ANALYSIS OF APPLICATION OF NEURAL NETWORKS TO IMPROVE THE RELIABILITY OF ACTIVE THERMAL NDT
Background. The relevant question of increasing the informative content and reliability of the thermal non-destructive testing is considered in this article. The most promising algorithms of digital processing of sequences of thermograms are given.
Objective. The main aim of this research is to determine the advantages and disadvantages of the application of each considered method of digital processing of thermograms. Secondary, the possibilities of testing automation with the use of the selected methods of digital processing of thermograms are analyzed in this article.
Methods. Computer simulation software was used to obtain the artificial sequence of the thermograms. Methods of wavelet analysis, principal components analysis and neural networks were used to process the received data.
Results. The simulation of active thermal testing process is carried out in this research. The artificial thermogram sequence with a high level of noise is obtained for the object of testing. In order to quantify the results of application of considered methods, relative errors of determining the area of defects were calculated. Also values of Tanimoto criterion are obtained. The advantages of the neural network processing of digital data in thermal non-destructive testing have been established and proved in this article. Shape of defects on a binary map built by the neural network was closest to true compared with principal components analysis method. The effectiveness of neural networks is also confirmed by quantitative estimates.Conclusions. The method of wavelet transformation has a high sensitivity. This method is ineffective in the conditions of uneven heating and high noise. The principal components analysis method allows increasing the SNR and improving the visual perception of thermograms, but does not provide complete separation of information about defects and noises caused by uneven heating. Methods of artificial neural networks theory provide the best reproduction of the shape and size of the defects, but the training process requires significant time and computing resources.
C. Ibarra-Castanedo et al., “Thermographic nondestructive evaluation: Overview of recent progress”, in Thermosense XXV, Orlando, 2003, pp. 33-43. doi: 10.1117/12.485699
S. Jiangang, “Analysis of data processing methods for pulsed thermal imaging characterisation of delaminations”, Quantitative InfraRed Thermography Journal, vol. 10, no. 1, pp. 9–25, 2013. doi: 10.1080/17686733.2012.757860
S. Pareek et al., “Application of artificial neural networks to monitor thermal condition of electrical equipment”, in Proc. 3rd Int. Conf. Condition Assessment Techniques in Electrical Systems (CATCON), Rupnagar, India, 2017, pp. 113–123. doi: 10.1109/CATCON.2017.8280208
P. Xiao et al., “Removing stripe noise from infrared cloud images via deep convolutional networks”, IEEE Photonics J., vol. 10, no. 4, pp. 1–14, 2018. doi: 10.1109/jphot.2018.2854303
R. Galagan and A. Momot, “Analysis of methods for digital processing of thermograms”, Visnik Nacionalnogo Tehnichnogo Universitetu Ukrayini “KPI”. Seriya Priladobuduvannya, no. 55, pp. 108–117, 2018. doi: 10.20535/1970.55(1).2018.135849
V. Vavilov, Infrared Thermography and Thermal Testing. Moscow, Russia: PH Spectr, 2013.
V. Ingle and J. Proakis, Digital Signal Processing using MATLAB. Stamford, UK: Cengage Learning, 2011.
X. Maldague et al., “Advances in pulsed phase thermography”, Infrared Physics & Technology, vol. 43, pp. 175–181, 2002. doi: 10.21611/qirt.1996.062
V. Vavilov et al., “The application of Fourier analysis and the principal components analysis for the processing of dynamic thermal testing data”, Izvestiya TPU, vol. 2, pp. 279–285, 2008.
V. Shiryaev et al., “The use of wavelets in active thermal testing”, in Proc. VI Scientific and Practical Conference “Information-measuring technology and technologies”, Tomsk, Russia, 2015, pp. 149–154.
V. Vavilov et al., “Processing of the results of active thermal control by the wavelet-analysis method”, Defectoscopy, vol. 4, pp. 70–79, 2011.
V. Vavilov et al., “A complex approach to the development of the method and equipment for thermal nondestructive testing of CFRP cylindrical parts”, Composites Part B: Engineering, vol. 68, pp. 375–384, 2015. doi: j.compositesb.2014.09.007
G. Montavon et al., “Methods for interpreting and understanding deep neural networks”, Digital Signal Processing, vol. 73, pp. 1–15, 2018. doi: 10.1016/j.dsp.2017.10.011
X. Kuang et al., “Single infrared image stripe noise removal using deep convolutional networks”, IEEE Photonics J., vol. 9, pp. 57–67, 2017. doi: 10.1109/JPHOT.2017.2717948
I. Hubara et al., “Quantized back-propagation: Training binarized neural networks with quantized gradients”, in ICLR 2018 Workshop: 6th Int. Conf. Learning Representations, Vancouver Convention Center, Vancouver, BC, Canada, 2018, pp. 1–4.
V. Vavilov and D. Nesteruk, “Active thermal inspection of composite materials with the use of neural networks”, Russian Journal of Nondestructive Testing, vol. 2011, pp. 655–662, 2011. doi: 10.1134/S1061830911100160
J. Gu et al., “Recent advances in convolutional neural networks”, Pattern Recognition, vol. 77, pp. 354–377, 2018. doi: 10.1016/j.patcog.2017.10.013
S. Sojasi et al., “Infrared testing of CFRP components: Comparisons of approaches using the Tanimoto criterion”, in Proc. NDT in Canada 2015 Conference, Edmonton, Canada, 2015.
GOST Style Citations
- There are currently no refbacks.
Copyright (c) 2019 The Author(s)
This work is licensed under a Creative Commons Attribution 4.0 International License.