Classification of computed thermal tomography images with deep learning convolutional neural network

Ankel, V.; Shribak, D.; Chen, W. -Y.; Heifetz, A.

doi:10.1063/5.0089072

Classification of computed thermal tomography images with deep learning convolutional neural network

Journal Article · Fri Jun 24 00:00:00 EDT 2022 · Journal of Applied Physics

DOI:https://doi.org/10.1063/5.0089072· OSTI ID:1960738

^[1]; ^[2]; ^[3]; ^[3]

Argonne National Lab. (ANL), Argonne, IL (United States); Univ. of Chicago, IL (United States)
Argonne National Lab. (ANL), Argonne, IL (United States); Georgia Inst. of Technology, Atlanta, GA (United States)
Argonne National Lab. (ANL), Argonne, IL (United States)

Thermal tomography (TT) is a computational method for the reconstruction of depth profile of the internal material defects from Pulsed Infrared Thermography (PIT) nondestructive evaluation. Here, the PIT method consists of recording material surface temperature transients with a fast frame infrared camera, following thermal pulse deposition on the material surface with a flashlamp and heat diffusion into material bulk. TT algorithm obtains depth reconstructions of thermal effusivity, which has been shown to provide visualization of the subsurface internal defects in metals. In many applications, one needs to determine the defect shape and orientation from reconstructed effusivity images. Interpretation of TT images is non-trivial because of blurring, which increases with depth due to the heat diffusion-based nature of image formation. We have developed a deep learning convolutional neural network (CNN) to classify the size and orientation of subsurface material defects in TT images. CNN was trained with TT images produced with computer simulations of 2D metallic structures (thin plates) containing elliptical subsurface voids. The performance of CNN was investigated using test TT images developed with computer simulations of plates containing elliptical defects, and defects with shapes imported from scanning electron microscopy images. CNN demonstrated the ability to classify radii and angular orientation of elliptical defects in previously unseen test TT images. We have also demonstrated that CNN trained on the TT images of elliptical defects is capable of classifying the shape and orientation of irregular defects.

View Accepted Manuscript (DOE)

Research Organization:: Argonne National Laboratory (ANL), Argonne, IL (United States)

Sponsoring Organization:: USDOE; USDOE Office of Nuclear Energy (NE), Nuclear Energy Enabling Technologies (NEET)

Grant/Contract Number:: AC02-06CH11357

OSTI ID:: 1960738

Alternate ID(s):: OSTI ID: 1873958

Journal Information:: Journal of Applied Physics, Journal Name: Journal of Applied Physics Journal Issue: 24 Vol. 131; ISSN 0021-8979

Publisher:: American Institute of Physics (AIP)Copyright Statement

Country of Publication:: United States

Language:: English

References (31)

ICME Approach to Determining Critical Pore Size of IN718 Produced by Selective Laser Melting Sangid, Michael D.; Ravi, Priya; Prithivirajan, Veerappan JOM, Vol. 72, Issue 1 https://doi.org/10.1007/s11837-019-03910-0	journal	November 2019
Quality Control of Additively Manufactured Metallic Structures with Machine Learning of Thermography Images Zhang, Xin; Saniie, Jafar; Cleary, William JOM, Vol. 72, Issue 12 https://doi.org/10.1007/s11837-020-04408-w	journal	October 2020
Detection of Defects in Additively Manufactured Stainless Steel 316L with Compact Infrared Camera and Machine Learning Algorithms Zhang, Xin; Saniie, Jafar; Heifetz, Alexander JOM, Vol. 72, Issue 12 https://doi.org/10.1007/s11837-020-04428-6	journal	October 2020
Spectral estimation of Gaussian random circles and spheres Lamberg, L.; Muinonen, K.; Ylönen, J. Journal of Computational and Applied Mathematics, Vol. 136, Issue 1-2 https://doi.org/10.1016/S0377-0427(00)00578-1	journal	November 2001
Defect characterization in pulsed thermography: a statistical method compared with Kohonen and Perceptron neural networks Vallerand, S.; Maldague, X. NDT & E International, Vol. 33, Issue 5 https://doi.org/10.1016/S0963-8695(99)00056-0	journal	July 2000
Laser powder-bed fusion additive manufacturing: Physics of complex melt flow and formation mechanisms of pores, spatter, and denudation zones Khairallah, Saad A.; Anderson, Andrew T.; Rubenchik, Alexander Acta Materialia, Vol. 108 https://doi.org/10.1016/j.actamat.2016.02.014	journal	April 2016
Qualification pathways for additively manufactured components for nuclear applications Hensley, C.; Sisco, K.; Beauchamp, S. Journal of Nuclear Materials, Vol. 548 https://doi.org/10.1016/j.jnucmat.2021.152846	journal	May 2021
Parameter estimation from pulsed thermography data using the virtual wave concept Mayr, G.; Stockner, G.; Plasser, H. NDT & E International, Vol. 100 https://doi.org/10.1016/j.ndteint.2018.09.003	journal	December 2018
Temporal and spatial deep learning network for infrared thermal defect detection Luo, Qin; Gao, Bin; Woo, W. L. NDT & E International, Vol. 108 https://doi.org/10.1016/j.ndteint.2019.102164	journal	December 2019
Two-stream convolutional neural network for non-destructive subsurface defect detection via similarity comparison of lock-in thermography signals Cao, Yanpeng; Dong, Yafei; Cao, Yanlong NDT & E International, Vol. 112 https://doi.org/10.1016/j.ndteint.2020.102246	journal	June 2020
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
The Influence of Porosity on Fatigue Crack Initiation in Additively Manufactured Titanium Components Tammas-Williams, S.; Withers, P. J.; Todd, I. Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/s41598-017-06504-5	journal	August 2017
Flash Method of Determining Thermal Diffusivity, Heat Capacity, and Thermal Conductivity Parker, W. J.; Jenkins, R. J.; Butler, C. P. Journal of Applied Physics, Vol. 32, Issue 9 https://doi.org/10.1063/1.1728417	journal	September 1961
Characterization of buried cylinders and spheres by pulsed infrared thermography Garrido, Florencio; Salazar, Agustín; Alonso, Fernando Journal of Applied Physics, Vol. 98, Issue 10 https://doi.org/10.1063/1.2132097	journal	November 2005
The effect of size on the quantitative estimation of defect depth in steel structures using lock-in thermography Wallbrink, C.; Wade, S. A.; Jones, R. Journal of Applied Physics, Vol. 101, Issue 10 https://doi.org/10.1063/1.2732443	journal	May 2007
Pulsed photothermal modeling of layered materials Balageas, D. L.; Krapez, J. C.; Cielo, P. Journal of Applied Physics, Vol. 59, Issue 2 https://doi.org/10.1063/1.336690	journal	January 1986
Specified value based defect depth prediction using pulsed thermography Zeng, Zhi; Tao, Ning; Feng, Lichun Journal of Applied Physics, Vol. 112, Issue 2 https://doi.org/10.1063/1.4737784	journal	July 2012
Three-dimensional thermographic imaging using a virtual wave concept Burgholzer, Peter; Thor, Michael; Gruber, Jürgen Journal of Applied Physics, Vol. 121, Issue 10 https://doi.org/10.1063/1.4978010	journal	March 2017
Flying spot thermography: Quantitative assessment of thermal diffusivity and crack width Salazar, Agustín; Mendioroz, Arantza; Oleaga, Alberto Journal of Applied Physics, Vol. 127, Issue 13 https://doi.org/10.1063/1.5144972	journal	April 2020
Thermal tomography 3D imaging of additively manufactured metallic structures Heifetz, A.; Shribak, D.; Zhang, X. AIP Advances, Vol. 10, Issue 10 https://doi.org/10.1063/5.0016222	journal	October 2020
Deep learning approaches for thermographic imaging Kovács, Péter; Lehner, Bernhard; Thummerer, Gregor Journal of Applied Physics, Vol. 128, Issue 15 https://doi.org/10.1063/5.0020404	journal	October 2020
Applications of non-destructive testing techniques for post-process control of additively manufactured parts Lu, Q. Y.; Wong, C. H. Virtual and Physical Prototyping, Vol. 12, Issue 4 https://doi.org/10.1080/17452759.2017.1357319	journal	August 2017
Active Thermography Data-Processing Algorithm for Nondestructive Testing of Materials Da Silva, Wellington Francisco; Melo, Renan A. C.; Grosso, Marcella IEEE Access, Vol. 8 https://doi.org/10.1109/ACCESS.2020.3025329	journal	January 2020
Neural Learning Based Blind Source Separation for Detection of Material Defects in Pulsed Thermography Images Zhang, Xin; Saniie, Jafar; Heifetz, Alexander 2020 IEEE International Conference on Electro Information Technology (EIT) https://doi.org/10.1109/EIT48999.2020.9208337	conference	July 2020
Spatial Temporal Denoised Thermal Source Separation in Images of Compact Pulsed Thermography System for Qualification of Additively Manufactured Metals Zhang, Xin; Saniie, Jafar; Heifetz, Alexander 2021 IEEE International Conference on Electro Information Technology (EIT) https://doi.org/10.1109/EIT51626.2021.9491844	conference	May 2021
Pulsed Thermal Imaging Measurement of Thermal Properties for Thermal Barrier Coatings Based on a Multilayer Heat Transfer Model Sun, J. G. Journal of Heat Transfer, Vol. 136, Issue 8 https://doi.org/10.1115/1.4027551	journal	May 2014
Quantitative Three-Dimensional Imaging of Heterogeneous Materials by Thermal Tomography Sun, J. G. Journal of Heat Transfer, Vol. 138, Issue 11 https://doi.org/10.1115/1.4033998	journal	July 2016
Material Evaluation by Infrared Thermography Holland, Stephen D.; Reusser, Ricky S. Annual Review of Materials Research, Vol. 46, Issue 1 https://doi.org/10.1146/annurev-matsci-070115-032014	journal	July 2016
Three-dimensional reconstruction of subsurface defects using finite-difference modeling on pulsed thermography Ramirez-Granados, J. C.; Paez, G.; Strojnik, M. Applied Optics, Vol. 51, Issue 16 https://doi.org/10.1364/AO.51.003153	journal	January 2012
Comparison of quantitative defect characterization using pulse-phase and lock-in thermography Maierhofer, Christiane; Röllig, Mathias; Krankenhagen, Rainer Applied Optics, Vol. 55, Issue 34 https://doi.org/10.1364/AO.55.000D76	journal	January 2016
A Physics-Informed Neural Network Method for Defect Identification in Polymer Composites Based on Pulsed Thermography Lim, Wei Hng; Sfarra, Stefano; Yao, Yuan International Workshop on Advanced Infrared Technology and Applications, The 16th International Workshop on Advanced Infrared Technology & Applications https://doi.org/10.3390/engproc2021008014	conference	November 2021

Similar Records

Pulsed Thermal Tomography Nondestructive Examination of Additively Manufactured Reactor Materials and Components (Final Technical Report)

Technical Report · Wed Dec 28 23:00:00 EST 2022 · OSTI ID:1923751

Performance of Pulsed Thermal Tomography Imaging with Machine Learning-Based Classification of Defects in Additively Manufactured Structures

Technical Report · Wed Sep 15 00:00:00 EDT 2021 · OSTI ID:1823035

Related Subjects

42 ENGINEERING

Classification of computed thermal tomography images with deep learning convolutional neural network

Citation Formats

References (31)

Similar Records

Related Subjects