Journal of Structural Dynamics

A Diamond Open Access Journal for High-quality Papers in the Field of Structural Dynamics

2684-6500

 

since :
View(s): 293 (8 ULiège)
Download(s): 42 (0 ULiège)
print
print
Hadrien Postorino, Eric Monteiro, Marc Rébillat & Nazih Mechbal

Cross-structures Deep Transfer Learning through Kantorovich potentials for Lamb Waves based Structural Health Monitoring.

(Issue 2)
Article
Open Access

Attached document(s)

original pdf file

Abstract

In Lamb Waves based Structural Health Monitoring (LWSHM) of composite aeronautic structures, Deep Learning (DL) methods have proven to be promising to monitor damage using the signals collected by piezoelectric sensors (PZTs). However, those data driven algorithms are strongly problem dependent: any structural change dramatically impacts the accuracy of the predictions and the generalization of the learnt algorithms to other structures within the fleet is impossible. Transfer Learning (TL) promises to face that issue by capitalizing on the knowledge acquired on a given structure to transfer it on another from the fleet. An original TL approach based on the Optimal Transport (OT) theory is proposed here to handle this issue. OT provides a rigorous mathematical framework for TL that can be practically implemented using Input Convex Neural Networks modelling Kantorovich potentials but that has never been used for LWSHM. Using OT, the knowledge acquired on a rich LW database is transferred to poorer LW databases collected on different structures with rising structural divergences. A Structural Index (SI) is defined and used to compute the gap between those different structures and can be used to estimate a priori the necessity of the use of TL methods. The proposed OT based TL method for LWSHM manages to reduce by almost 50\% the predictions errors between numerical structures with strong differences (bias in mechanical properties and erroneous PZT position) in comparison with standard approaches. That leads to a promising approach to combine rich numerical database with poorer database in order to build robust algorithms for LWSHM of a fleet of aeronautical composite structures.

Index by keyword : Data-driven Lamb Waves SHM, CNN, Monge-Kantorovich duality, Deep Transfer Learning, Fleet monitoring

To cite this article

Hadrien Postorino, Eric Monteiro, Marc Rébillat & Nazih Mechbal, «Cross-structures Deep Transfer Learning through Kantorovich potentials for Lamb Waves based Structural Health Monitoring.», Journal of Structural Dynamics [En ligne], Issue 2, URL : https://popups.uliege.be/2684-6500/index.php?id=135.

About: Hadrien Postorino

Arts et Métiers Institute of Technology, CNAM, PIMM, HESAM University, 151 boulevard de l'Hopital, 75013, Paris, France

Call for papers

Second issue

More info