Use of Principal Component Analysis and Autoencoder Neural Networks in Characterization of Acoustic Emission Waveforms from Composite Coupon Specimens

Abstract

Acoustic emission (AE) monitoring is a method of structural health monitoring that relies on the detection of elastic waves generated by the release of concentrated strain energy when damage is created in a structural material. One of its strengths is that recorded waveforms can, in theory, be used to infer the source mechanisms, enabling estimation of damage type, location, and severity. One of the challenges, however, is how to automate the interpretation and reliably retain useful information from AE waveforms, which are often thousands of samples long. In this work, a method of waveform analysis in the frequency domain is presented that combines principal component analysis and an autoencoder to reduce the dimensionality of the problem to a pair of parameters, capturing the spectrum shape and the spectrum energy content. Tensile tests were carried out on composite coupon specimens while monitoring AE, and the progression of damage was assessed by X-ray scanning the specimens at two locations along their length, both before and after testing. Locations and types of damage in the scans are in good agreement with the results of the AE monitoring and analysis framework. The method is proposed as a tool for automated interpretation of AE signals with the potential to be generalized to other material, layup, and sensor setups.