Abstract
A dynamic threshold method for ultrasonic C-Scan imaging is developed to improve the performance of flaw sizing: the reference test blocks with flat-bottom hole flaws of different depths and sizes are used for ultrasonic C-Scan imaging. After preprocessing, flaw regions are separated from the C-scan image. Then the flaws are sized roughly by 6-dB-drop method. Based on the real size of flat-bottom holes, enumeration method is used to get the optimal threshold for the flaw. The neural network is trained using the combination of amplitude and depth of flaw echo, the rough size of flaw and the optimal threshold. Finally, the C-Scan image can be reconstructed according to dynamic threshold generated by trained RBF NN. The experimental results show that the presented method has better performance and it is ideally suited for automatic analysis of ultrasonic C-scan images.
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.
