We present an ultrasonic array imaging approach based on deep learning to characterize structural defects. The proposed deep learning-based approach takes a raw ultrasonic defect image as an input and gives an output of a quantitative defect image. The test results obtained using finite element (FE) simulation and experimental data demonstrate that the fine structural features defects are successfully restored and visualized by the proposed deep learning approach.
This paper studies an air-coupled ultrasonic scanning approach for damage assessment in steel-clad concrete structures. An air-coupled ultrasonic sender generates guided plate waves in the steel cladding and a small contact-type receiver measures the corresponding wave responses. A frequency-wavenumber (f-k) domain signal filtering technique is used to isolate the behavior of the fundamental symmetric (S0) mode of the guided plate waves. The behavior of the S0 mode is sensitive to interface bonding conditions. The proposed inspection approach is verified by a series of experiments performed on laboratory-scale specimens. The experimental results demonstrate that hidden disbond between steel cladding and underlying concrete substrate can be successfully detected with the ultrasonic test setup and the f-k domain signal filtering technique.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.