European Commission logo
English English
CORDIS - EU research results
CORDIS

A novel physics-based methodology for the seismic analysis of retaining structures leveraging machine learning techniques

Project description

A closer look at soil–structure interactions during seismic shaking

A structure’s seismic response depends on several factors – from its height to the type of ground on which it sits. Soil–structure interaction is important and a factor to consider when designing or retrofitting a building. With this in mind, the EU-funded ReStructure 2.0 project will develop a novel framework based on soil–structure interaction principles, recognising the relative displacement between wall and retained soil as the driving factor in the seismic response of the wall–soil system. Based on the combination of computational simulations, experimental and field data, relational databases and machine learning techniques, the project’s findings will be useful to ensure the design process is more sustainable, affordable and green.

Objective

The standard seismic design of retaining structures is based on a century-old theory, that does not account for the actual physical behavior of soil-structure systems. This theory unrealistically assumes that the seismic earth pressure increment is proportional to surface acceleration. Methods based on this theory often lead to conservative design of retaining structures that causes an unsustainable consumption of resources without any benefits on the performance and safety of the construction. Such design approach is against the principles of the European Green Deal that identified the need of cleaner constructions in the Building and Renovation policy area. The main goal of ReStructure 2.0 is to develop a novel physics-based framework based on soil-structure interaction principles, recognizing the relative displacement between wall and retained soil as the driving factor in the seismic response of wall-soil system. The proposed method accounts for soil inhomogeneity and non-linearity, wall flexibility, mass of the wall, and different boundary condition at base and top of the wall. This more adequate design approach can lead to a significant reduction of the resources used during the construction, making the process more sustainable, affordable, and green. This novel approach is based on the combination of computational simulations, experimental and field data, relational databases, and machine learning techniques. Two distinct solutions will be developed: (i) complete frequency-dependent elastodynamic approach, and (ii) simplified single-frequency method. ReStructure 2.0 is tailored around my expertise and profile to give me the opportunity to reach the maturity needed to move forward with my career. This fellowship will allow me to: (i) capitalize on my unique skillset matured in years of international collaborations, (ii) bring back to the EU innovative approaches and methodologies that I developed in the US, and (iii) grow as a researcher, teacher, and mentor.

Coordinator

UNIVERSITA DELLA CALABRIA
Net EU contribution
€ 183 473,28
Address
VIA PIETRO BUCCI 7/11/B
87036 Arcavacata Di Rende
Italy

See on map

Region
Sud Calabria Cosenza
Activity type
Higher or Secondary Education Establishments
Links
Total cost
€ 183 473,28