Acoustic emission-based damage classification of glass/polyester composites using harmony search k -means algorithm

In this study acoustic emission monitoring was used for detection and classification of damage mechanisms during mode I delamination test of glass/polyester composites. For this purpose, the integration of harmony search and k-means algorithms was applied to cluster acoustic signals generated during delamination test. The clustering analysis represented three clusters, each one related to a distinct damage mechanism. Considering the relationship between acoustic emission parameters and damage mechanisms, the acoustic emission signals of each cluster were assigned to a distinct damage mode. Furthermore, the dominance of various damage types was investigated based on the distribution of signals in different clusters. Finally, scanning electron microscopic observation was employed to verify the obtained results. The results indicate good performance of proposed algorithms in damage classification procedure.