Damage monitoring of carbon fibre reinforced polymer composites using acoustic emission technique and deep learning

Abstract

In this research work, a deep Convolutional Neural Network (CNN) was trained for image-based Acoustic Emission (AE) waveform classification. AE waveforms from different damage modes of Carbon Fibre Reinforced Polymer (CFRP) composites were used to train the CNN for online damage monitoring. Spectrograms of AE Waveforms from four different damage modes, matrix cracking, delamination, debonding, and fibre breakage, were obtained in their Mel scale and used as the training data and test data for the CNN. The overall prediction accuracy of the CNN is 97.9%, while the fibre breakage and delamination events were able to be predicted with 100% accuracy. Then this pre-trained CNN is used for online damage monitoring of mode I delamination test of CFRP specimens. AE waveforms generated during the mode I test are classified using the trained CNN and the results are analysed in terms of the classified AE descriptors. The classified AE descriptors proved to identify the occurrences of different damage modes, thereby validating the damage classification accuracy of the CNN.