Transfer Learning to close the gap between experimental and numerical data
Communication sans acte
The deployment of Deep Learning (DL) strategies is particularly advantageous in Structural Health Monitoring (SHM) based of lamb Wave (LW) propagation due to the high quantity of data collected by the network of piezoelectric transducers (PZT) during all the life cycle of the composite structure. However, such strategies rely on large training databases, difficult to collect experimentally. The use of numerical simulations faces that issue, but the modelsnever fit perfectly to the real structures, leading to error of diagnostic. We propose here to use Transfer Learning (TL) approaches to reduce the predictions errors of a Convolutional Neural Network (CNN) trained with numerical data. The network predicts the size and the position of a damage on a composite plate equipped with PZT. It is trained on a large source database composed of different damage scenarios on a composite plate. A second smaller target database is generated with small variations on the mechanic properties and PZT positions to simulate manufacturing uncertainties. Those uncertainties lead to prediction errors of the CNN. A Domain Adaptation (DA) based on Optimal Transport (OT) is used to project the target data on the source domain and therefore reduces the predictions error of the CNN. These TL approach should allow us to close the gap between experimental and numerical data.
Files in this item
Showing items related by title, author, creator and subject.
Towards an industrial deployment of PZT based SHM processes: A dedicated metamodel for Lamb wave propagation Communication avec actePOSTORINO, Hadrien; REBILLAT, Marc; MONTEIRO, Eric; MECHBAL, Nazih (2020)Numerical simulations of Structural Health Monitoring processes based on wave propagation can be very costly in terms of computation time, especially for complex aeronautic composite structures, and therefore strongly ...
Cross-structures Deep Transfer Learning through Kantorovich potentials for Lamb Waves based Structural Health Monitoring Article dans une revue avec comité de lecturePOSTORINO, Hadrien; MONTEIRO, Eric; REBILLAT, Marc; MECHBAL, Nazih (University of Liege library ( Belgium), 2023-04)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 ...
Experimental Damage Localization and Quantification with a Numerically Trained Convolutional Neural Network Communication avec actePOSTORINO, Hadrien; MONTEIRO, Eric; REBILLAT, Marc; MECHBAL, Nazih (Springer International Publishing, 2022-06)Structural Health Monitoring (SHM) based on Lamb wave propagation is a promising technology to optimize maintenance costs, enlarge service life and improve safety of aircrafts. A large quantity of data is collected during ...
Communication avec acteSCHEFFLER, Mattias; MECHBAL, Nazih; REBILLAT, Marc; MONTEIRO, Eric; BARABINO, Nicolas (IEEE, 2019)This paper describes an original methodology to operate a new nonlinear vibrating membrane pump, actuated by a moving magnet actuator without the use of a motion sensor, in the scope of cardiac assistance. A nonlinear ...
Communication avec acteLI, Xixi; MONTEIRO, ERIC; REBILLAT, Marc; GUSKOV, Mikhail; MECHBAL, Nazih (A. Benjeddou, N. Mechbal and J.F. Deü, 2019)One of the most important issues in engineering is the monitoring and the early detection of structural damages to prevent catastrophic failures. This process is referred to as Structural Health Monitoring and is expected ...