10 - AE feature extraction and signal representation model based on wavelet packet decomposition

Abstract

This chapter performs acoustic emission (AE) monitoring of damage behaviors in carbon fiber/epoxy composite laminates during tensile loads under hygrothermal environment. A feature extraction model is established based on the original waveforms of AE signals. Tensile tests synchronized with AE tests are carried out on carbon fiber/epoxy composite laminates under different environments. A feature extraction and representation method is developed based on the wavelet packet decomposition and Shannon's entropy so as to cover the full frequency domain. Based on the extracted features, cosine similarity and clustering algorithms are employed to achieve damage mode identification during the failure process of composite laminates. The influence of hygrothermal aging on damage source localization, damage initiation and evolution, and the AE features is analyzed.