Multi-line overlapping shield tunnels have a complicated layout in the underground space, and the interaction mechanism between tunnels is very complicated. Based on the construction formation of multi-line overlapped shield tunnel with short-distance up- and down-crossing, indoor model tests were conducted to analyze ground settlement (caused by excavation unloading and stratum loss) and the longitudinal deformation law of existing tunnels based on the drainage method, according to the characteristics and control requirements of the short-distance construction of shield tunnels. The results show that as long as the construction strategy of first-down and then-up crossing is adopted, no sudden change in ground settlement would occur. Furthermore, neither the changes in transient settlements nor the final ground settlement would be too large, which is different from the strategy of first-up and then-down crossing; the first-up and then-down crossing strategy generally increases the curvature of the deformation curve of the existing tunnel, and the deformation of the existing tunnel will cause obvious repeated vibrations. This provides theoretical guidance for the design and construction of multi-line overlapped tunnels.

In order to effectively predict the dynamic displacement and disaster, according to the analysis of the influencing parameters affecting the deformation of a subway foundation pit supported by piles (walls), the rough set attribute reduction method (RSARM) and the average influence value algorithm (AIVA) are used to simplify the influencing factors of foundation pit deformation. Those simplified factors are taken as the input of the ELM, with the output being the displacement of the foundation pit. Finally, the IPM of foundation pit displacement derived from the ELM is obtained, which is finally used for engineering practice. The results show that it is feasible to simplify the influencing factors of the deformation of the foundation pit by RSARM and AIVA. The proposed IPM of foundation pit displacement has high accuracy and good generalization ability, which can be used for the deformation prediction.