A Neural Network Framework for Validating Information–Theoretics Parameters in the Applications of Acoustic Emission Technique for Mechanical Characterization of Materials

Abstract

A multiparameter approach is preferred while utilizing Acoustic Emission (AE) technique for mechanical characterization of composite materials. It is essential to utilize a statistical parameter, which is independent of the sensor characteristics, for this purpose. Thus, a new information–theoretics parameter, Lempel–Ziv (LZ) complexity, is used in this research work for mechanical characterization of Carbon Fibre Reinforced Plastic (CFRP) composites. CFRP specimens in plain weave fabric configurations were tested and the acoustic activity during the loading was recorded. The AE signals were classified based on their peak amplitudes, counts, and LZ complexity indices using k-means++ data clustering algorithm. The clustered data were compared with the mechanical results of the tensile tests on CFRP specimens. The results show that the clustered data are capable of identifying critical regions of failure. The LZ complexity indices of the AE signal can be used as an AE descriptor for mechanical characterization. This is validated by studying the clustered signals in their time–frequency domain using wavelet transform. Finally, a neural network framework based on SqueezeNet was trained using the wavelet scalograms for a quantitative validation of the data clustering approach proposed in this research work. The results show that the proposed method functions at an efficiency of more than 85% for three out of four clustered data. This validates the application of LZ complexity as an AE descriptor for AE signal data analysis.