Realistic 3D simulations of the tunnelling process are increasingly required to investigate the interactions between machine-driven tunnel construction and the surrounding soil in order to provide reliable estimates of the expected settlements and associated risks of damage for existing structures, in particular in urban tunnelling projects. To accomplish the step from large-scale computational analysis to real-time predictions of expected settlements during tunnel construction, the focus of this paper is laid on the generation of a numerically efficient hybrid surrogate modelling strategy, combining Gappy proper orthogonal decomposition (GPOD) and recurrent neural networks (RNN). In this hybrid RNN-GPOD surrogate model, the RNN is employed to extrapolate the time variant settlements at several monitoring points within an investigated surface area and GPOD is utilised to predict the whole field of surface settlements based on the RNN predictions and a POD radial basis functions approximation. Both parts of the surrogate model are created based on results of finite element simulations from geotechnical and process parameters varied within the range of intervals given in the design stage of a tunnel project. In the construction stage, the hybrid surrogate model is applied for real-time reliability analyses of the mechanised tunnelling process to support the machine operator in steering the tunnel boring machine.

The risk assessment of tunneling-induced damage in buildings is a challenging task in geotechnical and structural engineering. It is important to consider the soil–structure interaction during the tunnel construction process. In this paper, finite-element (FE) simulation models of mechanized tunneling processes are combined with FE models of buildings to predict tunneling-induced damage. The soil–structure interaction is taken into account by considering the building stiffness in the tunneling process simulation model and by applying the computed foundation settlements as boundary conditions of the building model. The building damage risk is assessed by means of strains in the structural members and a corresponding category of damage is determined. Uncertainties of the geotechnical parameters and the structural parameters are quantified as random variables and intervals in the framework of polymorphic uncertainty modeling. For real-time predictions, the FE simulation models are approximated by artificial neural networks. This makes it possible to predict the structural damage risk according to scenarios of the operational tunneling process parameters in order to assist machine drivers during tunnel construction.