Fuzzy control system of multioperational machine status

Introduction. The paper presents the key aspects of constructing a management system for the state of multi-operation computer-controlled machines based on the information-control module of e-Mind Machine and the apparatus of fuzzy sets and fuzzy logic. It is shown that the input effects of the control system are formed due to the sets of inheriting and operating components of the status parameters. The work objective is to develop a system for monitoring the condition, detecting dimensional wear, and determining the period of tool life on the basis of the fuzzy logic methods. Materials and Methods. A new algorithm for constructing an expert system based on the fuzzy logic methods is proposed. The applicability of fuzzy neuron methods for solving the problems on determining the service life of the instrument through comparing the calculated values to the data of the manufacturing firms is demonstrated. The study is based on the application of the concept of electronic services using expert systems. Research Results. The basic principles of the construction and application of the status monitoring system are substantiated. They provide the possibility, under managing, to adapt to the emerging situation and to predict state changes when processing the parts. The monitoring functions include not only the processing of data obtained from the test units of the mechatronic system and external equipment, but both the forecasting of the residual dimensional tool life and the durability for the period of normal wear and tear. The decision-making process on managing the tool status is presented in the form of an algorithm for the expert system activity based on the use of a fuzzy neuron controller. Discussion and Conclusions. The results obtained can be applied in the parts production where accuracy is one of the key parameters. Automated control systems for the machine condition allow reducing costs due to equipment downtime, and monitoring the tool status can reduce the rejection rate. The characteristic examples of decision-making in the fuzzy neuron system are given.

нечеткое управление, нейронечеткий контроллер, мониторинг, экспертная система управления состоянием станка, fuzzy control, fuzzy neuron controller, monitoring, expert control system of machine status

1. Sensor Fused Intelligent Monitoring System for Machining Intelligent Manufacturing Systems. Available at: http://www.ims.org/2012/11/simon-sensor-fused-intelligent-monitoring-system-for-machining. (accessed: 03.12.14.).

2. Čuš, F., Župerl, U. Real-Time Cutting Tool Condition Monitoring in Milling. Journal of Mechanical Engineering, 2011,vol. 2 (57), pp. 142–150.

3. Grigoryev, S.N., Gurin, V.D., Cherkasova, N.Y. Povyshenie proizvoditel'nosti frezerovaniya s pomoshch'yu diagnostirovaniya sostoyaniya instrumenta s uchetom dostovernosti otobrazheniya sostoyaniya ob''ekta po kriteriyu ego otkaza. [Improving milling efficiency by tool diagnostics with account for the display validity of the object status by its failure criterion.] Vestnik MSTU “STANKIN”, 2011, no. 3 (15), pp. 44–48 (in Russian).

4. Vallejo, A.-J. On-line Cutting Tool Condition Monitoring in Machining Processes using Artificial Intelligence. Robotics, Automation and Control. P. Pecherková, M. Flídr, J. Duník, eds. Vienna: I-Tech, 2008, p. 494.

5. Bagci, E. Monitoring and analysis of MRR-based feedrate optimization approach and effects of cutting conditions using acoustic sound pressure level in free-form surface milling. Scientific Research and Essays, 2011, vol. 6 (2), pp. 256–277.

6. Salgado, D.-R., Alonso, F.-J. Tool wear detection in turning operations using singular spectrum analysis. Journal of Materials Processing Technology, 2006, vol. 171 (3), pp. 451–458.

7. Jemielniak, K. Tool wear monitoring based on a non-monotonic signal feature. Journal of Engineering Manufacture, 2006, vol. 220 (2), pp. 163–170.

8. Samodurov, G.V., et al. Printsipy postroeniya intellektual'noy elektronnoy dokumentatsii stanka. [Principles of constructing intelligent electronic machine documentation.] STIN, 2012, no. 7, pp. 15–20 (in Russian).

9. Tugengold, A.K., et al. Monitoring i upravlenie sostoyaniem instrumenta na mnogooperatsionnykh stankakh. [Monitoring and control of the tool status on multi- operation machines.] STIN, 2016, no. 11, pp. 13–21 (in Russian).

10. Tugengold, A.K., Voloshin, R.N. Gibkiy monitoring mekhatronnykh tekhnologicheskikh mashin. [Flexible monitoring of mechatronic technological machines.] Vestnik of DSTU, 2016, no. 4, pp. 51–58 (in Russian).

11. Zadeh, L.-A. A fuzzy-algorithmic approach to the definition of complex or imprecise concepts. International Journal of Man-Machine Studies, 1976, vol. 8, pp. 249–291.

12. Zadeh, L.-A. Fuzzy sets. Information and control, 1965, vol. 8 (3), pp. 338–353.

13. Ni, J., Djurdjanovic, D. Watchdog — information technology for proactive product maintenance and its implications to ecological product re-use. Advanced Engineering Informatics, 2003, vol. 17, pp. 109–125.

14. Tugengold, A.K., Dimitrov, V.P., Borisova, L.V. K voprosu postroeniya nechetkoy ekspertnoy sistemy produktsionnogo tipa dlya tekhnologicheskoy regulirovki mashin. [To the question of fuzzy expert system constructing production type for technological adjustment of machines.] Vestnik of DSTU, 2008, vol. 8, no. 3 (38), pp. 419–426 (in Russian).

15. Sandvik Coromant. Technology Information. Available at: http://www.sandvik.coromant.com/ruru/knowledge/pages/default.aspx (accessed: 12.02.17).

16. Dimitrov, V.P., Borisova, L.V. Formalizatsiya nechetkikh ekspertnykh znaniy pri lingvisticheskom opisanii tekhnicheskikh system. [Formalization of fuzzy expert knowledge at the linguistic description of technical systems.] Rostovon- Don: DSTU Publ. Centre, 2011, 209 p. (in Russian).

17. Tugengold, A.K., et al. Otsenka nechetkoy granitsy stoykosti instrumenta mnogooperatsionnogo stanka. [The estimation of fuzzy boundary of multioperational machine tool life.] Vestnik of DSTU, 2015, vol. 15, № 2 (81), pp. 33–41 (in Russian).