Neural Network Model for Assessing the Physical and Mechanical Properties of a Metal Material Based on Deep Learning

Andrei Kliuev, Roman Klestov, Valerii Stolbov

Cite: Kliuev A., Klestov R., Stolbov V. Physical and Mechanical Properties of a Metal Material Based on Deep Learning. J. Digit. Sci. 2(1), 18 – 28 (2020).

Abstract. The paper investigates the algorithmic stability of learning a deep neural network in problems of recognition of the materials microstructure. It is shown that at 8% of quantitative deviation in the basic test set the algorithm trained network loses stability. This means that with such a quantitative or qualitative deviation in the training or test sets, the results obtained with such trained network can hardly be trusted. Although the results of this study are applicable to the particular case, i.e. problems of recognition of the microstructure using ResNet-152, the authors propose a cheaper method for studying stability based on the analysis of the test, rather than the training set.

Keywords: Deep neural networks, material microstructure, image recognition, deep learning, algorithmic stability.

1. Gitman M.B., Klyuev A.V., Stolbov V.Y., Gitman I.M. Complex Estimation of Strength Properties of Functional Materials on the basis of the Analysis of Grain-Phase Structure Parameters // Strength of Materials. 2017. Vol. 49. No.5. – PP. 710-717.
2. Kliuev A., Klestov R., Bartolomey M., Rogozhnikov A. (2019) Recommendation System for Material Scientists Based on Deep Learn Neural Network. In:   DSIC 2018. Advances in Intelligent Systems and Computing. vol 850, pp. 216-223.Springer, Cham.
3. Vapnik V. N., Chervonenkis A. YA. Teoriya raspoznavaniya obrazov / M.: Nauka (1974).
4. Bousquet O., Elisseeff A. Algorithmic Stability and Generalization Performance. Advances in Neural Information Processing Systems. 13, 196-202 (2001). 
5. Bousquet O., Elisseeff A. Stability and Generalization. Journal of Machine Learning Research. 2, 499-526 (2002).
6. Jason Brownlee (2019) Impact of Dataset Size on Deep Learning Model Skill and Performance Estimates [Digital resource]. URL ( (Request date 04.02.2019).
7. Junghwan Cho, Kyewook Lee, Ellie Shin, Garry Choy, Synho Do (2015) How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?  arXiv:1511.06348 – 2015.- preprint arXiv.
8. LeCun Y., Boser B., Denker J. S., Henderson D., Howard R. E., Hubbard W.  and Jackel L. D.: Backpropagation Applied to Handwritten Zip Code Recognition, Neural Computation, 1(4):541-551, (1989).
9.  Szegedy Christian, Liu Wei, Jia Yangqing, Sermanet Pierre, Reed Scott, Anguelov Dragomir,  Erhan Dumitru, Vanhoucke Vincent, Rabinovich Andrew: Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 1-9 (2015).
10. Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun: Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp.770-778 (2016).
11. Jie Hu, Li Shen, Gang Sun: Squeeze-and-Excitation Networks. ILSVRC 2017 image classification winner. arXiv:1709.01507 (2017).
12. Brian L. DeCost, Toby Francis, Elizabeth A. Holm: Exploring the microstructure manifold: image texture representations applied to ultrahigh carbon steel microstructures. Acta Materialia. 133, 20-40 (2017).
13. Azimi S. M., Britz D., Engstler M., Fritz M., Mücklich F.: Advanced Steel Microstructure Classification by Deep Learning Methods. arXiv: 1706.06480 (2017).
14. G.V. Aristov, A.V. Klyuev: Detection and classification metal’s and alloy’s microstructure using deep neural network. Proceeding of 27th International conferencion of computer graphics and machine vision GraphiCon. p.180-183 (2017)
15. Masci J., Meier U., Ciresan D., Schmidhuber J., Fricout G.: Steel defect classification with Max-Pooling Convolutional Neural Networks. The 2012 International Joint Conference on Neural Networks (IJCNN), pp.1-6-131 (2012).
16. Shiyang Zhou, Youping Chen, Dailin Zhang, Jingming Xie, Yunfei Zhou: Classification of surface defects on steel sheet using convolutional neural networks. Materiali in tehnologije, vol.51, pp. 123 (2017).
17. Soukup D., Huber-Mork R.: Convolutional Neural Networks for Steel Surface Defect Detection from Photometric Stereo Images. ISVC 2014: Advances in Visual Computing, pp. 668-677 (2014).
18. Faghih-Roohi S., Hajizadeh S., Nu´nez A., Babuska R., De Schutter B.: Deep convolutional neural networks for detection of rail surface defects. Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN 2016), pp. 2584–2589 (2016).
19. Goodfellow Ian J., Pouget-Abadie Jean, Mirza Mehdi, Xu Bing, Warde-Farley David, Ozair Sherjil, Courville Aaron, Bengio Yoshua: Generative Adversarial Networks. arXiv:1406.2661 (2014).
20. Alec Radford, Luke Metz, Soumith Chintala: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks.      arXiv:1511.06434 (2015).
21. Gatys L. A., Ecker A. S., Bethge M.: Texture synthesis and the controlled generation of natural stimuli using convolutional neural networks. arXiv:1505.07376 (2015).
22. Nicholas Lubbers, Turab Lookman, Kipton Barros: Inferring low-dimensional microstructure representations using convolutional neural networks. arXiv:1611.02764v1 (2016).
23. Klyuev A.V., Stolbov V.Y., Gitman M.B., Klestov R.A. (2020) Stability of the Deep Neural Networks Learning Process in the Recognition Problems of the Material Microstructure. In:  ICIS 2019. Lecture Notes in Networks and Systems, vol 78. pp. 307-313. Springer, Cham. DOI: 10.1007/978-3-030-22493-6_27.     
24. Klestov R., Klyuev A., Stolbov V. About some approaches to problem of metals and alloys microstructures classification based on neural network technologies .Advances in Engineering Research.157, 292-296 (2018).
25.  Gitman I.M., Klyuev A.V., Gitman M.B. and Stolbov V.Yu. Multi-scale Approach for Strength Properties Estimation in Functional Materials. ZAMM Zeitschrift fur Angewandte Mathematik und Mechanik, vol.98. No.6. 945-953 (2018).

Published online 29.05.2020