Intelligent Control of Technological Systems in Digital Manufacturing
| Authors: Kabaldin Y.G., Shatagin D.A., Anosov M.S., Kuzmishina A.M. | Published: 13.01.2020 |
| Published in issue: #1(718)/2020 | |
| Category: Mechanical Engineering and Machine Science | Chapter: Technology and Equipment for Mechanical and Physico-Technical Processing | |
| Keywords: adaptive control of a machine-tool, artificial intelligence, cutting process diagnostics, digital twin of a machine-tool |
This paper presents an analysis of the development of adaptive control systems for CNC machines. It is shown that the construction of systems for optimal control of machining processes is based on such approaches as artificial intelligence, genetic algorithms for optimizing processing modes, expert systems for knowledge accumulation, cloud technologies and the development of digital twins of the equipment. An adaptive system of intelligent control of a CNC machine is developed based on training of a neural network model, which can improve the quality of machining parts and reduce the wear of the cutting tool.
References
[1] Balakshin B.S. Adaptivnoye upravleniye stankami [Adaptive machine control]. Moscow, Mashinostroyeniye publ., 1973. 668 p.
[2] Kol’tsov A.G. Upravleniye stankami i stanochnymi kompleksami [Management of machine tools and machine complexes]. Omsk, OmSTU publ., 2007. 56 p.
[3] Fomin V.N., Fradkov A.L., Yakubovich V.N. Adaptivnoye upravleniye dinamicheskimi ob”yektami [Adaptive dynamic object management]. Moscow, Nauka publ., 1981. 448 p.
[4] Yadykin I.B., Shumskiy V.M., Ovsepyan F.A. Adaptivnoye upravleniye nepreryvnymi tekhnologicheskimi protsessami [Adaptive Continuous Process Management]. Moscow, Energoatomizdat publ., 1984. 240 p.
[5] Kozlov Yu.M., Yusupov R.M. Bespoiskovyye samonastraivayushchiyesya sistemy [Searchless, self-tuning systems]. Moscow, Nauka publ., 1969. 455 p.
[6] Kuropatkin P.V. Optimal’nyye i adaptivnyye sistemy [Optimal and adaptive systems]. Moscow, Vysshaya shkola, 1980. 287 p.
[7] Churakov E.P. Optimal’nyye i adaptivnyye sistemy [Optimal and adaptive systems]. Moscow, Energoizdat publ., 1987. 256 p.
[8] Metody robastnogo, neyro-nechetkogo i adaptivnogo upravleniya [Robust, neuro-fuzzy and adaptive control methods]. Ed. Egupov N.D. Moscow, Bauman Press, 2002. 744 p.
[9] Izerman R. Tsifrovyye sistemy upravleniya [Digital control systems]. Moscow, Mir publ., 1984. 541 p.
[10] Yaruta S.P., Usachev P.A. Principles of creation of adaptive process control for CNC machine tools. Modern scientific researches and innovations, 2012, no. 4 (in Russ.). Available at: http://web.snauka.ru/issues/2012/04/11652 (accessed 26 Mach 2019).
[11] Iskusstvennyy intellekt i kiber-fizicheskiye mekhanoobrabatyvayushchiye sistemy v tsifrovom proizvodstve [Artificial Intelligence and Cyber-Physical Machining Systems in Digital Production]. Ed. Kabaldin Yu.G. Nizhniy Novgorod, NNSTU publ., 2018. 271 p.
[12] Kabaldin Yu.G., Bilenko S.V., Seryy S.V. Upravleniye dinamicheskimi protsessami v tekhnologicheskikh sistemakh mekhanoobrabotki na osnove iskusstvennogo intellekta [Control of dynamic processes in technological systems of machining based on artificial intelligence]. Komsomolsk-on-Amur, KnASU publ., 2003. 201 p.
[13] Shitikov V.K., Mastitskiy S.E. Klassifikatsiya, regressiya i drugiye algoritmy Data Mining s ispol’zovaniyem R [Classification, Regression, and Other Data Mining Algorithms Using R]. 2017. 351 p. Available at: https://github.com/ranalytics/data-mining
[14] Frankel A., Larsson J. There is a better way: a digital double increases the efficiency of the processes of design and technological design and production. SAD/CAM/CAE Observer, 2016, no. 3, pp. 36–40 (in Russ.).
[15] Namiot D.E. Time series databases for Internet of Things. Applied informatics, 2017, vol. 12, no. 2(68), pp. 79–87 (in Russ.).
[16] Perspektivy razvitiya kiberfizicheskikh proizvodstvennykh system [Prospects for the deve-lopment of cyber physical production systems]. Available at: https://controlengrussia.com/innovatsii/robototehnika/kiberfizicheskie-sistemy/ (accessed 14 June 2016).
[17] Kabaldin Yu.G., Shatagin D.A., Anosov M.S., Kuz’mishina A.M. Development of digital twin of CNC unit based on machine learning methods. Vestnik of Don State Technical University, 2019, vol. 19, no. 1, pp. 45–55 (in Russ.), doi: https://doi.org/10.23947/1992-5980-2019-19-1-45-55
[18] Kabaldin Yu.G., Shatagin D.A., Kolchin P.V., Mansurov R.Sh. Modular design of machine-tool equipment as cyber-physical systems based on artificial intelligence and cloud technologies for digital productions. Vestnik mashinostroyeniya, 2019, no. 1, pp. 7–15 (in Russ.).
