Skip to main content
SpringerLink
Log in

Convolution Neural Networks Based Automatic Subsurface Anomaly Detection and Characterization in Quadratic Frequency Modulated Thermal Wave Imaging

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

Recent trends in thermal non-destructive testing focusing on artificial intelligence and various deep learning architectures have been investigated for quality assessment of different materials. The present work introduces three famous computer vision models (AlexNet, GoogleNet and VggNet) with one-dimensional convolution layers for defect detection for material inspected by quadratic frequency modulated thermal wave imaging. These models employ sequential convolution operations and pooling on temporal thermal profiles and extract deep features further to classify defect and sound regions in the test sample. The three deep learning models are trained from scratch with the experimental thermographic data of a carbon fiber reinforced polymer (CFRP) specimen with artificially simulated flat bottom hole defects of different sizes at varying depths. The performance metrics conclude that AlexNet presents high testing accuracy and F-score of 98.92% and 0.954 resulting in less deviation to the actual labels favoring enhanced defect signal-to-noise ratio with less computation time in CPU-based hardware. Further, the depth of the detected defect was quantified using a recently introduced quantification model using the chirp-z transform-based phase analysis. The estimated depths are rearranged in the respective locations and visualized the depth map.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Vrana J. NDE 4.0: Digital Twin, Semantics, Interfaces, Networking, Feedback, New Markets and Integration into the Industrial Internet of Things. arXiv:2004.05193 (2020).

  2. Saeed N, Al Zarkani H, Omar MA. Sensitivity and robustness of neural networks for defect-depth estimation in CFRP composites. J Nondestruct Eval. 2019;38(3):1–10.

  3. Maldague X, Yves L, Jean-Pierre Couturier. A study of defect depth using neural networks in pulsed phase thermography: modelling, noise, experiments. Rev géné de therm. 1998:37(8):704–17.

  4. Wallbrink C, Wade SA, Rhys J. The effect of size on the quantitative estimation of defect depth in steel structures using lock-in thermography. J Appl Phys. 2007;101(10):1007.

  5. Laureti S, Silipigni G, Senni L, Tomasello R, Burrascano P, Ricci M. Comparative study between linear and non-linear frequency-modulated pulse-compression thermography. Appl Opt. 2018:57(18):D32–D39.

  6. Subbarao GV, Ravibabu M. Quadratic frequency modulated thermal wave imaging for non-destructive testing. Progress In Electromagn Res 2012;26:11–22.

  7. Wang F, Wang Y, Liu J, Wang, Y. The Feature Recognition of CFRP Subsurface Defects Using Low-Energy Chirp-Pulsed Radar Thermography. IEEE Trans Ind Inf. 2020;16(8):5160–68. https://doi.org/10.1109/TII.2019.2954718.

  8. Krizhevsky A, Ilya S, Geoffrey EH. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Proc Syst. 2012;25.

  9. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1–9.

  10. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. arXiv:1409.1556.

  11. Yousefi B, Kalhor D, Usamentiaga Fernández R, Lei L, Castanedo CI, Maldague XP. Application of deep learning in infrared non-destructive testing. In: QIRT 2018 Proceedings; 2018.

  12. Saeed N, King N, Said Z, Omar MA. Automatic defects detection in CFRP thermograms, using convolutional neural networks and transfer learning. Infrared Phys Technol. 2019;102:103048.

  13. Luo Q, Gao B, Woo WL, Yang Y. Temporal and spatial deep learning network for infrared thermal defect detection. Ndt & E Int. 2019;108:102164.

  14. Oliveira BC, Seibert AA, Borges VK, Albertazzi A, Schmitt RH. Employing a U-net convolutional neural network for segmenting impact damages in optical lock-in thermography images of CFRP plates. Nondestruct Test Eval. 2021;36(4):440–58.

  15. Liu K, Ma Z, Liu Yi, Yang J, Yao Y. Enhanced defect detection in carbon fiber reinforced polymer composites via generative kernel principal component thermography. Polymers. 2021;13(5):825.

  16. Kiranyaz S, Avci O, Abdeljaber O, Ince T, Gabbouj M, Inman DJ. 1D convolutional neural networks and applications: a survey. Mech Syst Signal Process. 2021;151:107398.

  17. Kim J-H, Seo S-Y, Song C-G, Kim K-S. Assessment of electrocardiogram rhythms by GoogLeNet deep neural network architecture. J Healthc Eng. 2019.

  18. Li H, Huang J, Ji S. Bearing fault diagnosis with a feature fusion method based on an ensemble convolutional neural network and deep neural network. Sensors. 2019;19(9):2034.

  19. Cao Y, Dong Y, Cao Y, Yang J, Yang MY. Two-stream convolutional neural network for non-destructive subsurface defect detection via similarity comparison of lock-in thermography signals. NDT & E Int. 2020;112:102246.

  20. Fang Q, Maldague X. A method of defect depth estimation for simulated infrared thermography data with deep learning. Appl Sci. 2020;10(19):6819.

  21. Marani R, Palumbo D, Galietti U, D’Orazio T. Deep learning for defect characterization in composite laminates inspected by step-heating thermography. Opt Lasers Eng. 2021;145:106679.

  22. Lakshmi AV, Gopitilak V, Parvez MM, Subhani SK, Ghali VS. Artificial neural networks based quantitative evaluation of subsurface anomalies in quadratic frequency modulated thermal wave imaging. Infrared Phys Technol. 2019;97:108–15.

  23. Lakshmi AV, Ghali VS, Subhani SK, Naik RB. Automated quantitative subsurface evaluation of fiber reinforced polymers. Infrared Phy Technol. 2020;110:103456.

  24. Tilak VG, Ghali VS, Lakshmi AV, Suresh B, Naik RB. Proximity based automatic defect detection in quadratic frequency modulated thermal wave imaging. Infrared Phys Technol. 2021;114:103674.

  25. Vesala GT, Ghali VS, Vijaya Lakshmi A, Naik RB. Deep and Handcrafted Feature Fusion for Automatic Defect Detection in Quadratic Frequency Modulated Thermal Wave Imaging. Russian J Nondestruct Test. 2021;57(6):476–85.

  26. Subhani SK, Suresh B, Ghali VS. Quantitative subsurface analysis using non stationary thermal wave imaging. Infra Phys Technol. 2018;88:41–7.

  27. Suresh B, Subhani SK, Vijayalakshmi A, Vardhan VH, Ghali VS. Chirp Z transform based enhanced frequency resolution for depth resolvable non stationary thermal wave imaging. Rev Sci Instrum. 2017;88(1):0149.

  28. Vesala GT, Ghali VS, Subhani S, Naga Prasanthi Y. Material characterisation by enhanced resolution in non-stationary thermal wave imaging. Insight-Non-Destruct Test Cond Moni. 2021;63(12):721–26.

  29. Fang Q, Ibarra-Castanedo C, Maldague X. Automatic defects segmentation and identification by deep learning algorithm with pulsed thermography: Synthetic and experimental data. Big Data Cognit Comput. 2021;5(1):9.

  30. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15(1):1929–58.

Download references

Funding

V. S. Ghali was supported in part by Naval Research Board, India, under the grant no. NRB-423/MAT/18-19.

Author information

Authors and Affiliations

  1. Infrared Imaging Center, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Educational Foundation, Vaddeswaram, Andhra Pradesh, India

    G. T. Vesala, V. S. Ghali & A. Vijaya Lakshmi

  2. PACE Institute of Technology and Sciences, Ongole, Andhra Pradesh, India

    S. Subhani

  3. Naval Materials Research Laboratory, Ambernath (E), Dist., Thane, Maharashtra, India

    R. B. Naik

Authors
  1. G. T. Vesala
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. V. S. Ghali
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. S. Subhani
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. A. Vijaya Lakshmi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. R. B. Naik
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to G. T. Vesala.

Ethics declarations

Conflict of Interest

The authors declare no conflict of interest.

Ethical Approval

The article is an extended version of paper V. Gopi Tilak, V. S. Ghali, R. B. Naik, A. Vijaya Lakshmi and B. Suresh, " Deep Learning in Quadratic Frequency Modulated Thermal Wave Imaging for Automatic Defect Detection," Machine Vision and Augmented Intelligence, 2021, IIIT Jabalpur, 2021 (Accepted). This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the topical collection “Advances in Machine Vision and Augmented Intelligence” guest edited by Manish Kumar Bajpai, Ranjeet Kumar, Koushlendra Kumar Singh and George Giakos.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Vesala, G.T., Ghali, V.S., Subhani, S. et al. Convolution Neural Networks Based Automatic Subsurface Anomaly Detection and Characterization in Quadratic Frequency Modulated Thermal Wave Imaging. SN COMPUT. SCI. 3, 219 (2022). https://doi.org/10.1007/s42979-022-01055-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-022-01055-7

Keywords

Search

Navigation