Neural Network-Based Prediction Model for the Stability of Unlined Elliptical Tunnels in Cohesive-Frictional Soils

• Published in: Buildings
• Main Authors: Sayan Sirimontree, Suraparb Keawsawasvong, Chayut Ngamkhanong, Sorawit Seehavong, Kongtawan Sangjinda, Thira Jearsiripongkul, Chanachai Thongchom, Peem Nuaklong
• Format: Article
• Language: English
• Published: MDPI AG 2022-04-01
• Subjects: tunnel stability; finite element; cohesive-frictional soils; underground opening; limit analysis; artificial neural network
• Online Access: https://www.mdpi.com/2075-5309/12/4/444

The scheme for accurate and reliable predictions of tunnel stability based on an artificial aeural network (ANN) is presented in this study. Plastic solutions of the stability of unlined elliptical tunnels in sands are first derived by using numerical upper-bound (UB) and lower-bound (LB) finite element limit analysis (FELA). These numerical solutions are later used as the training dataset for an ANN model. Note that there are four input dimensionless parameters, including the dimensionless overburden factor <i>γD/c′</i>, the cover–depth ratio <i>C/D</i>, the width–depth ratio <i>B/D</i>, and the soil friction angle <i>ϕ.</i> The impacts of these input dimensionless parameters on the stability factor <i>σ_s</i>/<i>c′</i> of the stability of shallow elliptical tunnels in sands are comprehensively examined. Some failure mechanisms are carried out to demonstrate the effects of all input parameters. The solutions will reliably and accurately provide a safety assessment of shallow elliptical tunnels.