Resumen
This paper introduces two deep learning approaches to localize acoustic emissions (AE) sources within metallic plates with geometric features, such as rivet-connected stiffeners. In particular, a stack of autoencoders and a convolutional neural network are used. The idea is to leverage the reflection and reverberation patterns of AE waveforms as well as their dispersive and multimodal characteristics to localize their sources with only one sensor. Specifically, this paper divides the structure into multiple zones and finds the zone in which each source occurs. To train, validate, and test the deep learning networks, fatigue cracks were experimentally simulated by Hsu?Nielsen pencil lead break tests. The pencil lead breaks were carried out on the surface and at the edges of the plate. The results show that both deep learning networks can learn to map AE signals to their sources. These results demonstrate that the reverberation patterns of AE sources contain pertinent information to the location of their sources.