Spatially resolved strain measurement at meter scale using a carbon fiber based strain sensor and artificial neural networks

Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/GutachtenBeitrag in KonferenzbandBeigetragenBegutachtung

Abstract

Life cycle optimization, maintenance planning and adaptive control systems in fiber-reinforced structures such as aircraft wings require the monitoring of loads and stresses during operation. State of the art systems using strain gauges can measure strains at limited numbers of discrete points, while systems based on fiber optic time domain reflectometry require complex and cost intensive evaluation units. A novel sensor based on electrical time domain reflectometry (ETDR) allows to acquire information about the spatial distribution of strain along a fractured carbon fiber (CF) embedded in a composite structure. This sensor concept has been investigated in previous studies with specimens up to 60 mm in length. Based on this work, a demonstrator with an improved sensor layout and two embedded sensors of 1 m length is developed. A shallow feed-forward network and a convolutional neural network are compared regarding their ability to infer strain profiles from measured ETDR reflectograms. The simultaneous evaluation of two sensors with a convolutional neural network allowed the inference of strain distributions with a good generalization ability.

Details

OriginalspracheEnglisch
TitelProceedings of the 10th ECCOMAS Thematic Conference on Smart Structures and Materials (Smart 2023)
Seiten1743-1754
Seitenumfang12
ISBN (elektronisch)978-960-88104-6-4
PublikationsstatusVeröffentlicht - Juli 2023
Peer-Review-StatusJa

Konferenz

Titel10th ECCOMAS Thematic Conference on Smart Structures and Materials
KurztitelSMART 2023
Dauer3 - 5 Juli 2023
Webseite
StadtPatras
LandGriechenland

Externe IDs

ORCID /0000-0003-2834-8933/work/143495369
ORCID /0000-0003-1385-1528/work/143495834
ORCID /0000-0002-8854-7726/work/143496306
Mendeley fbb3fa9e-ab5a-3c42-b766-3d7c5925303d
unpaywall 10.7712/150123.9945.444359

Schlagworte

Schlagwörter

  • carbon fiber, composite, continuous strain measurement, spatially resolved strain sensor, convolutional neural network, structural health monitoring