An Unsupervised Pattern Recognition Approach for AE Data Originating from Fatigue Tests on Polymer-Composite Materials

Abstract : Acoustic Emission (AE) technique is gaining more and more interest for structural health monitoring (SHM) in polymer-composite materials. Recent literature has shown that using appropriate pattern recognition techniques (PRT), the identifi,cation of the natural clusters of acoustic emission data can be obtained. This work investigates acoustic emission generated during tension fatigue tests carried out on a carbon fi,ber reinforced polymer (CFRP) composite specimen. Since fatigue data processing, especially noise reduction remains an important challenge in AE data analysis, a noise modeling has been proposed in the present work to tackle this problem. A Davies-Bouldin-index-based progressive feature selection has been implemented to reduce high dimensional fatigue dataset. A classifier offline-learned from quasi-static data is then used to classify the processed data to different AE sources. An adaptation has been studied to enable the classifier to generate new class, i.e. AE source, for unidentified AE events. With efficient proposed noise removal and automatic separation of AE events, the results of this work provide an insight into fatigue damage development in composites and then ability to health assessment which is necessary for residual life prediction. KEYWORDS: organic-matrix composites, acoustic emission, data clustering, noise reduction, feature selection.
Type de document :
Communication dans un congrès
Le Cam, Vincent and Mevel, Laurent and Schoefs, Franck. EWSHM - 7th European Workshop on Structural Health Monitoring, Jul 2014, Nantes, France. 2014
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01021059
Contributeur : Anne Jaigu <>
Soumis le : mercredi 9 juillet 2014 - 08:46:26
Dernière modification le : vendredi 6 juillet 2018 - 15:06:09
Document(s) archivé(s) le : jeudi 9 octobre 2014 - 10:52:41

Fichier

0433.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01021059, version 1

Citation

Dinh Dong Doan, Emmanuel Ramasso, Vincent Placet, Lamine Boubakar, Noureddine Zerhouni. An Unsupervised Pattern Recognition Approach for AE Data Originating from Fatigue Tests on Polymer-Composite Materials. Le Cam, Vincent and Mevel, Laurent and Schoefs, Franck. EWSHM - 7th European Workshop on Structural Health Monitoring, Jul 2014, Nantes, France. 2014. 〈hal-01021059〉

Partager

Métriques

Consultations de la notice

444

Téléchargements de fichiers

420