When conducting AE testing, there is an industrial need to separate AE from monitoring area to that from outside of the area in some cases. In this study, usefulness of autoencoder to solve this problem is discussed by simple experiment using an isotropic thin steel ruler. It was shown that a single trained autoencoder can be used for separating AE signals with variety of waveforms from monitoring area to those from outside of monitoring area when setting an appropriate threshold.
Previous Article in event Previous Article in session
Next Article in event Next Article in session
Idea of AE separation from unpredicted source area during AE testing by autoencoder
Published: 09 November 2020 by MDPI in 1st International Electronic Conference on Applied Sciences session Acoustics and Vibrations
Keywords: Acoustic Emission; Artificial Neural Network (ANN); Autoencoder; Anomaly data separation