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.

Defect Detection in CFRP Concrete Reinforcement Using the Microwave Infrared Thermography (MIRT) Method—A Numerical Modeling and Experimental Approach

“…Microwave heating has been widely employed in the literature for various purposes related to concrete structures, including expediting the curing process, decontaminating cement, and facilitating the drilling or melting of concrete [24][25][26][27]. In this proposal, microwaves are suggested as a potential energy source for infrared thermography [28][29][30][31][32][33][34]. The primary benefit of utilizing microwave heating lies in its volumetric nature.…”

Multi-Task Learning of Scanning Electron Microscopy and Synthetic Thermal Tomography Images for Detection of Defects in Additively Manufactured Metals

“…This limits the applicability of UT because LPBF-printed metals have rough surfaces due to the specifics of the manufacturing process. Pulsed infrared thermography (PIT) or the active thermography NDE method use non-contact sensors for the imaging of subsurface defects in optically opaque materials [21][22][23][24][25][26][27][28]. PIT uses a flash lamp to deposit a thermal pulse on a material surface.…”

“…In classification tasks, features extracted from images are used to assign a predefined class value to the input image, and in regression tasks, the features extracted from CNNs are used to predict appropriate continuous values. In prior studies, CNN was shown to be an efficient method for analysis of images for in situ monitoring of AM [8][9][10][11][12], and NDE of AM [23][24][25][26][27][28].…”