A neural network that takes into account the physical phenomena accompanying the cutting process

Authors

  • N. Ravskaya Igor Sikorsky Kyiv Polytechnic Institute, Kyiv, Ukraine
  • A. Klochko National Technical University «Kharkiv Polytechnic Institute», Ukraine
  • A. Zakovorotny National Technical University «Kharkiv Polytechnic Institute», Ukraine
  • I. Korbut Igor Sikorsky Kyiv Polytechnic Institute, Kyiv, Ukraine https://orcid.org/0000-0002-1221-4052
  • P. Rodin Igor Sikorsky Kyiv Polytechnic Institute, Kyiv, Ukraine

DOI:

https://doi.org/10.20535/2521-1943.2020.89.188954

Keywords:

neural networks, ANN, MINS, argument accounting method

Abstract

The article deals with the application of artificial neural networks to control the cutting process. The issues of improving the control accuracy of the system and the need to create an ANN based on the phenomena accompanying the cutting process are considered. The creation of such ANN is an urgent problem and is of great practical importance. The article shows that despite the fact that MINS allows solving problems of image classification, which are often not formalized or difficult to formalize, this method is not applicable for obtaining models of the cutting process in order to predict the phenomena accompanying it and optimize the conditions for carrying it out. To solve such problems, it is advisable to use group argument accounting method

References

  1. Jimmy, W.Key (2016), “Artificial neural networks for control of technological processes. Part 1”, Control Engineering, vol. 63, no. 3, pp. 62–66.
  2. Ravskaya, N.S. and Kovaleva, L.I. (2002), “Application of self-organization methods to identify processes and objects”, Lucrarile stiintifice all simpozion lui international, Universitario Ropet, Inginerie Mecanica, Petrosani, Focus.
  3. Dyubner, L.G., Skrynnik, P.V. and Kovaleva, L.I. (2004), “Osnovnye polozheniya algoritma dlya modelirovaniya protsessa rezaniya s uchetom fizicheskikh yavlenii, ego soprovozhdayushchikh”, Nadijnistʹ instrumentu ta optymyzacija texnolohičnyx system, DDMА, no. 15.
  4. Zakovorotny, O.Yu., and Dmitrienko, V.D. (2015), “Avtomatizatsiya analiticheskikh preobrazovanii geometricheskoi teorii upravleniya”, Energeticheskie i elektrotekhnicheskie sistemy, no. 2.
  5. Ivakhnenko, A.G. (1971), Sistemy evristicheskoi samoorganizatsii v tekhnicheskoi kibernetike [Systems of heuristic self-organization in technical cybernetics], Tekhnika, Kiev, Ukraine.
  6. Ivakhnenko, A.G. and dr. (1976), Prinyatie reshenii na osnove samoorganizatsii [Self-organizing decision making], Sov. Radio, Moscow, Russia.
  7. Kruglov, V.V. and Borisov, V.V. (2001), Iskusstvennye neironnye seti [Artificial neural networks], Teoriya i praktika, Goryachaya liniya, Telekom, Moscow, Russia.
  8. Rosenblatt, F. (1965), Printsipy neirodinamiki: Pertseptrony i teoriya mekhanizmov mozga [Principles of neurodynamics: Perceptrons and the theory of brain mechanisms], Mir, Moscow, Russia.
  9. Vasiliev, V.I. (1988), Raspoznayushchie sistemy [Recognition systems], Naukova dumka, Kiev, Ukraine.
  10. Milokost, І.O. (2016), “Adjustment of the openings in case of drilling thin virobes from orthotronic carbon fiber reinforced plastics”, dis. cand. tech. sciences: 05.06.01, Kiev, Ukraine.
  11. Rodin, R.P., Ravskaya, N.S. and Kas'yanov, A.I. (1965), Monolitnye tverdosplavnye kontsevye frezy [Solid Carbide End Mills], Vyshcha shkola, Kiev, Ukraine.

Published

2020-09-01

How to Cite

[1]
N. Ravskaya, A. Klochko, A. Zakovorotny, I. Korbut, and P. Rodin, “A neural network that takes into account the physical phenomena accompanying the cutting process”, Mech. Adv. Technol., no. 2(89), Sep. 2020.

Issue

Section

Up-to-date machines and the technologies of mechanical engineering