Ultrasonic defect characterization using time-domain scattering matrices and convolutional sparse coding

Abstract

In this paper, the use of the time-domain scattering matrix for ultrasonic characterization of defects is explored. An approach based on convolutional sparse coding is proposed for extraction of the shift-invariant features of the time-domain scattering matrix. The results of a simulation show that the proposed approach can be reliably used for classification of the rough cracks. In addition, the mean sizing error and its standard deviation are also reduced compared with the use of the frequency domain scattering matrix. In experiments, a 1.5 mm slot and 1.5 mm elliptical defect were sized to within 0.25 mm using a 2.5 MHz, 64 element linear array with an element pitch of 0.5 mm. Excellent sizing results were obtained for inclined slots with a large orientation angle (i.e. 60°).