A Convolutional Neural Network for the Non-destructive Testing of 3D-printed Samples

Mostafa El Saadouny, Jan Barowski, Ilona Rolfes

44th International Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz), pp. 1-2, DOI: 10.1109/IRMMW-THz.2019.8874445, Paris, France, Sep 1-6, 2019


The three-dimensional printing is a very important technology that participates in many applications. In this paper, we present an approach for the Non-Destructive Testing (NDT) of the three dimensional printed objects. This methodology solves the image classification problem by using Convolutional Neural Networks (CNN). The network has been trained by a large number of synthetic aperture radar (SAR) images obtained by 80 GHz radar system. The proposed solution has been used for testing different data sets for monitoring the performance under different scenarios, and the obtained results show a high degree of accuracy regarding the defected samples classification.

[IEEE Library]