An Evaluation of 3D-Printed Materials’ Structural Properties Using Active Infrared Thermography and Deep Neural Networks Trained on the Numerical Data

Abstract

This article describes an approach to evaluating the structural properties of samples manufactured through 3D printing via active infrared thermography. The mentioned technique was used to test the PETG sample, using halogen lamps as an excitation source. First, a simplified, general numerical model of the phenomenon was prepared; then, the obtained data were used in a process of the deep neural network training. Finally, the network trained in this manner was used for the material evaluation on the basis of the original experimental data. The described methodology allows for the automated assessment of the structural state of 3D−printed materials. The usage of a generalized model is an innovative method that allows for greater product assessment flexibility.

Keywords

• active thermography
• deep learning
• numerical modeling
• LSTM neural networks
• 3D-printed structure quality