This work aims at determining the location of low speed impact events on thin aluminium panels, specifically designed to be used on typical aircraft fuselage and wing panels, by processing the acoustic emission signals. The detection principle is based on the propagation of the first antisymmetric lamb wave (A0 mode) in the panel on which four PZT sensors are bonded to receive the signals. The impact location is assessed with the use of a supervised machine learning algorithm that is based on linear regression, appropriately designated to post-process the acquired signals. Some experimental cases are reported in order to investigate the optimal kind and amount of training data to improve the performance of the algorithm and therefore the accuracy of the impact location estimation.

Machine Learning regression models diagnosis for structural health monitoring

G. Petrone;A. Casaburo;S. De Rosa
2021

Abstract

This work aims at determining the location of low speed impact events on thin aluminium panels, specifically designed to be used on typical aircraft fuselage and wing panels, by processing the acoustic emission signals. The detection principle is based on the propagation of the first antisymmetric lamb wave (A0 mode) in the panel on which four PZT sensors are bonded to receive the signals. The impact location is assessed with the use of a supervised machine learning algorithm that is based on linear regression, appropriately designated to post-process the acquired signals. Some experimental cases are reported in order to investigate the optimal kind and amount of training data to improve the performance of the algorithm and therefore the accuracy of the impact location estimation.
File in questo prodotto:
File Dimensione Formato  
Dipietrangelo_Flavio.pdf

accesso aperto

Tipologia: Versione Editoriale (PDF)
Licenza: Dominio pubblico
Dimensione 1.61 MB
Formato Adobe PDF
1.61 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11588/867389
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact