Damage detection in an aluminum plate through a phi-OTDR sensor and support vector machines

R. Zahoor; E. Catalano; R. Vallifuoco; L. Zeni; A. Minardo

doi:10.1117/12.2678095

23 May 2023 Damage detection in an aluminum plate through a phi-OTDR sensor and support vector machines

R. Zahoor, E. Catalano, R. Vallifuoco, L. Zeni, A. Minardo

Proceedings Volume 12643, European Workshop on Optical Fibre Sensors (EWOFS 2023); 126432B (2023) https://doi.org/10.1117/12.2678095
Event: European Workshop on Optical Fibre Sensors (EWOFS 2023), 2023, Mons, Belgium

Abstract

In this paper, we make use of a phase-sensitive time domain reflectometry (phi-OTDR) sensor with 60-cm spatial resolution to detect the Lamb waves generated by a piezo-ceramic actuator in an aluminum plate. Furthermore, a machine learning algorithm based on Support Vector Machine (SVM) classifiers was employed for damage localization. We show that SVMs are able to identify the characteristics in Lamb wave signals that may be linked to damage location. This study makes full use of the rich information provided by the phi-OTDR sensor, extracting damaged data from diverse damage spots. The results indicate that the proposed technique has the potential to identify and locate damages in thin-plate structures.

Citation Download Citation

R. Zahoor, E. Catalano, R. Vallifuoco, L. Zeni, and A. Minardo "Damage detection in an aluminum plate through a phi-OTDR sensor and support vector machines", Proc. SPIE 12643, European Workshop on Optical Fibre Sensors (EWOFS 2023), 126432B (23 May 2023); https://doi.org/10.1117/12.2678095

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