Abstract
Ultrasonic testing (UT) has been actively studied to evaluate the porosity of additively manufactured parts. Currently, ultrasonic measurements of as-deposited parts with a rough surface remain problematic because the surface lowers the signal-to-noise ratio (SNR) of ultrasonic signals, which degrades the UT performance. In this study, various deep learning (DL) techniques that can effectively extract the features of defects, even from signals with a low SNR, were applied to UT, and their performance in terms of the porosity evaluation of additively manufactured parts with rough surfaces was investigated. Experimentally, the effects of the processing conditions of additive manufacturing on the resulting porosity were first analyzed using both optical and scanning acoustic microscopy. Second, convolutional neural network (CNN), deep neural network, and multi-layer perceptron models were trained using time-domain ultrasonic signals obtained from additively manufactured specimens with various levels of porosity and surface roughness. The experimental results showed that all the models could evaluate porosity accurately, even that of the as-deposited specimens. In particular, the CNN delivered the best performance at 94.5%. However, conventional UT could not be applied because of the low SNR. The generalization performance when using newly manufactured as-deposited specimens was high at 90%.
Highlights
Ultrasonic testing (UT) at low signal-to-noise ratio (SNR) for the inspection of Additive manufacturing (AM) parts. This is because the reduction of the SNR of ultrasonic signals as a result of the surface roughness of AM parts is more severe than that due to the artificial noise used in previous studies
We investigated the performance of deep learning (DL)-based UT to evaluate the porosity of AM parts with a rough surface
DL techniques were used in conjunction with UT to evaluate the porosity of AM parts with rough surfaces
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Ultrasonic signals obtained from a rough surface have a low signal-to-noise ratio (SNR), which degrades the UT performance To overcome this problem, previous studies commonly used various surface polishing methods as a post-processing step to prepare the surface of as-deposited AM parts whose roughness exceeded a certain level. They measured ultrasonic signals from welding defects and added various levels of artificial noise They reported that their convolutional neural network (CNN) outperformed the fully connected deep neural network (DNN) and multi-layer perceptron (MLP) as the SNR decreased. UT at low SNRs for the inspection of AM parts This is because the reduction of the SNR of ultrasonic signals as a result of the surface roughness of AM parts is more severe than that due to the artificial noise used in previous studies. The applicability of the conventional UT was considered for performance comparison. (3) The generalization performance was evaluated using newly manufactured AM specimens that were not used to train the DL model in order to verify the generalizability of the pre-trained model
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
