Stability Evaluations of Unlined Horseshoe Tunnels Based on Extreme Learning Neural Network

This paper presents an Artificial Neural Network (ANN)-based approach for predicting tunnel stability that is both dependable and accurate. Numerical solutions to the instability of unlined horseshoe tunnels in cohesive-frictional soils are established, primarily by employing numerical upper bound (UB) lower (LB) finite element limit analysis (FELA). The training dataset ANN model made up these solutions. Four dimensionless parameters required parametric analyses, namely overburden factor ?D/c?, cover-depth ratio C/D, width-depth B/D, soil friction angle ?. influence on explored illustrated terms a design chart. Moreover, failure mechanisms shallow influenced four also provided. Therefore, current solution, based FELA models, presented this paper, allowing efficient accurate establishment evaluation optimum surcharge loading practice.