All-Russian Scientific and Research Institute of Tube Industry - RosNITI (Chelyabinsk, Russia):

D. Yu. Zvonarev, Cand. Eng., Senior Researcher, e-mail: zvonarev@rosniti.ru
A. V. Vydrin, Dr. Eng., Prof., Deputy General Director on Scientific Work, e-mail: vydrinav@rosniti.ru

Taganrog Metallurgical Plant – Tagmet (Taganrog, Russia)
V. L. Neroznikov, Head of tube Laboratory

In existing practice, analytical dependencies that are general in nature and do not take into account the characteristics of a particular piercing mill are used to determine the settings for piercing mills. Therefore, it is possible to set the required setting both at the first attempt and by clarifying the calculated setting by piercing several tuning billets. The latter leads to the increased consumption of metal. It is possible to exclude metal losses during the piercing mill setting using modern digital technologies, including BigData and artificial intelligence technologies. Technologies are based on a systematic and continuous analysis of data from production units in order to obtain the basis for decision-making. An artificial neural network can be used as the basis of artificial intelligence.

1. Osadchy V. Ya., Vavilin А. S., Zimovets V. G., Kolikov А. P. Technology and equipment for pipe production: a tutorial for universities. Moscow: Intermet Inzhiniring, 2007. 560 p.
2. Danchenko V. N., Kolikov А. P., Romantsev B. A., Samusev S. V. Pipe technology. Moscow: Intermet Inzhiniring, 2002. 640 p.
3. Chernyshev Yu. М., Bolotov А. V., Starogorodtsev V. P., Shamilov А. R. et. al. Expansion of assortment and improvement of the quality of pipes on the TRM piercing mill. 220. Stal. 2018. No. 1. pp. 42–45.
4. Romantsev B. А., Gocharuk А. V., Vavilkin N. М., Samusev S. V. Plastic metal working: tutorial. Moscow: Izdatelsky dom MISiS, 2008. 960 p.
5. Lu Lu, Zhi Chun Jie. Shear stresses and velocity analysis of piercing process in Discher’s mill using Finite Element Method. Advances in Engineering Research. 2017. Vol. 113. pp. 753–757.
6. Mulchin V. V., Vydrin А. V., Korol А. V., Kuryatnikov А. V. et. al. Determination of setup parameters on piercing mills with guiding drive disks (Disher mills). Stal. 2010. No. 8. pp. 68–70.
7. Kuryatnikov А. V., Korol А. V., Korsakov А. А. Development of computer programs for calculating setup parameters of piercing mills. Proceedings of XX anniversary scientific and technical conference «Tubes-2012». Proceedings of JSC RosNITI. 2012. Part II. pp. 41–43.
8. Installations for production of seamless pipes. Key Technologies for Success. SMS group GmbH. Mönchengladbach, 2007. 18 p.
9. Tagmet JSC official website. [Electronic resource]. Available at: https://tagmet.tmk-group.ru/tagmet_powers (accessed: 25.07.2019).
10. Schneppe U. Technological and digital networks for management of hot rolling mill in Hagen. Chernye Metally. 2017. No. 9. pp. 53–57.
11. d`Hone F. SMS digital technologies for sizing mills. Chernye Metally. 2018. No. 1. pp. 42–44.
12. Reifferscheid М. Ideas, techniques and decisions for application of digital technologies in ferrous metallurgy. Chernye Metally. 2018. No. 6. pp. 62–67.
13. Dobrzanski L. A., Honysz R. Application of artificial neural networks in modeling of normalized structural steels mechanical properties. Journal of Achievements in Materials and Manufacturing Engineering. 2009. Vol. 32. Is. 1. pp. 37–45.
14. Vydrin А. V., Ashenbreyner А. О., Bunyashin М. V. Casing collapse pressure prediction methods for HighCollapse casing pipes with increased crush resistance. Proceedings of the International scientific and technical congress «OMD 2014. Fundamental issues. Innovation materials and technologies». Part 2.Moscow: «Belyi veter» JSC. 2014. pp. 47–51.
15. DARPA Neural Network Study, AFCEA International Press, 1988.
16. Smith L. An Introduction to Neural Networks. Unpublished draft, University of Stirling, 2001. [Electronic resource]. Available at: http://www.cs.stir.ac.uk/~lss/NNIntro/InvSlides.html (accessed: 25.07.2019).