Health Assessment of Composite Structures in Unconstrained Environments Using Partially Supervised Pattern Recognition Tools. - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Health Assessment of Composite Structures in Unconstrained Environments Using Partially Supervised Pattern Recognition Tools.

Résumé

The health assessment of composite structures from acoustic emission data is generally tackled by the use of clustering techniques. In this paper, the K-means clustering and the newly proposed Partially-Hidden Markov Model (PHMM) are exploited to analyse the data collected during mechanical tests on composite structures. The health assessment considered in this paper is made difficult by working in unconstrained environments. The presence of the noise is illustrated in several examples and is shown to distort strongly the results of clustering. A solution is proposed to filter out the noisy partition provided by the clustering methods. After filtering, the PHMM provides results which appeared closer to the expectations than the K-means. The PHMM offers the possibility to use uncertain and imprecise labels on the possible states, and thus covers supervised and unsupervised learning as special cases which makes it suitable for real applications.
Fichier principal
Vignette du fichier
PHMSociety_composite_phmm.pdf (2.36 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00801920 , version 1 (18-03-2013)

Identifiants

  • HAL Id : hal-00801920 , version 1

Citer

Emmanuel Ramasso, Vincent Placet, Rafael Gouriveau, Lamine Boubakar, Noureddine Zerhouni. Health Assessment of Composite Structures in Unconstrained Environments Using Partially Supervised Pattern Recognition Tools.. Annual Conference of the Prognostics and Health Management Society, PHM'12., Sep 2012, Hyatt Regency Minneapolis, Minnesota, United States. pp.1-11. ⟨hal-00801920⟩
189 Consultations
86 Téléchargements

Partager

Gmail Facebook X LinkedIn More