Digitalization and defects analysis for the maintenance of mechanized tunnels

The planning and the management of existing infrastructures (and tunnels) is already a central challenge for industrialized countries in order to manage heritage and strategic infrastructures ensuring a sustainable and resilient asset. In the last years, a larger amount of the tunnel industry follows the lead of the mechanized excavation method and the issue for the management and the maintenance of this particular kind of underground structures increases through the years. ETS srl has carried out the diagnostic and maintenance of existing mechanized tunnels through an innovative multi-dimensional survey system (ARCHITA), coupled with a deep study of the tunnel structure, and a new ongoing approach for the Management and Identification of the Risk for Existing Tunnels (MIRET). ARCHITA surveys the geometrical and structural conditions of the tunnel without frequent and long stops of the traffic. In the MIRET approach, identification of tunnel hazard can be performed by combining advanced deep learning approaches (U-Net based Convolutional Neural Networks) and innovative photogrammetric algorithms (in the frame of DIC-Digital Image Correlation) for automatic detection and measurement of defects (in this paper water defects).