Tula State University, Tula, Russia:

A. D. Gusev, Postgraduate Student, e-mail: dkines07@gmail.com

I. V. Tikhonova, Cand. Eng., Associate Professor, e-mail: tivtihonova@yandex.ru

Ya. A. Stakhanova, Graduate Student, e-mail: yana.stakhanova@mail.ru

This article raises a possibility of wider usage of neural network technology in material  science. Authors, via TIBCO STATISTICA, tried to build neural network prototype that can predictmicrohardness changes in heat-affected zone of steel sheets after laser cutting. The objects of research were different steel grades by GOST standard, such as Steel 35, Steel 45, U8A, 65G, 40Kh, 60S2KhA, 09G2S, 30KhGSA and 20Kh13. For neural network training, authors used data from various Tula State University researches about laser cutting parameters and hardness. With all this data, authors were able to create a neural network with predicting accuracy of 90 %. For easiness to use, neural network was unloaded from TIBCO STATISTICA and rebuilt in Pure Basic programming language. This program supports displaying multiple graphs and able to predict microhardness for all steel grades used in neural network training. Authors believe that with further adjustments and adding more details to program, it can be used to measure hardness of steel sheets with ease and more.

1. Usataya Т. V., Deryabina L. V., Kurzaeva L. V., Usatyi D. Yu. Application of VR/AR technologies in the design of metallurgical equipment. Chernye Metally. 2020. No. 9. pp. 56–61.
2. Marchand D., Abhinav J., Glensk A., Curtin W. A. Machine learning for metallurgy I. A neuralnetwork potential for Al-Cu. Physical review materials. 2020. Vol. 4. No. 10. pp. 1–21.
3. Stricker M., Binglun Y., Mak E., Curtin W. A. Machine learning for metallurgy II. A neural-network potential for magnesium. Physical review materials. 2020. Vol. 4. Iss. 10. pp. 1–20.
4. Abhinav J., Marchand D., Glensk A., Ceriotti M., Curtin W. A. Machine learning for metallurgy III: A neural network potential for Al-Mg-Si. Physical review materials. 2021. Vol. 5. No. 5. pp. 1–18.
5. Dragoni D., Daff T. D., Gάbor C., Marzari N. Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron. Physical review materials. 2018. Vol. 2. No. 1. pp. 1–16.
6. Sergeev N. N., Minaev I. V., Gvozdev А. Е. et. al. Influence of carbon content and laser cutting parameters on the structure and length of the heat-affected zone of steel sheets. Stal. 2018. No. 5. pp. 21–25.
7. Minaev I. V. Features of the formation of the structure and properties of carbon structural and tool steels during gas laser cutting: Dissertation … of Candidate of Engineering Sciences. Tula: Tulskiy gosudarstvenny pedagogicheskiy universitet imeni L. N. Tolstogo, 2021. 352 p.
8. Jebarri N., Jebari M. M., Saadallah F., Tarrats-Saugnac A., Bennaceur R., Longuemard J. P. Thermal affected zone obtained in machining steel XC42 by high-power continuous CO₂ laser. Optics and Laser Techonology. 2007. Vol. 40. pp. 864–873.
9. Boujelbene M., Alghamdi A. S., Miraoui I., Bayraktar E., Gazbar M. Effects of the laser cutting parameters on the micro-hardness and on the heat affected zone of the mi-hardened steel. International Journal of Advanced and Applied Sciences. 2017. Vol. 4. No. 5. pp. 19–25.
10. Parthiban A., Chandrasekaran M., Muthuraman V., Sathish S. Optimization of CO₂ laser cutting of stainless steel sheet curved profile. Materials Today: Proceedings. 2018. Vol. 5. pp. 14531–14538.
11. Gadrakhmanov A. T., Israphilov I. H., Shafigullin L. N., Gabdrakhmanova T. F. Study of laser cutting of low-alloy steel with using various gases. Journal of Physics. 2019. Vol. 1328. p. 012015.
12. Sergeev N. N., Sergeev А. N., Gvozdev А. Е. et. al. A complex of scientific, technical, design and technological developments for the creation, manufacture and implementation of highprecision import-substituting equipment for high-quality laser and flame processing of sheet metal: monograph. Tula: Izdatelstvo Tulskogo gosudarstvennogo universiteta. 2014. 188 p.
13. Sergeev N. N., Minaev I. V., Gvozdev А. Е. et. al. Methodology for selecting modes of laser cutting of structural steel sheets to provide the required complex of surface quality indicators. Materialovedenie. 2019. No. 10. pp. 25–32.

1. Usataya Т. V., Deryabina L. V., Kurzaeva L. V., Usatyi D. Yu. Application of VR/AR technologies in the design of metallurgical equipment. Chernye Metally. 2020. No. 9. pp. 56–61.
2. Marchand D., Abhinav J., Glensk A., Curtin W. A. Machine learning for metallurgy I. A neuralnetwork potential for Al-Cu. Physical review materials. 2020. Vol. 4. No. 10. pp. 1–21.
3. Stricker M., Binglun Y., Mak E., Curtin W. A. Machine learning for metallurgy II. A neural-network potential for magnesium. Physical review materials. 2020. Vol. 4. Iss. 10. pp. 1–20.
4. Abhinav J., Marchand D., Glensk A., Ceriotti M., Curtin W. A. Machine learning for metallurgy III: A neural network potential for Al-Mg-Si. Physical review materials. 2021. Vol. 5. No. 5. pp. 1–18.
5. Dragoni D., Daff T. D., Gάbor C., Marzari N. Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron. Physical review materials. 2018. Vol. 2. No. 1. pp. 1–16.
6. Sergeev N. N., Minaev I. V., Gvozdev А. Е. et. al. Influence of carbon content and laser cutting parameters on the structure and length of the heat-affected zone of steel sheets. Stal. 2018. No. 5. pp. 21–25.
7. Minaev I. V. Features of the formation of the structure and properties of carbon structural and tool steels during gas laser cutting: Dissertation … of Candidate of Engineering Sciences. Tula: Tulskiy gosudarstvenny pedagogicheskiy universitet imeni L. N. Tolstogo, 2021. 352 p.
8. Jebarri N., Jebari M. M., Saadallah F., Tarrats-Saugnac A., Bennaceur R., Longuemard J. P. Thermal affected zone obtained in machining steel XC42 by high-power continuous CO₂ laser. Optics and Laser Techonology. 2007. Vol. 40. pp. 864–873.
9. Boujelbene M., Alghamdi A. S., Miraoui I., Bayraktar E., Gazbar M. Effects of the laser cutting parameters on the micro-hardness and on the heat affected zone of the mi-hardened steel. International Journal of Advanced and Applied Sciences. 2017. Vol. 4. No. 5. pp. 19–25.
10. Parthiban A., Chandrasekaran M., Muthuraman V., Sathish S. Optimization of CO₂ laser cutting of stainless steel sheet curved profile. Materials Today: Proceedings. 2018. Vol. 5. pp. 14531–14538.
11. Gadrakhmanov A. T., Israphilov I. H., Shafigullin L. N., Gabdrakhmanova T. F. Study of laser cutting of low-alloy steel with using various gases. Journal of Physics. 2019. Vol. 1328. p. 012015.
12. Sergeev N. N., Sergeev А. N., Gvozdev А. Е. et. al. A complex of scientific, technical, design and technological developments for the creation, manufacture and implementation of highprecision import-substituting equipment for high-quality laser and flame processing of sheet metal: monograph. Tula: Izdatelstvo Tulskogo gosudarstvennogo universiteta. 2014. 188 p.
13. Sergeev N. N., Minaev I. V., Gvozdev А. Е. et. al. Methodology for selecting modes of laser cutting of structural steel sheets to provide the required complex of surface quality indicators. Materialovedenie. 2019. No. 10. pp. 25–32.