Memory-centric models of industrial robots control systems

Machine-building Engineering and Machine Science


DOI: 10.34759/vst-2021-4-245-256

Аuthors

Zelenskii A. A.*, Ilyukhin Y. V.**, Gribkov A. A.***

Moscow State University of Technology "STANKIN", 1, Vadkovsky lane, Moscow, 127994, Russia

*e-mail: zelenskyaa@gmail.com
**e-mail: y.ilyukhin@stankin.ru
***e-mail: a.gribkov@stankin.ru

Abstract

The article recounts the significance of real-time traffic control systems for global competitiveness and technological security ensuring amidst the fourth industrial revolution realization. As far as the growth potential of computers elements base running speed is close to exhaustion, and further development in this trend is being associated with significant technical complexions and economic efficiency reduction, computers architecture improvement should be considered as the main trend of the computer productivity increasing. The article considered pressing tasks of the computations productivity increasing, which may be solved at the cost of computers architecture improvement. These tasks include the processed data flow volume reduction; increasing data transmission speed between computer elements; eliminating queues while several computing devices simultaneously accessing the same memory. The authors propose conceptual model of the industrial robot movement control based on the analysis of the possible ways of the set problems solving. The problem of the processed data flow reduction is being solved in the system built according to the conceptual model being proposed by application of extra computing modules, such as coprocessors and accelerators, performing parallel computing. The main portion of computations herewith is being performed without control from the system core. The problem of data transmission speed increasing between the system functional elements and blocks is being solved by the memory-centric architecture employing, with which all devices requiring high speed of data exchange with memory for their operation, are being integrated into the memory. The queues elimination problem is being solved by dynamic random access memory (DRAM) splitting into local areas accessible only by a single device. Interaction between devices is being implemented in the high-speed static random access memory (SRAM) employing minimum data volumes, as well as through the communication network ensuring direct communication between the devices without delays occurrence. The actor instrumental model, ensuring emulation of parallel computing and functional modules interaction, is being selected to describe the industrial robot movement control system operation built according to the presented conceptual model.

Keywords:

gas turbine, cooled blades, blade airfoil leading edge, cyclonic cooling, thermo-hydraulic processes

References

  1. O Strategii nauchno-tekhnologicheskogo razvitiya Rossiiskoi Federatsii. Ukaz Prezidenta Rossiiskoi Federatsii ot 01.12.2016, ¹ 642 (On Strategy of Scientific and Technological Development of the Russian Federation. Decree of the President of the Russian Federation dated 01.12.2016 no. 642). URL: http://www.kremlin.ru/acts/bank/41449
  2. Grishin D. V. Development of effective forms of production process stuffing in aircraft building industry. Aerospace MAI Journal, 2018, vol. 25, no. 1, pp. 209-219.
  3. Rebrov S.G., Yanchur S.V., Drondin A.V., Zernov O.D. Developing the concept of solar energy units robotic assembly in orbit. Aerospace MAI Journal, 2019, vol. 26, no. 1, pp. 201-211.
  4. Tay S., Chuan L., Aziati A., Ahmad A. An Overview of Industry 4.0: Definition, Components, and Government Initiatives. Journal of Advanced Research in Dynamical and Control Systems, 2018, vol. 10, special issue 14, pp. 1379-1387.
  5. Leiserson C.E., Thompson N.C., Emer J.S. et al. There’s plenty of room at the Top: What will drive computer performance after Moore’s law? Science, 2020, vol. 368, no. 6495. DOI: 10.1126/ science.aam9744
  6. Flynn M. Some Computer Organizations and Their Effectiveness. IEEE Transactions on Computers, 1972, vol. 21, no. 9, pp. 948-960. DOI: 10.1109/ TC.1972.5009071
  7. Ezhova N.A., Sokolinskii L.B. Vestnik YuUrGU. Seriya Vychislitel’naya matematika i informatika, 2019, vol. 8, no. 3, pp. 58-91. DOI: 10.14529/cmse190304
  8. Connolly M. A Programmable Processing-in-Memory Architecture for Memory Intensive Applications. Master’s Thesis on Computer Engineering. Rochester Institute of Technology, 2021, 42 p.
  9. Ghose S., Hsieh K., Boroumand A., Ausavarungnirun R., Mutlu O. Enabling the Adoption of Processing-in-Memory: Challenges, Mechanisms, Future Research Directions. 2018, 45 p. URL: CoRR abs/1802.00320
  10. Bakhur V. Intel predstavila bol’shie arkhitekturnye izmeneniya v novykh pokoleniyakh protsessorov, 2021. URL: https://www.cnews.ru/news/line/2021-08-19_intel_predstavila_bolshie_arhitekturnye
  11. Estefan J.A. Survey of model-based systems engineering (MBSE) methodologies. Incose MBSE Focus Group, 2008, 70 p. URL: http:// www.omgsysml.org/MBSE_Methodology_ Survey_RevB.pdf
  12. Suh S.H., Kang S.K., Chung D.H., Stroud I. Theory and design of CNC systems. Springer Science & Business Media, 2008, 476 p.
  13. Zelenskii A.A., Khar’kov M.A., Ivanovskii S.P., Abdullin T.Kh. Vestnik Voronezhskogo gosudarstvennogo tekhnicheskogo universiteta, 2018, vol. 14, no. 5, pp. 8-12.
  14. Martinov L.I., Martinov G.M. Mekhatronika, avtomatizatsiya, upravlenie, 2010, no. 11, pp. 50-55.
  15. Fu K.S., Gonzalez R.C., Lee C.S.G. Robotics: Control, Sensing, Vision, and Intelligence. Mcgraw-Hill Book Company, 1987, 580 p.
  16. Ruishu Z., Chang Z., Weigang Z. The status and development of industrial robots. 4th International Conference on Applied Materials and Manufacturing Technology (25–27 May 2018, Nanchang, China), 2018, vol. 423, no. 1. DOI: 10.1088/1757-899X/423/ 1/012051
  17. Romanov A.M. Rossiiskii tekhnologicheskii zhurnal, 2019, vol. 7, no. 5(31), pp. 30–46. DOI: 10.32362/2500-316X-2019-7-5-30-46
  18. Zelenskii A.A., Abdullin T.Kh., Ilyukhin Yu.V., Khar’kov M.A. STIN, 2019, no. 8, pp. 5-8.
  19. Ilyukhin Yu.V. Mekhatronika, 2000, no. 2, pp. 7-12.
  20. Zelenskii A.A., Pismenskova M.M., Voronin V.V. Control of collaborative robot systems and flexible production cells on the basis of deep learning. Russian Engineering Research, 2019, vol. 39, no. 12, pp. 1065-1068. DOI:10.3103/S1068798X19120256
  21. Modeli parallel’nykh vychislenii. URL: http://www.ccas.ru/paral/prog/models.html
  22. Zelenskii A.A., Shadrin N.G., Abdullin T.Kh.,Khar’kov M.A. Vestnik komp’yuternykh i informatsionnykh tekhnologii, 2019, no. 11, pp. 46-52.
  23. Popova N.V. Matematicheskie metody: elektronnyi uchebnik (Mathematical methods: electronic textbook), 2005. URL: http://matmetod-popova.narod.ru/Index1.htm
  24. Burgin M. Systems, Actors and Agents: Operation in a multicomponent environment. 2017, 28 p. URL: arXiv:1711.08319
  25. Rinaldi L., Torquati M., Mencagli G., Danelutto M., Menga T. Accelerating Actor-based Applications with Parallel Patterns. 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, 2019, pp 140-147. DOI: 10.1109/ EMPDP.2019.8671602
  26. Shah V., Vaz Salles M.A. Reactors: A case for predictable, virtualized actor database systems. International Conference on Management of Data, 2018, pp. 259-274. DOI: 10.1145/3183713.3183752
  27. Lohstroh Ì., Menard Ñ., Bateni S., Lee E. Toward a Lingua Franca for Deterministic Concurrent Systems. ACM Transactions on Embedded Computing Systems, 2021, vol. 20, no. 4, pp. 1-27. DOI:10.1145/3448128
  28. Laigner R., Lifschitz S., Kalinowski M., Poggi M., Vaz Salles M.A. Towards a Technique for Extracting Relational Actors from Monolithic Applications. Anais do XXXIV Simpósio Brasileiro de Banco de Dados, 2019, pp. 133-144. DOI: 10.5753/sbbd.2019.8814

mai.ru — informational site of MAI

Copyright © 1994-2024 by MAI