To autonomous control of technical state of machine tools

Introduction. At present, developers and researchers focus on the automated maintenance of the machine performance, especially under the conditions of the production computerization. The opportunities for assessing technical state of the equipment, fault diagnostics and monitoring are greatly expanded. This allows preventing failures and minimizing the impact of disadvantages on the performance. For this purpose, some autonomous control system is developed. Its conceptual problems are discussed in this paper.

Materials and Methods. The autonomous control system of the machine technical state is considered. It is shown that signals from the sensors and to the actuating mechanisms arrive through the distributed control nodes of the technical state of the machine devices. Therewith, proper communication is provided by e-MindMachine. Generalized functions for managing the technical state of metal cutting machines include the decision making and command execution involving built-in facilities. The specificities in the construction of the machine maintenance system are described and explained. As a result, the following statement is established: when analyzing processes in the machine tools and in the solution synthesis for controlling the machine maintenance (MM), methods of artificial intelligence and intellectual control (including the theory of fuzzy sets and fuzzy logic) are adequate.

Research Results. This approach accumulates the achievements presented in the known maintenance systems of various machines, and it raises the service factor up to the independently operating systems of the automated autonomous control of the machine technical state. The system structure, the generalized control functions of which include the decision making and command execution using the built-in means, is considered. It is shown how methods of the theory of fuzzy sets and fuzzy logic are used in the solution synthesis for control. The incremental development and implementation of the autonomous system depending on the condition and capability of an enterprise are recommended.

Discussion and Conclusions. The issues on introducing the autonomous MM control system are considered. Appropriate methods for determining the sequencing of operations and evaluation of the performance are offered. The monitoring subsystem provides, firstly, the implementation of the traditional diagnostics under monitoring the machine state on-line. Secondly, it is supposed to perform the following functions: evaluation of the diagnostic results, and forecasting and decision making – in order to control the actions preventing damage to the device (or the machine as a whole).

1. Мальцев, А. И. Мониторинг технического состояния крупных машин / А. И. Мальцев, А. А. Мальцев. — Электросталь : ДАМО, 1998. — 62 с.

2. ГОСТ Р ИСО 17359-2009. Контроль состояния и диагностика машин. Общее руководство по организации контроля состояния и диагностирования / Межгосударственный Совет по стандартизации, метрологии и сертификации. —Москва : Стандартинформ, 2010. — 20 с.

3. Никитин, Ю. P. О построении системы диагностирования станков с ЧПУ / Ю. P. Никитин, И. В. Абрамов // Мехатроника, автоматизация и управление. — 2011. — № 4. — С. 32–35.

4. Muller, A. Proactive maintenance for industrial system operation based on a formalised prognosis process /

5. Muller, M.-C. Suhner, B. Iung // Reliability Engineering and System Safety. — 2006. — Vol. 93. — P. 234–253.

6. Intelligent prognostics tools and e-maintenance / J. Lee [et al.] // Computers in Industry. — 2006. — Vol. 57. — P. 476–489.

7. Djurdjanovic, D. Watchdog Agent — an infotronics-based prognostics approach for product performance degradation assessment and prediction / D. Djurdjanovic, J. Lee, J. Ni // Advanced Engineering Informatics. — 2003. — № 17 (3). — P. 109–125.

8. Moore, W.-J. An intelligent maintenance system for continuous cost-based prioritisation of maintenance activities / W.-J. Moore, A.-G. Starr // Computers in Industry. — 2006. — Vol. 57. — P. 595–606.

9. Круглова, Т. Н. Диагностирование и прогнозирование технического состояния мехатронных модулей движения технологического оборудования / Т. Н. Круглова, Н. А. Глебов. — Новочеркасск : ЮРГТУ, 2011. — 120 с.

10. E-Maintenance update: the road to success for modern industry / C. Emmanouilidis [et al.] // Proceedings of the 24th International Congress on condition monitoring and diagnostic engineering management, 2011. – Birmingham : COMADEM International, 2011. — 423 p.

11. Wang, P. Fault prognostics using dynamic wavelet neural networks / P. Wang, G. Vachtsevanos // Artificial Intelligence for Engineering Design, Analysis and Manufacturing. — 2001. — Vol. 15. — P. 349–365.

12. Zhang, W. An agent-based platform for service integration in E-maintenance / W. Zhang, W. Halang, C. Diedrich // Proceedings of ICIT 2003, IEEE international conference on industrial technology. — Piscataway Township : IEEE, 2003. — Vol. 1. — P. 426–33.

13. Lee, J. E-manufacturing: fundamental, tools, and transformation / J. Lee // Robotics and Computer-Integrated Manufacturing. — 2003. — № 19 (6). — P. 501–507.

14. MIMOSA — four years later / J. Mitchell [et al.] // The Journal of Sound and Vibration. — 1998. — Vol. 11. —P. 12–21.

15. Prognostics and health management design for rotary machinery systems — Reviews, methodology and applications / J. Lee [et al.] // Mechanical Systems and Signal Processing. — 2014. — Vol. 42. — P. 314–334.

16. Xiangang Cao. Development of SOA Based Equipments Maintenance Decision Support System / Xiangang Cao, Pingyu Jiang // ICIRA: International Conference on Intelligent Robotics and Applications. — Berlin ; Heidelberg : Springer-Verlag, 2008. — Part II, vol. 5315. — P. 576–582. 65

17. Rissland, E.-L. Combining case-based and rule-based reasoning: A heuristic approach / E.-L. Rissland, D. B. Skala // IJCAI-89 : Proceedings of the 11th international joint conference on Artificial intelligence. — San Francisco : Morgan Kaufmann Publishers Inc., 1989. — Vol. 1. — P. 524–530.

18. Erl, T. Service-oriented Architecture: Concepts, Technology, and Design / T. Erl. — New Jersey : Prentice Hall, 2005. — 764 p.

19. PROTEUS — An integration platform for distributed maintenance systems / T. Bangemann [et al.] // Computers in Industry : Special issue on e-maintenance. — 2006. — № 57 (6). — P. 539–551.

20. Thurston, M. Standards Developments for Condition-Based Maintenance Systems / M. Thurston, M. Lebold // New Frontiers in Integrated Diagnostics and Prognostics : Proceedings of the 55th Meeting of the Society for Machinery Failure Prevention Technology. — Virginia Beach : Defense Technical Information Center, 2001. — P. 363–373.

21. A component based system for S-maintenance / M.-H. Karray [et al.] // 9th IEEE International Conference on Industrial Informatics, INDIN’11. — Caparica ; Lisbon : HAL, 2011. — P. 1–8.

22. Muller, A. On the concept of e-maintenance: Review and current research / A. Muller, C. Marquez, B. Iung // Journal of Reliability Engineering and System Safety. — 2008. — Vol. 93. — P. 1165–1187.

23. Соловьева, Н. Инструмент для соблюдения сроков / Н. Соловьева // Силовые машины. — 2013. — № 14. —С. 4.

24. ГОСТ Р ИСО 13379-2009. Контроль состояния и диагностика машин. Руководство по интерпретации данных и методам диагностирования / Научно-исследовательский центр контроля и диагностики технических систем ; Технический комитет по стандартизации ТК 183 «Вибрация, удар и контроль технического состояния»; Федеральное агентство по техническому регулированию и метрологии. — Москва : Стандартинформ, 2010. — 27 с.

25. Тугенгольд, А. К. Модуль E-Mindmachine в интеллектуальной системе мониторинга станка / А. К. Тугенгольд, Р. Н. Волошин, С. В. Ющенко // Международный научно-исследовательский журнал. — 2015. — № 9 (40), ч. 2. — С. 100–102.

26. Monitoring and Control of Tools in Multifunctional Machine Tools / A. K. Tugengold [et al.] // Russian Engineering Research. — 2017. — Vol. 37, № 5. — P. 440–446.

27. Тугенгольд, А. К. Гибкий мониторинг мехатронных технологических машин / А. К. Тугенгольд, Р. Н. Волошин // Вестник Дон. гос. техн. ун-та. — 2016. — № 4. — С. 51–58.

28. Monitoring of Machine Tools / A. K. Tugengold [et al.] // Russian Engineering Research. — 2017. — Vol. 37, № 8. — P. 440–446.

29. Пуш, В. Э. Автоматические станочные системы / В. Э. Пуш, Р. Пигерт, В. Л. Сосонкин. — Москва : Машиностроение, 1982. — 319 с.

30. Структура и алгоритм работы системы диагностики состояния многооперационного станка [Электронный ресурс] / А. В. Ядченко [и др.] // Современные научные исследования и разработки. — 2017. — № 8 (8). — С. 230–237. — Режим доступа : http://olimpiks.ru/d/1340546/d/vypusk_88.pdf.

31. Аппаратное и программное обеспечение для станка ROBOCUT FANUC [Электронный ресурс] / FANUC. — Режим доступа: http://www.fanuc.eu/ru/ru/robocut-ib/опции-для-станков-robocut (дата обращения 10.10.17).

32. ГОСТ Р ИСО 13379-1-2015. Контроль состояния и диагностика машин. Методы интерпретации данных и диагностирования. Часть 1. Общее руководство / Федеральное агентство по техническому регулированию и метрологии. — Москва : Стандартинформ, 2016. — 33 с.

33. ГОСТ Р ИСО 13381-1-2016. Контроль состояния и диагностика машин. Прогнозирование технического состояния. Часть 1. Общее руководство / Научно-исследовательский центр контроля и диагностики технических систем ; Технический комитет по стандартизации ТК 183 «Вибрация, удар и контроль технического состояния»; Федеральное агентство по техническому регулированию и метрологии. — Москва : Стандартинформ, 2017. — 20 с.

34. ISO 13381-1:2004 Condition monitoring and diagnostics of machines. Prognostics. General guidelines [Электронный ресурс] / British Standards Institution. — Режим доступа: https://shop.bsigroup.com/ProductDetail/?pid=000000000030152751 (дата обращения: 26.02.18).