SYNTHESIS OF NEURO-FUSSY REGULATOR WITH ADJUSTMENT BY GENETIC ALGORITHM
DOI:
https://doi.org/10.26906/SUNZ.2023.3.041Keywords:
fuzzy controller, membership function, defuzzification neuro-fuzzy regulator, genetic algorithmAbstract
The purpose of the article is to consider the method of developing a neuro-fuzzy regulator with the adjustment of its parameters by a genetic algorithm. The obtained results confirm the workability of the technique and allow us to conclude that the neuro-fuzzy regulator, with appropriate settings, ensures high quality of the control system, including in the presence of random disturbances to a dynamic object. The method of neuro-fuzzy regulator synthesis proposed in the article was tested under the conditions of a limited volume of initial data (the volume of the training sample), the size of which does not affect the quality of the algorithm. Two or three values of the sampling parameters are enough to form the ranges for the boundaries of the terms of the fuzzy variables, and then the optimal values are selected by genetic algorithm. As a result, an algorithm for the synthesis of the regulator and a genetic algorithm for adjusting its parameters were developed.Downloads
References
Siddique N.H. Computational intelligence: synergies of fuzzy logic, neural networks, and evolutionary computing / N. H. Siddique. – Chichester, West Sussex, United Kingdom: John Wiley & Sons Inc., 2013. – 517 p., ISBN: 9781118337844.
Hall, M.A. (2012) Cumulative multi-niching genetic algorithm for multimodal function optimization. International Journal of Advanced Research in Artificial Intelligence, vol. 1, no. 9, pp. 6–13. DOI: 10.14569/IJARAI.2012.010902.
Bounemeur A., Chemachema M., Essounbouli N. New approach of robust DirectAdaptive Control of a class of SISO Nonlinear Systems, in 15th international conference on Sciences and Techniques of Automatic control & computer engineering - STA'2014, 2014: Hammamet, Tunisia. p.725-730. DOI: 10.1109/sta.2014.7086723.
Filasov´a A., Hladk´y V., Krokavec D. Nonlinear System H∞ Fuzzy Control within Takagi-Sugeno Framework, in International Conference on Process Control (PC) June 18–21, 2013, Štrbské Pleso, Slovakia. 2013. p. 13-18. DOI:10.1109/pc.2013.6581375.
PhamThi Ly, Bui Quoc Khanh Using Genetic Algorithm to Optimize Controllers of Thermal Load System in Thermal Power Plant Published: April 26th, 2022. DOI: 10.5772/intechopen.103915.
Harpreet Singh, Madan M. Gupta, Thomas Meitzler, et al., ―Real-Life Applications of Fuzzy Logic, Advances in Fuzzy Systems, vol. 2013, Article ID 581879, 3 pages, 2013. DOI: 10.1155/2013/581879.
Aceves-Lopes A. A simplified version of Mamdani's fuzzy controller: the natural logi controller. IEEE Transactions on fuzzy systems, 2006. 14(1): p. 16-30. DOI: 10.1109/TFUZZ.2005.861603.
Ion Iancu (2012). A Mamdani Type Fuzzy Logic Controller, Fuzzy Logic - Controls, Concepts, Theories and Applications, Prof. Elmer Dadios (Ed.), ISBN: 978-953-51-0396-7.
Oleksenko O., Khudov H., Petrenko K., Horobets Yu., KoliandaV, Kuchuk N., Konstantinov A., Kireienko V., Serdiuk O., Yuzova I. and Solomonenko Yu. (2021), “The Development of the Method of Radar Observation System Construction of the Airspace on the Basis of Genetic Algorithm”, International Journal of Emerging Technology and Advanced Engineering, Vol. 11, Is. 8, pp. 23-30, doi: https://doi.org/10.46338/ijetae0821_04.
B. Dun, O. Zakovorotnyi, and N. Kuchuk, “Generating currency exchange rate data based on Quant-Gan model”, Advanced Information Systems, vol. 7, no. 2, pp. 68–74, Jun. 2023. doi: 10.20998/2522-9052.2023.2.10.
Ковриго Ю.М. Fuzzy-регулятор для керування інерційними технологічними параметрами котлоагрегату ТЕС / Ю.М. Ковриго, О.С.Бунке, П.В. Новіков / Nauka i Studia NR 8 (169) 2017 – с. 76-84.
B. Kopchak, L. Kasha. Genetic algorithm application for synthesis and analysis of electromechanical systems. Energy Eng. Control Syst., 2018, Vol. 4, No. 2, pp. 73 – 78. DOI: 10.23939/jeecs2018.02.073
