Abstract
The non-uniformity of non-planar object inspection data makes their analysis challenging. This paper reports a study of the use of recurrent neural network and artificial feed-forward neural network in pulsed thermography during the automated inspection of non-planar carbon fiber reinforced plastic samples. The time series, including the raw temperature–time series and sequenced signals obtained from the first derivative after thermographic signal reconstruction was used to train and test the models respectively. Quantitative comparisons of testing results showed that the long short-term memory recurrent neural network model was more accurate in handling time dependent information compared to the artificial feed-forward neural network model.
Similar content being viewed by others
References
Sun, Y., Bai, P., Sun, H., Zhou, P.: Real-time automatic detection of weld defects in steel pipe. NDT and E Int. 38, 522–528 (2005)
Wenzel, T., Hanke, R.: Fast image processing on die castings. In: Anglo-German Conference on NDT Imaging and Signal Processing (1998)
Kazantsev, I.G., Lemahieu, I., Salov, G.I., Denys, R.: Statistical detection of defects in radiographic images in nondestructive testing. Signal Process. 82, 791–801 (2002)
Benítez, H.D., Loaiza, H., Caicedo, E., Ibarra-Castanedo, C., Bendada, A., Maldague, X.: Defect characterization in infrared non-destructive testing with learning machines. NDT and E Int. 42, 630–643 (2009)
Benitez, H., Ibarra-Castanedo, C., Loaiza, H., Caicedo, E., Bendada, A., Maldague, X.: Defect quantification with thermographic signal reconstruction and artificial neural networks. In: Proceedings of 8th Conference on Quantitative Infrared Thermography, Padova, Italy, p. 6, (2006)
Darabi, A., Maldague, X.: Neural network based defect detection and depth estimation in TNDE. NDT and E Int. 35, 165–175 (2002)
Duan, Y., Liu, S., Hu, C., Hu, J., Zhang, H., Yan, Y., Tao, N., Zhang, C., Maldague, X., Fang, Q., Ibarra-Castanedo, C., Chen, D., Li, X., Meng, J.: Automated defect classification in infrared thermography based on a neural network. NDT and E Int. 107, 102147 (2019)
Shipway, N.J., Barden, T.J., Huthwaite, P., Lowe, M.: Automated defect detection for fluorescent penetrant inspection using random forest. NDT and E Int. 101, 113–123 (2019)
Chun, P., Ujike, I., Mishima, K., Kusumoto, M., Okazaki, S.: Random Forest-based evaluation technique for internal damage in reinforced concrete featuring multiple nondestructive testing results,". Constr. Build. Mater. 253, 119238 (2020)
Osman, A., Hassler, U., Kaftandjian, V., Hornegger, J.: An automated data processing method dedicated to 3D ultrasonic non destructive testing of composite piece. In: IOP conference series: materials science and engineering, p. 012005 (2012)
Osman, A.: Automated evaluation of three dimensional ultrasonic datasets, INSA de Lyon; Friedrich-Alexander-Universität Erlangen-Nürnberg, 2013.
Osman, A., Kaftandjian, V., Hassler, U.: Automatic classification of 3D segmented CT data using data fusion and support vector machine. In: Tenth International Conference on Quality Control by Artificial Vision, p. 80000F (2011)
Kovács, P., Lehner, B., Thummerer, G., Mayr, G., Burgholzer, P., Huemer, M.: Deep learning approaches for thermographic imaging. J Appl Phys 128, 1551 (2020)
Dai, X., Duan, Y., Hu, J., Liu, S., Hu, C., He, Y., Chen, D., Luo, C., Meng, J.: Near infrared nighttime road pedestrians recognition based on convolutional neural network. Infrared Phys. Technol. 97, 25–32 (2019)
Dai, X., Hu, J., Zhang, H., Shitu, A., Luo, C., Osman, A., Sfarra, S., Duan, Y.: Multi-task faster R-CNN for nighttime pedestrian detection and distance estimation. Infrared Phys Technol 115, 1036 (2021)
Mery, D.: Aluminum casting inspection using deep learning: a method based on convolutional neural networks. J. Nondestr. Eval. 39, 1–12 (2020)
Lin, J., Yao, Y., Lin, M., Wang, Y.: Detection of a casting defect tracked by deep convolution neural network. The International J Adv Manufacturing Technol 97, 573–581 (2018)
Słoński, M., Schabowicz, K., Krawczyk, E.: Detection of flaws in concrete using ultrasonic tomography and convolutional neural networks. Materials 13, 1557 (2020)
Wei, S., Li, X., Ding, S., Yang, Q., Yan, W.: Hotspots Infrared detection of photovoltaic modules based on Hough line transformation and Faster-RCNN approach. In: 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 1266–1271 (2019)
Hu, C., Duan, Y., Liu, S., Yan, Y., Tao, N., Osman, A., Ibarra-Castanedo, C., Sfarra, S., Chen, D., Zhang, C.: LSTM-RNN-based defect classification in honeycomb structures using infrared thermography. Infrared Phys. Technol. 102, 103032 (2019)
Chulkov, A.O., Tuschl, C., Nesteruk, D.A., Oswald-Tranta, B., Vavilov, V.P., Kuimova, M.V.: The detection and characterization of defects in metal/non-metal sandwich structures by thermal NDT, and a comparison of areal heating and scanned linear heating by optical and inductive methods. J. Nondestr. Eval. 40, 1–13 (2021)
Popow, V., Gurka, M.: Full factorial analysis of the accuracy of automated quantification of hidden defects in an anisotropic carbon fibre reinforced composite shell using pulse phase thermography,". NDT and E Int. 116, 102359 (2020)
Duan, Y., Zhang, H., Maldague, X.P., Ibarra-Castanedo, C., Servais, P., Genest, M., Sfarra, S., Meng, J.: Reliability assessment of pulsed thermography and ultrasonic testing for impact damage of CFRP panels. NDT and E Int. 102, 77–83 (2019)
Duan, Y., Servais, P., Genest, M., Ibarra-Castanedo, C., Maldague, X.P.: ThermoPoD: A reliability study on active infrared thermography for the inspection of composite materials. J. Mech. Sci. Technol. 26, 1985–1991 (2012)
Theodorakeas, P., Avdelidis, N.P., Hrissagis, K., Ibarra-Castanedo, C., Koui, M., Maldague, X.: Automated transient thermography for the inspection of CFRP structures: experimental results and developed procedures. In: Thermosense: Thermal Infrared Applications XXXIII, p. 80130W (2011)
Zhu, X., Vondrick, C., Fowlkes, C.C., Ramanan, D.: Do we need more training data? Int. J. Comput. Vision 119, 76–92 (2016)
Althnian, A., AlSaeed, D., Al-Baity, H., Samha, A., Dris, A.B., Alzakari, N., Abou Elwafa, A., Kurdi, H.: Impact of dataset size on classification performance: an empirical evaluation in the medical domain. Appl Sci 11, 796 (2021)
Maldague, X., Largouët, Y., Couturier, J.: A study of defect depth using neural networks in pulsed phase thermography: modelling, noise, experiments. Revue générale de thermique 37, 704–717 (1998)
Maldague, X., Marinetti, S.: Pulse phase infrared thermography. J. Appl. Phys. 79, 2694–2698 (1996)
Shepard, S., Lhota, J., Wang, D., Rubadeux, B., Ahmed, T.: Depth and spatial resolution enhancement using thermographic signal reconstruction. In: 6th Far-East Conference on NDT-FENDT02, pp. 279–284 (2002)
Cheng, L., Gao, B., Tian, G.Y., Woo, W.L., Berthiau, G.: Impact damage detection and identification using eddy current pulsed thermography through integration of PCA and ICA. IEEE Sens. J. 14, 1655–1663 (2014)
Marinetti, S., Grinzato, E., Bison, P.G., Bozzi, E., Chimenti, M., Pieri, G., Salvetti, O.: Statistical analysis of IR thermographic sequences by PCA. Infrared Phys. Technol. 46, 85–91 (2004)
Shepard, S.M., Lhota, J.R., Rubadeux, B.A., Wang, D., Ahmed, T.: Reconstruction and enhancement of active thermographic image sequences. Opt. Eng. 42, 1337–1342 (2003)
Shepard, S.M., Lhota, J.R., Rubadeux, B.A., Ahmed, T., Wang, D.: Enhancement and reconstruction of thermographic NDT data. In: Thermosense XXIV, pp. 531–535 (2002)
Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Networks 5, 157–166 (1994)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)
Bourquin, J., Schmidli, H., van Hoogevest, P., Leuenberger, H.: Advantages of Artificial Neural Networks (ANNs) as alternative modelling technique for data sets showing non-linear relationships using data from a galenical study on a solid dosage form. Eur. J. Pharm. Sci. 7, 5–16 (1998)
Schmidhuber, J.: Deep learning in neural networks: An overview. Neural Netw. 61, 85–117 (2015)
Bengio, Y., Grandvalet, Y.: No unbiased estimator of the variance of k-fold cross-validation. J. Mach. Learn. Res. 5, 1089–1105 (2004)
Hecht-Nielsen, R.: Theory of the backpropagation neural network. In: Neural networks for perception, pp. 65–93. Elsevier (1992)
Sokolova, M., Lapalme, G.: A systematic analysis of performance measures for classification tasks. Inf. Process. Manage. 45, 427–437 (2009)
Acknowledgements
Thanks for the supports of National Natural Science Foundation of China [Grant No. 61505264, 2016], and Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery Grant. A special thanks to the Canada Research Chair in Multipolar Infrared Vision (MIVIM) for providing experimental data of CFRP samples.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Tao, Y., Hu, C., Zhang, H. et al. Automated Defect Detection in Non-planar Objects Using Deep Learning Algorithms. J Nondestruct Eval 41, 14 (2022). https://doi.org/10.1007/s10921-022-00845-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10921-022-00845-6