14:20 Thursday 7. Jul - A3B
A novel approach to damage classification based on bispectral analysis and neural network
Abstract »Damage detection and assessment by using Higher Order Statistic Analysis has proved several times to be doable and particularly reliable; indeed, Fourier transform of displacements’ third-order cumulants, also known as Bispectrum, has the advantage of being able to detect non-linearity in the dynamic response of the structural element, while being insensitive to ambient vibrations and Gaussian noise. Thus, asymmetry in the statistic distribution may be easily spotted and related to the damaged conditions, as the majority of common faults, e.g. fatigue cracks, shows bilinear effects.
In this study, firstly a novel approach to damage localisation, resorting to Neural Networks fed with bispectral data, is presented. Afterwards, NNs’ parameters and architecture, as well as several different selections of input data, are investigated in order to maximise its forecast abilities. To validate the introduced approach, a simple finite element model of a 4-meters-long cantilever beam has been built and data have been generated via FE nonlinear analyses performed on it. This model is intended to be a first concept, as generic as possible, of various beam-like structural elements.
Authors
Civera, Marco*Civera, Marco*
s163502@studenti.polito.it
+447576948188
Biography:
M.Sc. Student at Politecnico di Torino, visiting student at Cranfield University. Master thesis
Affiliation:
Polytechnic of Turin
Department of Structural, Building and Geotechnical engineering
10129 Turin
ItalyZanotti Fragonara, Luca**Zanotti Fragonara, Luca**
l.zanottifragonara@cranfield.ac.uk
Affiliation:
Cranfield University
School of Aerospace, Transportation and Manufacturing
MK43 0AL Cranfield
United KingdomSurace, CeciliaSurace, Cecilia
cecilia.surace@polito.it
011090
Affiliation:
Politecnico di Torino
Department of Structural, Building and Geotechnical engineering
10129 Turin
Italy
+390110904904*Contact**Speaker
FOREWORD
PROGRAM
SESSIONS
POSTERS
AUTHORS
EXHIBITORS
FLOORPLANS
SPONSORS
NEWS
FAVORITES
SEARCH 
MORE
OTHER APPS
HELP
Neural Networks and AI approaches
Paper
