Application of Artificial Neural Networks for Predicting the Stability of Rectangular Tunnels in Hoek–Brown Rock Masses

Suraparb Keawsawasvong,Chayut Ngamkhanong,Sorawit Seehavong

doi:10.3389/fbuil.2022.837745

Suraparb Keawsawasvong, Chayut Ngamkhanong + Show 1 more

Open Access

https://doi.org/10.3389/fbuil.2022.837745

Copy DOI

Abstract

An artificial neural network (ANN) model for predicting the stability of rectangular tunnels in rock masses based on the Hoek–Brown (HB) failure criterion is presented in this study. Since the safety assessment of the tunnel stability is one critical issue for civil engineers during the construction, it is very important to develop a reliable and accurate stability analysis of such problems. The finite element limit analysis (FELA) with the HB failure criterion is used to develop the numerical upper and lower bound solutions of the problem of rectangular tunnels in rock masses. A novel machine learning-aided prediction of this problem is then developed based on the datasets of the numerical bound solutions obtained from the FELA. The inputs consist of six dimensionless parameters including the cover-depth ratio of tunnels, the width ratio of tunnels, the normalized uniaxial compressive strength, the geological strength index, the mi parameter, and the degree of disturbance of rock masses. The results show that the optimal ANN models provide very great accuracy in predicting the stability of the rectangular tunnels based on the HB failure criterion. The solutions will provide a prompt assessment of tunnel stability in rock masses for geotechnical engineers during the construction of rock tunnels.

Highlights

Tunnel safety has been a classic issue for geotechnical engineers during the processes of both construction and operation
To the authors’ knowledge, this study is the first to establish a machine learning aided design for predicting the stability factor of the rectangular tunnel that is located in a rock mass following the Hoek–Brown (HB) failure criterion
The stability factor of the problem is investigated in terms of six dimensionless parameters including the width ratio, cover depth ratio, degree of disturbance, geological strength index, material constant related to the frictional strength, and normalized uniaxial compressive strength

Summary

Introduction

Tunnel safety has been a classic issue for geotechnical engineers during the processes of both construction and operation. It is very important to ensure the stability to prevent a collapse inside the tunnel during the construction process. To assess the stability of rock masses during the tunnel construction by an open-face conventional tunneling or a tunneling boring machine, the failure criterion for capturing the collapse of rocks is required to accurately compute the tunnel stability in rocks. The Hoek–Brown (HB) failure criterion is one of the famous criteria for capturing the failure behaviors of rock masses. The first version of this failure criterion was introduced by Hoek and Brown (1980) in the 1980s by employing the curve-fitting of triaxial test data of intact and jointed rocks. In 2002, Hoek et al (2002) updated the old version by Prediction of Rectangular Tunnel Stability accounting for the effect of highly fractured properties. A brief history and the development of this failure criterion can be found in the study by Hoek (Hoek, 2004; Hoek, 2007)

Objectives

Methods

Results

Conclusion