KEYWORD |
Analysis of Experimental Data from Destructive Testing of Ordinary and Prestressed Concrete Beams: Correlation of Dynamic Parameters and Acoustic Emissions using Artificial Intelligence
keywords ACOUSTIC EMISSIONS, ARTIFICIAL INTELLIGENCE, DYNAMIC IDENTIFICATION, MACHINE LEARNING, PRESTRESSED CONCRETE, STRUCTURAL HEALTH MONITORING
Reference persons MARCO CIVERA
Thesis type EXPERIMENTAL AND MODELING
Description The aim of this thesis is the analysis of experimental data from destructive bending tests of various ordinary and prestressed reinforced concrete beams.
Specifically, the data consists of dynamic identifications (modal parameters), static monitoring data (displacements and deflections), acoustic emissions and photogrammetric image data (DIC).
The student's objective will be to correlate the amount of different data listed above with the residual strength of the beam using artificial intelligence and machine learning algorithms.
The thesis is part of an active collaboration with the University of Rome La Sapienza, ANAS, and other private and public actors within the Italian Centro Nazionale Mobilità Sostenibile (CN MOST).
Required skills Good knowledge of Matlab
Notes Average mark at least >= 27/30
Deadline 02/01/2026
PROPONI LA TUA CANDIDATURA