Damage identification of plain-woven composites at T > T_g using AE: Damage clustering and initiation detection

In this work, the damage modes and their initiation detections of plain-woven composites under tensile and compressive loads at T > T_g are investigated by conducting a comprehensive analysis of AE signals, including the feature selection, algorithm comparison and clustering validity. According to a newly proposed Pearson correlation coefficient cumulative criterion, the PF and PA are the most representative features of AE signals. A systematic comparison of K-Means, GMM and Hierarchical model, reveals that the Hierarchical model is the most suitable clustering algorithm for plain-woven composites at T > T_g. The cluster validity indexes combined with microscopic observations identify matrix cracking, interface debonding and fiber breakage as the three dominant damage modes, with PF ranges of [0–200 kHz], [200–350 kHz] and [350–600 kHz], respectively, and independent of different loading conditions. Three damage initiation criteria, sentry function, b-value and cumulative AE counts, are compared and the sentry function is determined to be optimal. The damage initiations of matrix cracking, interface debonding and fiber breakage within plain-woven composites at T > T_g can be effectively detected by AE.