Contribution of functional approach to the classification and the identification of acoustic emission source mechanisms

O. Traore (1) , P. Christini (1) , N. Favretto-Christini (1) , L. Pantera (2) , Philippe Vieu (3) , Sylvie Viguier-Pla (3)

1 LMA - Laboratoire de Mécanique et d'Acoustique [Marseille]
2 LP2E - Laboratoire des Programmes Expérimentaux et d'Essais en Sûreté
3 UT3 - Université Toulouse III - Paul Sabatier

In a context of nuclear Reactivity Initiated Accident, we describe acoustic emission signals, for which a problem of classification is open. As classical approaches with a reduced number of variables do not give satisfactory discrimination, we propose to use the envelopes of the received signals.We perform a k-means clustering and discuss the first results of this approach.

Domaines: Physique Nucléaire Expérimentale [nucl-ex]; Physique Nucléaire Théorique [nucl-th]

O. Traore, P. Christini, N. Favretto-Christini, L. Pantera, Philippe Vieu, et al.. Contribution of functional approach to the classification and the identification of acoustic emission source mechanisms. International Workshop on Functional and Operational Statistics (IWFOS 2017), Jun 2017, La Corogne, Spain. ⟨10.1007/978-3-319-55846-2_33⟩. ⟨cea-02434561⟩