In this article we present an approach to the quantitative evaluation of the 3D printed sample made of polyethylene terephthalate glycol (PETG) using the active infrared thermography (AIT) method with halogen lamps excitation. For this purpose, numerical and experimental studies were carried out. The numerical model solved with finite element method (FEM) was used first to create a database of signals and further to train neural networks. The networks were trained to detect the heterogeneity of the internal structure of the tested printed sample and to estimate the defects position. After training, the performance of the network was validated with the data obtained in the experiment carried out with the active thermography regime on a real 3D print identical to the modelled one.
HullC., Apparatus for Production of Three-Dimensional Objects by Stereolithography. U.S. Patent 4575330A, 11 March 1986, n.d.
2.
OkarmaK. and Fastowiczand J., Computer vision methods for non-destructive quality assessment in additive manufacturing, in: Prog. Comput. Recognit. Syst.BurdukR.KurzynskiM. and WozniakM. (eds), Springer International Publishing, Cham, 2020, pp. 11–20. doi:10.1007/978-3-030-19738-4_2.
3.
LopatoP.PsujG. and SzymanikB., Nondestructive inspection of thin basalt fiber reinforced composites using combined terahertz imaging and infrared thermography, Adv. Mater. Sci. Eng.2016 (2016), e1249625, doi:10.1155/2016/1249625.
4.
Ibarra-CastanedoC.GonzálezD.KleinM.PillaM.VallerandS. and MaldagueX., Infrared image processing and data analysis, Infrared Phys. Technol.46 (2004), 75–83, doi:10.1016/j.infrared.2004.03.011.
5.
KowalczykJ.LopatoP.PsujG. and UlbrichD., Glass–adhesive–steel joint inspection using mechanic and high frequency electromagnetic waves, Materials13 (2020), 4648, doi:10.3390/ma13204648.
6.
SawczukW.CañásA.M.R.UlbrichD. and KowalczykJ., Modeling the average and instantaneous friction coefficient of a disc brake on the basis of bench tests, Materials14 (2021), 4766, doi:10.3390/ma14164766.
7.
MaraniR.PalumboD.GaliettiU. and D’OrazioT., Deep learning for defect characterization in composite laminates inspected by step-heating thermography, Opt. Lasers Eng.145 (2021), 106679, doi:10.1016/j.optlaseng.2021.106679.
8.
SzymanikB.PsujG.HashemiM. and LopatoP., Detection and identification of defects in 3D-printed dielectric structures via thermographic inspection and deep neural networks, Materials14 (2021), 4168, doi:10.3390/ma14154168.
9.
MetzC.FranzP.FischerC.WachtendorfV. and MaierhoferC., Active thermography for quality assurance of 3D-printed polymer structures, Quant. InfraRed Thermogr. J.18 (2021), 50–71, doi:10.1080/17686733.2019.1686896.
10.
SchmidhuberJ., Deep learning in neural networks: An overview, Neural Netw.61 (2015), 85–117, doi:10.1016/j.neunet.2014.09.003.
11.
BuiV.LeN.T.NguyenV.H.KimJ. and JangY.M., Multi-behavior with bottleneck features LSTM for load forecasting in building energy management system, Electronics10 (2021), 1026, doi:10.3390/electronics10091026.
12.
PsujG., Multi-sensor data integration using deep learning for characterization of defects in steel elements, Sensors18 (2018), 292, doi:10.3390/s18010292.
13.
SherstinskyA., Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network, Phys. Nonlinear Phenom.404 (2020), 132306, doi:10.1016/j.physd.2019.132306.
14.
LindemannB.MüllerT.VietzH.JazdiN. and WeyrichM., A survey on long short-term memory networks for time series prediction, Procedia CIRP99 (2021), 650–655, doi:10.1016/j.procir.2021.03.088.
15.
TaraghiI.LopatoP.PaszkiewiczS. and PiesowiczE., X-ray and terahertz imaging as non-destructive techniques for defects detection in nanocomposites foam-core sandwich panels containing carbon nanotubes, Polym. Test.79 (2019), 106084, doi:10.1016/j.polymertesting.2019.106084.
16.
KłosowskiG.RymarczykT.NiderlaK.RzemieniakM.DmowskiA. and MajM., Comparison of machine learning methods for image reconstruction using the LSTM classifier in industrial electrical tomography, Energies14 (2021), 7269, doi:10.3390/en14217269.
17.
BealeM.H.HaganM.T. and DemuthH.B., Deep Learning Toolbox User’s Guide, The MathWorks, Inc, Natick, MA, USA, 2021.
18.
BishopC.M., Pattern recognition and machine learning, Springer, New York, 2006.
19.
KingmaD.P. and BaJ., Adam: A Method for Stochastic Optimization, ArXiv14126980 Cs. 2017, http://arxiv.org/abs/1412.6980 (accessed November 8, 2021).
20.
GrandiniM.BagliE. and VisaniG., Metrics for Multi-Class Classification: an Overview, ArXiv200805756 Cs Stat. 2020, http://arxiv.org/abs/2008.05756 (accessed November 8, 2021).
