Under CopyrightKraljevski, IvanIvanKraljevskiDuckhorn, FrankFrankDuckhornBarth, MartinMartinBarthTschöpe, ConstanzeConstanzeTschöpeSchubert, FrankFrankSchubertWolff, MatthiasMatthiasWolff2022-03-1522.12.20212021https://publica.fraunhofer.de/handle/publica/41333110.1109/SENSORS47087.2021.963986410.24406/publica-r-4133312-s2.0-85123613250We present an approach for ultrasonic non-destructive testing of adhesive bonding employing unsupervised machine learning with autoencoders. The models are trained exclusively on the features derived from pulse-echo ultrasonic signals on a specimen with good adhesive bonding and tested on another specimen with artificially added defects. The resulting pseudo-probabilities indicating anomalies are visualized and presented along to the C-scan of the same specimen. As a result, we achieved improved representation of the defects, providing a possibility of their automatic and reliable detection.enmachine learningnon-destructive testingultrasonic transducerconvolutional autoencoder620666conference paper