Journal article
A Deep Learning Framework for Acoustic Emission Sources Localization and Characterization in Complex Aerospace
Materials evaluation, v 79(4), pp 391-400
01 Apr 2021
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.
Metrics
Details
- Title
- A Deep Learning Framework for Acoustic Emission Sources Localization and Characterization in Complex Aerospace
- Creators
- Arvin Ebrahimkhanlou - New Mexico Inst Min & Technol, Dept Mech Engn, 801 Leroy Pl,Weir 211, Socorro, NM 87801 USAMelanie B. Schneider - Appl Res Associates Inc, 4300 San Mateo Blvd NE,Suite A140, Albuquerque, NM 87110 USABrennan Dubuc - Univ Texas Austin, Appl Res Labs, 10000 Burnet Rd, Austin, TX 78758 USASalvatore Salamone - Univ Texas Austin, Dept Civil Architectural & Environm Engn, 10100 Burnet Rd,Bldg 177, Austin, TX 78758 USA
- Publication Details
- Materials evaluation, v 79(4), pp 391-400
- Publisher
- Amer Soc Nondestructive Test
- Number of pages
- 10
- Grant note
- N00014-17-1-2367 / Office of Naval Research American Society for Nondestructive Testing
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Civil, Architectural, and Environmental Engineering
- Web of Science ID
- WOS:000640305100006
- Scopus ID
- 2-s2.0-85125265821
- Other Identifier
- 991021889985104721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Industry collaboration
- Domestic collaboration
- Web of Science research areas
- Materials Science, Characterization & Testing