Deep Learning-Based Anomaly Detection from Ultrasonic Images

Published: 12.04.2022.

Deep Learning-Based Anomaly Detection from Ultrasonic Images

Non-destructive testing is a group of methods for evaluating the integrity of components. Among them, ultrasonic inspection stands out due to its ability to visualize both shallow and deep sections of the material in the search for flaws. Testing of the critical components can be a tiring and time-consuming task. Therefore, human experts in analyzing inspection data could use a hand in discarding anomaly-free data and reviewing only suspicious data. Using such a tool, errors would be less common, inspection times would shorten and non-destructive testing would be more efficient. In this work, we evaluate multiple state-of-the-art deep-learning anomaly detection methods on the ultrasonic non-destructive testing dataset. We achieved an average performance of almost 82% of ROC AUC. We discuss in detail the advantages and disadvantages of the presented methods.

Authors: Luka Posilović, Duje Medak, Fran Milković, Marko Subašić, Marko Budimir (INETEC), Sven Lončarić

Journal: Ultrasonics, Volume 124, August 2022, 106737

Read the article here.

30 Years of technological excellence

We have gained international acclaim for developing technologies for nuclear power plant examination and repair, inspection and repair services, as well as various engineering studies that we conduct as our regular scope of activities.

  • 0+ client services
  • 0% export services
  • 0% represented worldwide

This website uses cookies. By continuing to use this website you are giving consent to cookies being used. Cookies are used for better funcionality and better user experience. For more information on cookies and how you can disable them visit our Cookie policy Cookie policy »