A Deep Learning Framework for Acoustic Emission Sources Localization and Characterization in Complex Aerospace Panels

Abstract

This paper presents a data-driven approach based on deep stacked autoencoders for the localization and characterization of acoustic emission sources in complex aerospace panels. The approach leverages the multimodal and dispersive reverberations of acoustic emissions. The approach is validated by Hsu-Nielsen pencil lead break tests on a fuselage section of a Boeing 777 instrumented with a single piezoelectric sensor.

Document Details

Document Type
Pub Defense Publication
Publication Date
Apr 01, 2021
Source ID
10.32548/2021.me-04179

Entities

People

  • Arvin Ebrahimkhanlou
  • Brennan Dubuc
  • Melanie Schneider
  • Salvatore Salamone

Organizations

  • Office of Naval Research Global

Tags

Readers

  • Aerospace Test and Evaluation
  • Neural Network Machine Learning.
  • Wave Propagation and Nonlinear Chaotic Dynamics.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Space
  • Space - Space Objects