Identification of the damage in woven composites based on acoustic emission cluster analysis

Understanding the failure mechanisms in textile composites based on acoustic emission (AE) signals is a challenging task. In the present work, unsupervised cluster analysis is performed on the AE data registered during tensile tests on 2D and 3D woven carbon and glass fibre/epoxy composites. The analysis is based on the k-means++ algorithm and principal component analysis. Peak amplitude and frequency features – peak frequency for 2D woven composites and frequency centroid for 3D woven composites – were found to be dominant in cluster analysis. Cluster bounds were identified for all composite types. These bounds do not differ with a reinforcement type, but do differ for glass and carbon reinforced composites. These bounds can be used as a starting point for AE analysis of other carbon or glass fibre/epoxy composites.