Artificial neural networks for predicting the maximum surface settlement induced by EPB-TBM : the Algiers metro case

Abstract

This thesis presents a methodology to correlate ground surface movements (settlement) with tunnel boring machine (TBM) operation parameters , Tunnel geometry and Geotechnical pa-rameters using an Artificial neural network model to predict maximum ground surface settle-ment. Data analyzed were selected from the excavation of the extension of Algiers subway line “1” (El-Harrach to H.B. Int. Airport) tunnel, which was performed by a shield TBM. The surface settlements observed along the entire tunnel section of the project (Contract 1-9) were satisfactorily reproduced by the proposed ANN model. A dedicated pre-processing procedure was necessary to enhance the model’s predictive capability, followed by a sensitivity analysis to assess the individual contribution of each feature