Abstract

The seismic forces must be properly defined as required by European geotechnical design Codes. They are dependent from the morphological and stratigraphic characteristics that determine the local seismic response. The local seismic response can be evaluated using a simplified approach which is based on the classification of the subsoil according to the values of the shear wave propagation speed Vs. In the present case study, to complete the quay of the Rovigo Interporto (facing the River Canal Bianco), where a not negligible load is planned to be applied (50 kPa), has been designed a foundation with a large slab founded with not pre-casted reinforced concrete piles diameter 350 mm, drilled without removing soil, with vibrating casing, for settlement reduction (rafted piles as settlement reducers), on an area of approximately 6000 m2. The subsoil in this area, from geological and geotechnical point of view, is very variable and with layers of soft clay and loose sand or silt, with no presence of a dense and uniform sand layer where to transfer loads to. Moreover, the geotechnical model was complicated because of the presence of an old diaphragm wall with anchors (whose projection in plant covers around half of area) and was designed a large underground basin for hydraulic invariance. For this reason, an extensive campaign of CPTU and DMT tests, together with boreholes, sampling and laboratory tests was carried out in this area, which allowed a detailed characterization of the subsoil. Through direct measurement of seismic micro-tremors, carried out before and after the installation of the piles, has been evaluated the modification of the resonance frequency of the site, and modification of the propagation speed of the shear waves Vs induced by the slab over rafted piles over the entire area.

Abstract

Obtaining soil parameters through laboratory tests and solving the governing equations that describe soil settlement can be time-consuming, making immediate on-site predictions of soil settlement challenging. In-situ testing provides a more efficient approach to obtain soil parameters than laboratory tests. Data from the Piezocone penetration test (CPTu) can be used for on-the-spot interpretation of soil mechanical parameters, which can then be incorporated into the governing equations for soil settlement calculation. Physics Informed Neural Networks (PINNs) algorithm uses automatic differentiation method to directly embed partial differential equations (PDEs) into a deep learning neural network and provides solution for these PDEs in a cost-effective manner compared to traditional numerical methods. In this paper, a framework integrating data from CPTu and PINNs to predict soil settlement is proposed and evaluated through comparison with numerical simulations from Finite Element Methods (FEMs). Results show that the framework gave a reasonably good agreement with the FEMs benchmark while substantially reduced the computation time. This method allows for immediate on-site prediction of soil settlement during site investigations, thus better guiding surveying and construction activities.