Estimating maximum surface settlement due to EPBM tunneling by Numerical-Intelligent approach - A case study: Tehran subway line 7

Ground settlement due to excavation of shallow tunnels is a common phenomenon. To control the settlement, one should be able to predict it, and based on it he may consider required preventions and protections. There are different methods for predicting settlement, each having some strengths and weaknesses. The main weakness of these methods is that they do not consider enough effective parameters on the settlement. The numerical methods, contrary to the empirical and analytical methods, take into account the effects of a larger number of parameters. However, ideal selection of many parameters is associated with ambiguity and difficulty and is time consuming. To overcome these issues, the intelligent methods are incorporated which are appropriate tools. The aim of this paper is to present a numerical-intelligent model for prediction of maximum surface settlement (S-max). At first, a section of Tehran subway line 7 was modeled using the finite difference method (FDM). Then a dataset including 100 S-max values were prepared for creating the intelligent model. Among the intelligent methods, the gene expression programming (GEP) method was selected to represent the mathematical equation and the built numerical-intelligent model explained a proper performance. The determination coefficient, R-2, for both the training and testing phases was 0.976 and 0.931, respectively. At the end, the derived mathematical equation from the GEP model was prepared using the visual basic (VB) in the form of predictor software. According to accuracy of the prediction results, the presented equation and software are reliable and suitable as an alternative for the numerical modelling.