　　题：Bayesian network(BN) Artificial neural network(ANN) Shielded tunnel boring machine(TBM) Jamming risk Numerical simulation Squeezing ground 

摘      要：This study presents an application of artificial neural network(ANN)and Bayesian network(BN)for evaluation of jamming risk of the shielded tunnel boring machines(TBMs)in adverse ground conditions such as squeezing *** analysis is based on database of tunneling cases by numerical modeling to evaluate the ground convergence and possibility of machine *** results of initial numerical analysis were verified in comparison with some case studies.A dataset was established by performing additional numerical modeling of various scenarios based on variation of the most critical parameters affecting shield *** includes compressive strength and deformation modulus of rock mass,tunnel radius,shield length,shield thickness,in situ stresses,depth of over-excavation,and skin friction between shield and *** the dataset,an ANN was trained to predict the contact pressures from a series of ground properties and machine ***,the continuous and discretized BNs were used to analyze the risk of shield *** results of these two different BN methods are compared to the field observations and summarized in this *** developed risk models can estimate the required thrust force in both *** BN models can also be used in the cases with incomplete geological and geomechanical properties.