Automated analysis of acoustic emission datasets based on the ISODATA algorithm

Acoustic emission (AE) testing is a widely used technique for the continuous evaluation of damage initiation and propagation in structural components. AE testing can be applied on a wide range of materials such as metals and fibre-reinforced composites. During loading, especially in composite materials, multiple failure mechanisms can become active resulting in the generation of AE signals with distinctive waveforms and statistical characteristics. By evaluating AE signals based on their characteristics it is possible to group them into clusters and improve the effectiveness of AE in monitoring structural degradation. The clustering process can be effectively carried out using automated clustering algorithms. The applicability of various clustering algorithms for AE data clustering has been considered in several studies. In this research study the effectiveness of the ISODATA clustering algorithm has been evaluated. The AE data considered have been acquired during tensile and flexural tests on glass fibre-reinforced composite samples. The automated clustering results are compared with manual filtering of the recorded AE signals.