Wavelet Based Clustering of Acoustic Emission Hits to Characterize Damage Mechanisms in Composites

Clustering data is an important topic in acoustic emission (AE) health monitoring. Identification of damagemechanisms in composites via AE technique requires an automatic process of classification. In this work, wepropose a novel and simple supervised method to discriminate AE signals produced by fracture mechanisms inpolymer composites. The novelty of this work is to propose new pertinent descriptors offered by using thecontinuous wavelet transform, where signals of learning are decomposed and the corresponding waveletcoefficients are calculated. In addition, the entropy criterion is applied to select the most correlated waveletsassociated to each failure mechanism. This process allows to establish a filter in the form of vectors for eachclass of signals and descriptors denote the reconstruction errors calculated by involving the filter associated toeach damage mechanism. The k-means algorithm is executed to calculate the center of each class. Thetechnique is applied to AE signals recorded from specific mechanical tests to demonstrate the performance ofthe proposed descriptors. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.