Deep learning algorithms for delaminations identification on composite panels by wave propagation signal analysis

E. Monaco; F. Ricci; N. D. Boffa

doi:10.1117/12.2660094

25 April 2023 Deep learning algorithms for delaminations identification on composite panels by wave propagation signal analysis

E. Monaco, F. Ricci, N. D. Boffa

Author Affiliations +

Proceedings Volume 12488, Health Monitoring of Structural and Biological Systems XVII; 124881D (2023) https://doi.org/10.1117/12.2660094
Event: SPIE Smart Structures + Nondestructive Evaluation, 2023, Long Beach, California, United States

Abstract

Performances are a key concern in aerospace vehicles, requiring safer structures with as little consumption as possible. Composite materials replaced aluminum alloys even in primary structures to achieve higher performances with lighter components. However, random events such as low-velocity impacts may induce damages that are typically more dangerous and mostly not visible than in metals. Structural health monitoring deals mainly with sensorised structures providing signals related to their “health status” aiming at lower maintenance costs and weights of aircrafts. Much effort has been spent during last years on analysis techniques for evaluating metrics correlated to damages’ existence, location and extensions from signals provided by the sensors networks. Deep learning techniques can be a very powerful instrument for signals patterns reconstruction and selection but require the availability of consistent amount of both healthy and damaged structural configuration experimental datasets, with high materials and testing costs, or data reproduced by validated numerical simulations. Within this work will be presented two supervised deep neural networks trained by experimental measurements as well as numerically generated strain propagation signals. The final scope is the detection of delaminations into composites plates for aerospace employ. The first type is based directly on the processing trough a convolutional autoencoder of the rough signals of both healthy and damaged structural configurations. The second approach is instead based on the production of images trough signal processing techniques and on employ of an image recognition convolutional network. Both networks are trained and tested on combinations of experimental and numerical data.

Conference Presentation

Citation Download Citation

E. Monaco, F. Ricci, and N. D. Boffa "Deep learning algorithms for delaminations identification on composite panels by wave propagation signal analysis", Proc. SPIE 12488, Health Monitoring of Structural and Biological Systems XVII, 124881D (25 April 2023); https://doi.org/10.1117/12.2660094

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available