Acoustic emission pattern recognition approach based on Hilbert–Huang transform for structural health monitoring in polymer-composite materials

One of the most important difficulties faced by in situ structural health monitoring approaches when establishing a relationship between a specific damage mechanism and its acoustic signature is the lack of an appropriate signal processing method able to deal with the non-stationary acoustic signals. The purpose of this paper is to use the Hilbert–Huang transform for the extraction of new relevant damage descriptor to be adopted for Acoustic Emission (AE) pattern recognition in order to help understanding the damage process. AE signals collected from unidirectional glass-fiber reinforced polymer composites samples were studied. First, the frequency content of the recorded signals in each test is analyzed. Secondly, the performance of the Hilbert–Huang transform damage classification approach is evaluated.