Abstract
The article is devoted to the problem of remote determination of the technical objects operability using a thermal imager. The structure of the information-measuring system is presented. It is proposed to use a hybrid model including a convolutional neural network and a fully connected neural network to identify defects exploring the surface temperature field of the test objects. The principles of constructing such a neural network are considered, and its parameters are investigated. Experimental studies of the developed system in the technical diagnosis of electronic devices were carried out.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Uvaysov, S.U., Yurkov, N.K.: Method for ensuring thermal control of radio engineering devices at the design stage. Bull. Samara Univ. Aerosp. Eng. Technol. Eng (7), 16–22 (2012)
Orlov, S.P., Vasilchenko, A.N.: Intelligent measuring system for testing and failure analysis of electronic devices. In: Proceedings of 19th IEEE International Conference on Soft Computing and Measurements (SCM’2016), vol. 1, pp. 401–403 (2016)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Haykin, S.: Neural networks and learning machines, 3rd edn, p. 905. Pearson Prentice Hall (2009)
Norvig, P., Rassell, S.: Artificial intelligence: a modern approach, 3rd edn, p. 1109. Pearson Prentice Hall (2010)
Nielsen, M.: Neural networks and deep learning. Free online book. http://neuralnetworksanddeeplearning.com (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097–1105. Curran Associated Inc. (2012)
Nair, V., Hinton, G.: Rectified linear units improve restricted Boltzmann machines. Proc. ICML 27, 807–814 (2010)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training reducing internal covariate shift. Cornell University Library. https://arxiv.org/abs/1502.03167v3 (2015)
Girin, R.V., Orlov, S.P.: Two-stage normalization of output signals of artificial neural networks. Bull. Samara State Tech. Univ. Techn. Sci. 56(4), 7–16 (2017)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representation by back-propagating errors. Lett. Nature 323, 533–536 (1986)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Orlov, S.P., Girin, R.V. (2020). Convolutional Neural Network Applied to Remote Technical Diagnosis by Thermograms. In: Jain, V., Patnaik, S., Popențiu Vlădicescu, F., Sethi, I. (eds) Recent Trends in Intelligent Computing, Communication and Devices. Advances in Intelligent Systems and Computing, vol 1006. Springer, Singapore. https://doi.org/10.1007/978-981-13-9406-5_81
Download citation
DOI: https://doi.org/10.1007/978-981-13-9406-5_81
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9405-8
Online ISBN: 978-981-13-9406-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)