Simulation of 3D Effect of Excavation Face Advancement Using a Neural Network Trained by Numerical Models

摘要

By the use of convergence-confinement method, three-dimensional problem of tunnel excavation is simulatedrnby an equivalent two-dimensional plane strain analysis. In this method, the evaluation of the convergencernoccurred before the time support starts interacting with ground is the critical point. The aim of this paper is tornassess this convergence for deep tunnels excavated in elastoplastic continuum and anisotropic stressrnconditions with the aid of a neural network approach. Numerical 3D FE models supply data sets required forrnthe training process of the network. About 170 circular tunnels between 100 and 1000 meters deep, excavatedrnin fair to good rock masses (according to RMR classification), are analyzed. The trained network will berncapable to evaluate the convergence values for different distances to the excavation face with regard to rockrnspecifications and stress conditions and is used for a sensitivity analysis of the parameters involved.