A Methodology to Automatically Segment 3D Ultrasonic Data Using X-ray Computed Tomography and a Convolutional Neural Network

Ultrasonic non-destructive testing (UT) is a proficient method for detecting damage in composite materials; however, conventional manual testing procedures are time-consuming and labor-intensive. We propose a semi-automated defect segmentation methodology employing a convolutional neural network (CNN) on 3D ultrasonic data, facilitated by the fusion of X-ray computed tomography (XCT) and Phased-Array Ultrasonic Testing (PAUT) data. This approach offers the ability to develop supervised datasets for cases where UT techniques inadequately assess defects and enables the creation of models with genuine defects rather than artificially introduced ones. During the training process, we recommend processing the 3D volumes as a sequence of 2D slices derived from each technique. Our methodology was applied to segment porosity, a common defect in composite materials, for which characteristics such as void size and shape remain immeasurable via UT. Precision, recall, F1 score, and Intersection over Union (IoU) metrics were used in the evaluation. The results of the evaluation show that the following challenges have to be faced for improvement: (i) achieving accurate 3D registration, (ii) discovering suitable similar keypoints for XCT and UT data registration, (iii) differentiating ultrasonic echoes originating from porosity versus those related to noise or microstructural features (interfaces, resin pockets, fibers, etc.), and, (iv) single out defect echoes located near the edges of the component. In fact, an average F1 score of 0.66 and IoU of 0.5 were obtained.

Automated summary

In this study, a semi-automated defect segmentation method using a convolutional neural network on 3D ultrasonic data was proposed, facilitated by the fusion of X-ray computed tomography and Phased-Array Ultrasonic Testing data. This approach allows for the creation of genuine defect models and addresses the limitations of traditional UT techniques in defect evaluation. However, challenges such as accurate defect localization still need to be addressed for further improvement.