Ground Movements Prediction in Shield-Driven Tunnels using Gene Expression Programming

Abstract

Introduction: The increase in population and traffic in metropolitan areas has led to the development of underground transportation spaces. Therefore, the estimation of the surface settlement caused by the construction of underground structures should be accurately considered. Several methods have been developed to predict tunneling-induced surface settlement. Among these methods, artificial intelligence-based methods have received much attention in recent years. This paper is aimed to develop a model based on Gene Expression Programming (GEP) algorithm to predict surface settlement induced by mechanized tunneling. Methods: For this purpose, Tehran Metro Line 6 was simulated numerically to investigate the effects of different parameters on the surface settlement, and 85 datasets were prepared from numerical simulations. Subsequently, several GEP models were implemented using the obtained datasets from numerical simulations and finally, a model with 30 chromosomes and 3 genes was selected as the optimum model. Results: A comparison was made between obtained maximum surface settlements by the proposed GEP model and numerical simulation. The results demonstrated that the proposed model could predict surface settlement induced by mechanized tunneling with a high degree of accuracy. Conclusion: Finally, a mathematical equation was derived from the proposed GEP model, which can be easily used for surface settlement prediction.

Interaction of Segmental Tunnel Linings and Dip-Slip Faults—Tabriz Subway Tunnels

“…The equivalent stiffness in a zone in the normal direction is equal to Equation ( 5) [44]: An appropriate constitutive model for the soil is crucial for the numerical modeling of a tunneling process and, consequently, for the correct prediction of lining loads. It is important to note that constant stiffness would not be an appropriate method of approximating surface settlements for all levels of shear strain [40,41]. The plastic hardening constitutive model is characterized by a hyperbolic stress-strain relationship in drained axial compression (while unloading/reloading is elastic) and stress dependency, defined by a power law.…”

Soft computing-based models for the prediction of masonry compressive strength

“…In the context of soft computing techniques, the individuals in the population are assumed to be computer programs (Koza 1992). Genetic programming techniques operate by randomly generating a population of computer programs (Ramesh et al 2020). Mutation, crossover, and reproduction take place during computation.…”

Risk Assessment of Building Damage Induced by Tunnelling Through a Gene Expression Programming Model

“…Among artificial intelligence methods, gene expression programming (GEP) has the advantage that being able to derive a mathematical equation between input and output data. The GEP has been applied in several geotechnical engineering problems recently (Armaghani et al 2018;Hajihassani et al 2019b;Ramesh et al 2020;Jalal et al 2021;Li et al 2021).…”