Neuronet prediction of tunnelling induced settlements

Abstract

Recent proliferation of tunnels in urban congested areas necessitates the continual updating of subsidence prediction techniques using settlement records of tunnel monitoring programs. This paper concerns with characterization of the surface settlement trough associated with soft ground tunneling through a new model based on the Artificial Neural Networks (ANN). The key element of the employed paradigm is the novel combined topology of the information processing system to cover the different sizes of the learning database. The neural network has been trained using the monitoring and geotechnical data of many tunneling projects in Egypt and abroad. The training database covers a wide spectrum of construction techniques, geotechnical data and the tunnel geometrical data. The main benefit of this approach is to avoid the computational complexities of satisfying all the constraints of constructional details, geotechnical conditions and tunnel configurations in order to obtain a rigorous assessment of settlements associated with tunneling. The proposed model was practiced in analyzing the present and future status of Hydroshield tunneling in Greater Cairo.