Fuzzy technologies in control systems of lifting and transport mechanisms

THE PURPOSE. The study is devoted to the problems of ensuring the smooth start and stop of lifting and transport mechanisms. Standard regulators do not allow you to achieve the desired results with changing indicators, the exact values of which are not always available for measurement. Control signals, in such systems, usually correspond to data from a certain range. The paper proposes to replace the standard controller with a controller based on fuzzy algorithms. The process of modeling a system with different types of controllers allows you to explore systems and identify the most optimal of.

METHODS. To solve the problem, the methods of mathematical modeling in the MatLab Simulink environment were used.

RESULTS. The article considers the possibility of using various kinds of regulators on lifting and transport mechanisms. For the functioning of the fuzzy type controller, a rule base has been developed that forms the process of operation of a real object, with an optimal functioning algorithm. Systems with a PID-type controller, with a neural network-type controller with network training, with the possibility of its adjustment for further use, are implemented, the probability of high processor load is taken into account, on the basis of which a supervisor is proposed. The possibility of using ANFIS networks for the implementation of regulators is considered.

CONCLUSION. The use of different types of controllers operating on the principle of neural network technologies makes it possible to achieve optimal performance in the control of lifting and turning mechanisms, both from the standpoint of ensuring the stability of movement, and from the standpoint of system reliability. Compared with the PID type controller, the application of the ANFIS network reduced the fluctuation by 2.9 times, and the use of the fuzzy type controller reduced the fluctuation by 0,75 times. The use of a neural controller compared to the use of the ANFIS network gives a decrease in the fluctuation of the speed formation process by about 0.48 times.

1. Langraf SV, Sapozhnikov AI, Glazyrin AS, et al. Dynamics of an electric drive with a fuzzy controller. Izvestiya Tomsk Polytechnic University. 2010;316(4):168-173.

2. Sinyukova TV, Sinyukov AV, Gracheva EI, et al. Neirosetevye tekhnologii v sistemakh upravleniya mekhanizmami peremeshcheniya gruzov Izvestiya vysshikh uchebnykh zavedenii. Problemy ehnergetiki. 2022;24(2):107-118.

3. Sinyukova TV, Sentsov EV, Sinyukov AV. Neural Network Speed Observers. 2019 1st International Conference on Control Systems, Mathematical Modelling, Automation and Energy Efficiency, SUMMA 2019. 2019. pp. 320-324.

4. Sinyukova TV, Gladyshev VE, Sinyukov AV. Methods for Reducing Electromechanical Oscillations in Conveyor Control Systems. 1st International Conference on Control Systems, Mathematical Modelling, Automation and Energy Efficiency, SUMMA 2019. – 2019. pp. 435-439.

5. Buyankin V.M. Ehlementy iskusstvennogo intellekta v sistemakh upravleniya ehlektroprivodom s nechetkoi logikoi. Tendentsii razvitiya nauki i obrazovaniya. –2020;60;2(8-13).

6. Belov A.M., Belov M.P. Primenenie neironnykh setei v ehlektroprivodnykh sistemakh nasosnykh agregatov. Mezhdunarodnaya konferentsiya po myagkim vychisleniyam i izmereniyam. 2022;1:91-94.

7. Yamkovaya MA, Shadrin SV. Neiroupravlenie ehlektroprivodom s peremennym momentom inertsii. Informatsionnye tekhnologii i matematicheskoe modelirovanie v upravlenii slozhnymi sistemami. 2020;3 (8):45-55.

8. Dementev DA, Maximova ED, Sysoletin IA, et al. Research of the effect of an additional signal on the control process of a single-circuit automatic control system with a neuroregulator. 2021 3rd International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE), 2021. 20608282.

9. Klepikov VB, Bieliaiev OS. Neuroregulator with a Simplified Structure for Electric Drive with Frictional Load. 2022 IEEE 3rd KhPI Week on Advanced Technology (KhPIWeek). – 2022. 22186939.

10. Wan qiaoYuan, Ying yuan Xiao, Xu Jia, et al. Neural Network Detection of Shilling Attack Based on User Rating History and Latest Features. 2019 International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI). – 2019. 19246289.

11. Yuxiang NIU, Hui LI, Feiyang LIU. A Loss-aware Continuous Hopfield Neural Network (CDN)-based Mapping Algorithm in Optical Network-on-Chip (Noc). 2022 20th International Conference on Optical Communications and Networks (ICON). – 2022. 22115387.

12. Hecht-Nielsen R. Neurocomputing: picking the human brain. IEEE Spectrum. – 1988. 3143635.

13. Jianyang Tian, Guangyu Zhang, Jin Wu, et al. The fuzzy human-simulated intelligent control for hot-rolling strip width. Proceedings of the 10th World Congress on Intelligent Control and Automation. 2012. 13166720.

14. Kuz'min AV, Uskov AA. Intellektual'nye tekhnologii upravleniya. Iskusstvennye neironnye seti i nechetkaya logika: monografiya. M.: NTI «Goryachaya liniya-TelekoM». 2004. 143 s.

15. Makarov IM, Lokhin VM, Mas'ko SV, et al. Ustoichivost' intellektual'nykh sistem avtomaticheskogo upravleniya. Informatsionnye tekhnologii. 2013;S2:1-32.

16. Tsypkin YAZ. Adaptivnye metody vybora reshenii v usloviyakh neopredelennosti. Avtomatika i telemekhanika. 1976;4:78-91.