Using clustering of acoustic emission signals on damage mechanisms analysis of quasi-isotropic self-reinforced polyethylene composites

Acoustic emission (A-E) was used to monitor the damage process in quasi-isotropic self-reinforced polyethylene composites (UHMWPE/LDPE) under quasi-static tensile load. The collected AE signals were classified by using the unsupervised pattern recognition (PR) technique, to identify the various mechanisms in the composites. The fracture surfaces of the specimens were observed by a scanning electron microscope (SEM). By combining the best clustering results with the observation results, correlations were established between the AE signal classes and the damage modes. The initiation and progression of the damage was then reviewed by the cumulative AE hits of each damage mode versus strain curves. A reliable identification of AE signals and a clear view of damage mechanisms in the composites are obtained in this study.