Detection and classification of matrix cracking in laminated composites using guided wave propagation and artificial neural networks

Abstract The guided wave propagation and artificial intelligence (AI) approaches were used to propose an intelligent model for automatic detection and classification of the matrix cracking in composites. Glass/epoxy cross-ply laminated composites were fabricated and the matrix cracking with several densities was induced in 90° layers. A non-destructive testing procedure using the fundamental antisymmetric Lamb wave propagation was performed on the intact specimens and those with 0.05, 0.15, and 0.25 matrix cracking density. The velocity of propagated Lamb wave, wave amplitudes in four different distances from the actuator, and the ratio of these amplitudes to the first received wave amplitude, in three frequencies of 100, 200, and 330 kHz were extracted from the acquired signals. The extracted sensory features were used to train three types of supervised machine learning models for the crack density classification. The linear discriminant analysis (LDA) was performed for dimensional reduction to find a linear combination of features that can better discriminate the classes. Support vector machines (SVM), linear vector quantization (LVQ) neural network (NN), and multilayer perceptron (MLP) NN were used for the classification. It was shown that SVM accounted for the highest classification accuracy (91.7%) followed by LVQ NN (88.9%) and MLP NN (77.8%), respectively.