RUDN Journal of Engineering ResearchRUDN Journal of Engineering ResearchВестник Российского университета дружбы народов. Серия: Инженерные исследования2312-81432312-8151Peoples’ Friendship University of Russia named after Patrice Lumumba (RUDN University)4974710.22363/2312-8143-2026-27-1-25-36GZMJMPArticlesСтатьиResearch ArticleModification of the Structure and Parameters of Genetic Algorithmswith Fuzzy Operators Implemented by Hybrid ControllersМодификация структуры и параметров генетических алгоритмов с нечеткими операторами, реализуемых гибридными контроллерамиhttps://orcid.org/0009-0003-4014-47701948-7354RogachevDmitry A.РогачевДмитрий Алексеевич

PhD in Technical Sciences, Senior Researcher

кандидат технических наук, ведущий научный сотрудник

Rogachev.soft@gmail.comhttps://orcid.org/0000-0002-3077-66228413-5020RogachevAleksey F.РогачевАлексей Фруминович

Doctor of Technical Sciences, Professor of the Department of Mathematical Modeling and Computer Science

доктор технических наук, профессор кафедры математического моделирования и информатики

rafr@mail.ruFederal Scientific Center for Hydraulic Engineering and Land Reclamation named after A.N. KostyakovФедеральный научный центр гидротехники и мелиорации им. А.Н. КостяковаVolgograd State Agrarian UniversityВолгоградский государственный аграрный университет13042026271253613042026Copyright ©; 2026, Rogachev D.A., Rogachev A.F.Copyright ©; 2026, Рогачев Д.А., Рогачев А.Ф.2026Rogachev D.A., Rogachev A.F.Рогачев Д.А., Рогачев А.Ф.https://creativecommons.org/licenses/by-nc/4.0https://journals.rudn.ru/engineering-researches/article/view/49747

The use of evolutionary genetic AI methods and, in particular, genetic algorithms (GA) ensures the construction of sufficiently universal optimization systems with various architectures and macroparameters. A systematic investigation of GA structures, parameters, and performance has made it possible to identify and synthesise key trends in their modification. The effects of GA structure and parameters on the timing and accuracy of fitness function optimization were performed on the OneMax binary chromosome coding test problem. Numerical studies of the solution of the problem of evolutionary genetic optimization have shown the applicability of a fuzzy controller to increase the efficiencyof GA. Numerical experiments have demonstrated that the average fitness value increases rapidly during the initial stage of the optimization process, which can be attributed to the high initial crossover probability ( Pc ). After 20-50 epochs, the optimization process reaches a stable regime. The fuzzy adaptation of the parameters of the genetic operators makes the algorithm more robust compared to fixed parameters. Recommendations have been formulated for the selection of macroparameters and for substantiating the choice of algorithm modification strategies in specific application domains, including the allocation of limited water resources.

Применение эволюционно-генетических методов AI и, в частности генетических алгоритмов - genetic algorithms (GA), обеспечивает построение достаточно универсальных систем оптимизации с различными архитектурами и макропараметрами. Исследования структур, параметров и результатов функционирования GA, проведенные на основе системного подхода, позволили обобщить тенденции модификации GA, влияния структуры и параметров GA на время и точность оптимизации функции приспособленности проведены на тестовой задаче OneMax с бинарным кодированием хромосомы. Проведенные численные исследования решения задачи эволюционно-генетической оптимизация показали применимость нечеткого контроллера для повышения эффективности GA. Численными экспериментами показано, что среднее значение фитнес-функции быстро растёт в начале процесса оптимизации благодаря высокому значению начальной вероятности Pc , принимаемой для генетического оператора скрещивания. Через 20…50 эпох процесс стабилизируется. Нечеткая адаптация параметров генетических операторов делает алгоритм более робастным по сравнению с фиксированными параметрами. Сформулированы рекомендации по выбору макропараметров и обоснованию выбора варианты модификации алгоритмов для конкретных предметных областей, включая распределение ограниченных водных ресурсов.

optimizationmodification of algorithmsadaptive parametersmembership functionfuzzy inferencewater resources distributionоптимизациямодификация алгоритмовадаптивные параметрыфункция принадлежностинечеткий выводнечеткий контроллерраспределение водных ресурсовRogachev D, Yurchenco I, Rogachev A. Management and optimization of sistematic water adjustment by economic-mathematic modeling methods and AI. International Russian Automation Conference; 2023 Sept 10–16: Sochi, Russian Federation. 2023. p. 888–893. http://doi.org/10.1109/RusAutoCon58002.2023.10272907 EDN: PWNESZRogachev D., Yurchenco I., Rogachev A. Management and optimization of sistematic water adjustment by economic-mathematic modeling methods and AI // International Russian Automation Conference; 2023 Sept 10-16. Sochi, 2023. p. 888-893. http://doi.org/10.1109/RusAutoCon58002.2023.10272907 EDN: PWNESZMelikhova EV, Rogachev AF. Computer simulation and optimization of parameters of configuration of the contour of moistening under drip irrigation of agricultures. In: Popkova E, editor. Ubiquitous Computing and the Internet of Things: Prerequisites for the Development of ICT. Studies in Computational Intelligence. Cham: Springer; 2019. p. 1193–1201. http://doi.org/10.1007/978-3-030-13397-9_122 EDN: FJWSYWMelikhova E.V., Rogachev A.F. Computer simulation and optimization of parameters of configuration of the contour of moistening under drip irrigation of agricultures // Ubiquitous Computing and the Internet of Things: Prerequisites for the Development of ICT. Studies in Computational Intelligence / Popkova E., (ed). Cham : Springer Publ.; 2019. Vol. 826. P.1193-1201. http://doi.org/10.1007/978-3-030-13397-9_122 EDN: FJWSYWMelikhova EV, Rogachev AF, Skiter NN. Infor-mation system and database for simulation of irrigated crop growing. Studies in Computational Intelligence. 2019;826:1185–1191. http://doi.org/10.1007/978-3-030-13397-9_121 EDN: WGYXJKMelikhova E.V., Rogachev A.F, Skiter N.N. Information system and database for simulation of irrigated crop growing // Ubiquitous Computing and the Internet of Things: Prerequisites for the Development of ICT. Studies in Computational Intelligence / Popkova E. (ed). Cham : Springer Publ.; 2019. Vol. 826. P. 1185-1191. http://doi.org/10.1007/978-3-030-13397-9_121 EDN: WGYXJKSkobtsov Y, Sekirin A, Zemlyanskaya S, Chengar O, Skobtsov V, Potryasaev S. Application of object-oriented simulation in evolutionary algorithms. In: Silhavy, R., Senkerik, R., Oplatkova, Z.K., Silhavy, P., Prokopova, Z. editors. Advances in Intelligent Systems and Computing. Cham: Springer. 2016. p. 453–462. http://doi.org/10.1007/978-3-319-33389-2_43 EDN: WWDZITSkobtsov Y., Sekirin A., Zemlyanskaya S., Chengar O., Skobtsov V., Potryasaev S. Application of object-oriented simulation in evolutionary algorithms // Advances in Intelligent Systems and Computing / Silhavy R., Senkerik R., Oplatkova Z.K., Silhavy P., Prokopova Z. (eds). Cham: Springer, 2016. p. 453-462. http://doi.org/10.1007/978-3-319-33389-2_43 EDN: WWDZITMurillo-Morera J, Quesada-López C, Castro-Herrera C, Jenkins M. A genetic algorithm based framework for software effort prediction. Journal of Software Engi-neering Research and Development. 2017;5(4):1–33. https://doi.org/10.1186/s40411-017-0037-xMurillo-Morera J., Quesada-López C., Castro-Herrera C., Jenkins M. A genetic algorithm based framework for software effort prediction // Journal of Software Engineering Research and Development. 2017. Vol. 5. No. 4. P. 1-33. https://doi.org/10.1186/s40411-017-0037-xPatnaik LM, Mandavilli S. Adaptation in genetic algorithms. In: Genetic Algorithms for pattern Recognition. CRC Press; 1996. 1st ed. p. 45–64. http://doi.org/10.1201/9780203713402-3Patnaik L.M., Mandavilli S. Adaptation in genetic algorithms. 1st ed // Genetic Algorithms for Pattern Recognition. CRC Press; 1996. p. 45-64. http://doi.org/10.1201/9780203713402-3Mahfoud SW. A comparison of parallel and se-quential niching methods. Proceedings of VI International conference on genetic algorithms. 1995;136–143. Available from: https://dblp.org/rec/conf/icga/Mahfoud95.html (accessed: 12.05.2025)Mahfoud S.W. A comparison of parallel and sequential niching methods // Proceedings of VI International conference on genetic algorithms. 1995. P. 136-143. Available from: https://dblp.org/rec/conf/icga/Mahfoud95.html (accessed: 12.05.2025).Grefenstette JJ. Lamarkian learning in multi-agent environment. Proceedings of the 4th international conference on genetic algorithms. 1991;303–310. Available from: https://dblp.org/rec/conf/icga/Grefenstette91 (accessed: 12.05.2025).Grefenstette J.J. Lamarkian learning in multi-agent environment // Proceedings of the 4th international conference on genetic algorithms. 1991. P. 303-310. Available from: https://dblp.org/rec/conf/icga/Grefenstette91 (accessed: 12.05.2025).Whitley D, Gordon V, Mathias K. Lamarkian evolution, the Baldwin effect & function optimization. Parallel Problem Solving from Nature — PPSN III. PPSN 1994. Lecture Notes in Computer Science. Berlin, Heidelberg: Springer Publ.; 1994;866:5–15. https://doi.org/10.1007/3-540-58484-6_245Whitley D., Gordon V., Mathias K. Lamarkian evolution, the Baldwin effect & function optimization // Parallel Problem Solving from Nature - PPSN III. PPSN 1994. Lecture Notes in Computer Science. Berlin, Heidelberg : Springer Publ.; 1994. Vol. 866. P. 5-15. https://doi.org/10.1007/3-540-58484-6_245Davidor Y. A genetic algorithm applied to robot trajectory generation. In: Davis L, editor. Handbook of genetic algorithms. New York: Van Nostrand Reinhold Publ.; 1991.Davidor Y. A genetic algorithm applied to robot trajectory generation // Davis L. editor, Handbook of genetic algorithms. New York : Van Nostrand Reinhold Publ.; 1991.Moscato P, Norman MG. A memetic approach for the traveling salesman problem: implementation of computational ecology for combinatorial optimization on message-passing systems. Parallel computing and transputer applications. Fogarty TC, editor. Berlin, Heidelberg: Springer Publ.; 1992;1:177–186.Moscato P., Norman M.G. A memetic approach for the traveling salesman problem: implementation of computational ecology for combinatorial optimization on message-passing systems // In: Fogarty T.C. (eds) Parallel computing and transputer applications. Berlin, Heidelberg : Springer Publ.; 1992.Vol. 1. P. 177-186.Radcliffe NJ, Surry PD. Formal memetic algorithm. In: Fogarty TC, editor. Proceeding — Selected Papers from AISB Workshop on Evolutionary Computing. Berlin, Heidelberg: Springer Publ.; 1994. p. 1–16. https://doi.org/10.1007/3-540-58483-8_1Radcliffe N.J., Surry P.D. Formal memetic algorithm // Evolutionary Computing.AISB EC 1994. Lecture Notes in Computer Science / Fogarty T.C. (eds). Berlin, Heidelberg : Springer Publ.; 1994. Vol. 865. P. 1-16 https://doi.org/10.1007/3-540-58483-8_1Singh BK, Misra AK. Software effort estimation by genetic algorithm tuned parameters of modified con-structive cost model for NASA software projects. International Journal of Computer Applications. 2012;59(9):22–26. https://doi.org/10.5120/9577-4053Singh B.K., Misra A.K. Software effort estimation by genetic algorithm tuned parameters of modified constructive cost model for NASA software projects // International Journal of Computer Applications. 2012. Vol. 59. No. 9. P. 22-26. https://doi.org/10.5120/9577-4053Herera F, Lozano M. Adaptation of genetic algorithm parametres based on fuzzy logic controllers. In: Herera F, Verdegay J, editors. Genetic algorithms and soft computing. 1996;95–125.Herera F., Lozano M. Adaptation of genetic algorithm parametres based on fuzzy logic controllers // Genetic Algorithms and Soft Computing / Herera F., Verdegay J. (eds). 1996. p. 95-125.Mitsuo G., Runwei C., Lin L. Network models and optimization. London : SpringerVerlag London Limited, 2008. https://doi.org/10.1007/978-1-84800-181-7Mitsuo G, Runwei C, Lin L. Network models and optimization. London: SpringerVerlag London Limited; 2008. https://doi.org/10.1007/978-1-84800-181-7Hinterding R., Michalevicz Z., Eiben A. Adaptation in evolutionary computation: a survey // Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC ‘97); 1997 Apr 3-16; Indianapolis, IN, USA; IEEE; 2002. p. 65-69. http://doi.org/10.1109/ICEC.1997.592270Hinterding R, Michalevicz Z, Eiben A. Adaptation in evolutionary computation: a survey. Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97); 1997 Apr 3–16; Indianapolis, IN, USA; IEEE; 2002 Aug 06 p. 65–69. http://doi.org/10.1109/ICEC.1997.592270Davis L. Handbook of genetic algorithms. New York : Van Nostrand Rein-hold; 1991. ISBN10 0442001738Davis L. Handbook of genetic algorithms. New York: Van Nostrand Reinhold; 1991. ISBN 10 0442001738Juldstrom B. What have you done for me lately adapting operator probabilities in a steady-state genetic algorithm // Proceedings 6th International Conference on Gas. San Francisco : Morgan Kaufmann Publ.; 1995. p. 81-87. ISBN 1-55860-370-0Juldstrom B. What have you done for me lately adapting operator probabilities in a steady-state genetic algorithm. Proceedings 6th international conference on Gas. San Francisco: Morgan Kaufmann Publ.; 1995. p. 81–87. ISBN 1-55860-370-0Koumousis V.K., Katsaras C.P. Asow-tooth genetic algorithm combining the effects of variable population size and reinitialization to enhance performance // IEEE Trans-actions on Evolutionary Computation. 2006. Vol. 10. Nо. 1. P. 19-28. http://doi.org/10.1109/TEVC.2005.860765Koumousis VK, Katsaras CP. Asow-tooth genetic algorithm combining the effects of variable population size and reinitialization to enhance performance. IEEE Transactions on Evolutionary Computation. 2006;10(1):19–28. http://doi.org/10.1109/TEVC.2005.860765Lin L., Gen M. Auto-tuning strategy for evolutionary algorithms: Balancing between exploration and exploitation // Soft Computing. 2009. Vol. 13. P. 157-168. http://doi.org/10.1007/s00500-008-0303-2 EDN: IYKVAZLin L, Gen M. Auto-tuning strategy for evolutionary algorithms: Balancing between exploration and exploitation. Soft Computing. 2009;13:157–168. http://doi.org/10.1007/s00500-008-0303-2 EDN: IYKVAZMoel M.C., Stewart C.V., Kelly R.B. Reducing the search time of a steady state genetic algorithm using the immigration operator // Proceedings IEEE International Conference Toolsfor AI. 1991 Nov 10-13; Danbury, CT, USA; IEEE; 1991. p. 500-501. http://doi.org/10.1109/TAI.1991.167032Moel MC, Stewart CV, Kelly RB. Reducing the search time of a steady state genetic algorithm using the immigration operator. Proceedings IEEE International Con-ference Toolsfor AI. 1991 Nov 10–13; Danbury, CT, USA; IEEE; 1991. p. 500–501. http://doi.org/10.1109/TAI.1991.167032Gladkov L.A., Gladkova N.V., Semushin E.Y. Parallel hybrid genetic algorithm for solving design and optimization problems // Advances in Intelligent Systems and Computing / Hu Z., Petoukhov S., He M. (eds). 2020. Vol. 1127. P. 249-258.2020. Vol. 1127. P. 249-258. http://doi.org/10.1007/978-3-030-39216-1_23 EDN: PMLJYGGladkov LA, Gladkova NV, Semushin EY. Parallel hybrid genetic algorithm for solving design and optimi-zation problems. Advances in Intelligent Systems and Computing. In: Hu Z, Petoukhov S, He M. editors. 2020;1127:249–258. http://doi.org/10.1007/978-3-030-39216-1_23 EDN: PMLJYGKureychick V.M., Kaplunov T.G. Time series fore-casting method based on genetic algorithm for predicting the conditions of technical systems // Journal of Physics: Conference Series. 2019. Article no. 032046. http://doi.org/10.1088/1742-6596/1333/3/032046 EDN: OZIEUEKureychick VM, Kaplunov TG. Time series fore-casting method based on genetic algorithm for predicting the conditions of technical systems. Journal of Physics: Conference Series. 2019:032046. http://doi.org/10.1088/1742-6596/1333/3/032046 EDN: OZIEUEЛабинский А.Ю. Перспективные направления использования генетических алгоритмов // Природные и техногенные риски (физико-математические и прикладные аспекты). 2023. № 2 (46). С. 81-88. EDN: SXNYDFLabinskiy A. The perspective trend of use the genetic algorithm. Natural and Man-Made Risks (Physico-Mathematical and Applied Aspects). 2023;2(45):81–88. (In Russ.) EDN: SXNYDFРогачев Д.А., Кирейчева Л.В., Юрченко И.Ф. Тимошкин А.Д., Кузнецов Ю.С., Фролина Е.А. Устройство для управления обучением нейронной сети с генетическим алгоритмом. Патент Российская Федерация № 2843987 C1, МПК G06N 3/08, № 2024120049: заявл. 17.07.2024 : опубл. 23.07.2025. EDN: ZSPIACRogachev DA, Kirejcheva LV, Yurchenko IF, Timoshkin AD, Kuznetsov YuS, Frolina EA. Neural network with genetic algorithm training control device. Patent of the Russian Federation No. 2843987 C1, IPC G06N 3/08, No. 2024120049: application 07.17.2024: published 07.23.2025. EDN: ZSPIAC