Intellectualization of the process of constructing membership functions and implementation of fuzzy logical inference based on them

Purpose of research. The method proposed in this work is aimed at increasing the speed and accuracy of the computational process of training a fuzzy logic system. The developed parameterized membership functions were used as the subject of the study. The effectiveness indicator was the impact of changing the labels of input membership functions, created by the traditional method and using parameterized membership functions, on the output characteristic.

Methods. A method has been developed and implemented for constructing parametric membership functions that are used in the process of fuzzy logic inference fuzzification. In addition to fuzzification, the system implements fuzzy inference and defuzzification. Triangular membership functions were used in the fuzzification process. As a compositional rule, 6 activated degrees of membership were used, combined on the basis of Zadeh’s compositional rule into 5 conclusions of fuzzy logical inference. At the defuzzification stage, a simplified center of gravity method was used. The object of the study was fuzzy logical inference using traditional and parameterized membership functions synthesized at the fuzzification stage.

Results. A mathematical model of fuzzy inference with implemented parameterized membership functions at the fuzzification stage is obtained. Based on the experiment, it was concluded that the proposed model has a smoother resulting surface when one parameter of the input membership function changes. In this case, the condition for the division of unity is ensured.

Conclusion. A mathematical model of fuzzy inference with implemented parameterized membership functions at the fuzzification stage is obtained. Based on the experiment, it was concluded that the proposed model has a smoother resulting surface when one parameter of the input membership function changes. In this case, the condition for the division of unity is ensured.

1. Bobyr M. V., Nasser A. A. Parameterization of membership functions in fuzzy logical inference. Mnogoyadernye protsessory, parallel'noe programmirovanie, PLIS, sistemy obrabotki signalov = Multi-core processors, parallel programming, FPGAs, signal processing systems. 2016; 1 (6): 287-291. (In Russ.). EDN VZDVXL.

2. Bobyr M.V., Yakushev A.S., Dorodnykh A.A. Fuzzy devices for cooling the cutting tool of the CNC machine implemented on FPGA. Measurement. 2020; 152: 107378. https://doi.org/10.1016/j.measurement.2019.107378.

3. Bobyr M.V., Emelyanov S.G. A nonlinear method of learning neuro-fuzzy models for dynamic control systems. Applied Soft Computing. 2020; 88: 106030. https://doi.org/10.1016/j.asoc.2019.106030.

4. Bobyr M.V., Arkhipov A.E., Yakushev A.S. Color mark shade recognition based on fuzzy clustering. Informatika i avtomatizatsiya = Computer Science and Automation. 2021; (2): 407-434. (In Russ.).

5. Titov V.S., Bobyr M.V., Antsiferov A.V. Algorithm for high-speed parts processing based on fuzzy logic. Mekhatronika, avtomatizatsiya, upravlenie = Mechatronics, Automation, Control. 2012; (6): 21-26. (In Russ.).

6. Bobyr’ M.V., Titov V.S., Nasser A.A. Automation of the cutting-speed control process based on soft fuzzy logic computing. J. Mach. Manuf. Reliab. 2015; 44: 633–641. https://doi.org/10.3103/S1052618815070067

7. Leekwijck W.V., Kerre E.E. Defuzzification: criteria and classification. Fuzzy Sets Syst. 1999; (108): 159–178.

8. Uskov A.A. Systems with fuzzy models of control objects. Smolensk: SFRUK, 2013; 153 p. (In Russ.).

9. Ryzhakov V.V., Ryzhakov M.V. Membership functions of elements of fuzzy sets on universal scales adapted by various mapping functions. Oboronnyi kompleks - nauchnotekhnicheskomu progressu Rossii = Defense Complex - Scientific and Technical Progress of Russia. 2009; (3): 93-97. (In Russ.). EDN KKNUMT.

10. Popova Yu. B., Burakovsky A. I. Characteristic functions of fuzzy sets in learning systems using the example of a trapezoidal membership function. In: Informatsionnye tekhnologii v tekhnicheskikh i sotsial'no-ekonomicheskikh sistemakh: sbornik materialov nauchno-tekhnicheskoi konferentsii = Information technologies in technical and socioeconomic systems: collection of materials of a scientific and technical conference. Minsk: Republican Institute of Higher School; 2016. P. 3-5. (In Russ.). EDN IEKRWA.

11. Izosimov S. D. Methodology for determining membership functions for approximation of periodic functions by fuzzy sets. Molodoi uchenyi = Young Scientist. 2015; (6): 164- 168. (In Russ.). EDN TNBZGZ.

12. Pospelov D.A. Fuzzy sets in control and artificial intelligence models. Moscow: Nauka. Gl. red. fiz.-mat. lit.; 1986. 312 p. (In Russ.).

13. Sergienko M. A. Methods for designing a fuzzy knowledge base. Vestnik Voronezhskogo gosudarstvennogo universiteta. Seriya: Sistemnyi analiz i informatsionnye tekhnologii = Bulletin of Voronezh State University. Series: System analysis and information technologies. 2008; (2): 67-71. (In Russ.). EDN KHNZGN.

14. Bizyanov E. E. Implementation of fuzzy models in information systems of economic objects. Ekonomika i menedzhment innovatsionnykh tekhnologii = Economics and management of innovative technologies. 2015; (4-1): 67-71. (In Russ.). EDN TUIYPD.

15. Bizyanov E. E., Gutnik A. A. Method for obtaining and storing parameters of membership functions of fuzzy sets. Informatsionnye tekhnologii i matema-ticheskoe modelirovanie v upravlenii slozhnymi sistemami = Information technologies and mathematical modeling in the management of complex systems. 2020; (3): 22-28. (In Russ.). https://doi.org/10.26731/2658-3704.2020.3(8).22-28. EDN ARXOPX.

16. Milostnaya N. A. Stability Study of a Neuro-Fuzzy Output System Based on Ratio Area Method. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University. 2021; 25(3): 70-85 (In Russ.). https://doi.org/10.21869/2223-1560-2021-25-3-70-85.

17. Dusakaeva S. T., Khokhlov I. A., P Niryan. L., Nosarev M. P. Application of the Mamdani fuzzy logic algorithm for selecting players for a football club at pre-season training camps. Sovremennye tekhnologii. Sistemnyi analiz. Modelirova-nie = Modern technologies. System analysis. Modeling. 2022; (4): 228-237. (In Russ.). https://doi.org/10.26731/1813-9108.2022.4(76).228-237. EDN EHIPOJ.

18. Adriyendi. Fuzzy Logic using Tsukamoto Model and Sugeno Model on Prediction Cost. International Journal of Intelligent Systems and Applications. 2018; 10 (6): 13-21.

19. Milostnaya N.A. High-speed defuzzifiers based on the area ratio method. Promyshlennye ASU i kontrollery = Industrial automated control systems and controllers. 2021; (11): 18-25. (In Russ.).

20. Bobyr M.V., Khrapova N. I., Lamonov M. A. Smart Traffic Light Control System Based on Fuzzy Logic. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University. 2021; 25(4): 162-176 (In Russ.). https://doi.org/10.21869/2223-1560-2021-25-4-162-176.

21. Pegat A. Fuzzy modeling and control. 2nd ed. Moscow: BINOM. Laboratory of knowledge, 2013; 798 p. (In Russ.).