One of the ways to increase the efficiency of the process of managing continuous
dynamic objects is to develop new or improve existing control systems based on modern methods
involving the achievements of information technology. The article deals with the creation of
highly efficient control algorithms for technological objects, operating in conditions of
uncertainty, designed to manage real-life objects. An algorithm is proposed for the structuralparametric adaptation of the PID parameters (proportional-integral-differential) -regulator,
which allows to reduce the number of iterations in the learning process of the fuzzy-logical
inference algorithm by reducing empty solutions. To determine the empty solutions, hybrid
algorithms are used, which include modernized genetic and immune algorithms, which in turn
allow you to configure the adaptation parameters of artificial neural network models. A block
diagram of an automated control system for executive mechanisms is proposed, which includes a
block for adapting the correction of not only parameters, but also the structure of the control
system, which allows to reduce the error in the results of training a neuro-fuzzy network from 8
to 1%. The proposed algorithm is simple to implement on microcontrollers, which allows it to
Electrical and Computer Engineering
155
be implemented in the tasks of process control in the conditions of information uncertainty in
real conditions at the operation stage.
Uzluksiz dinamik ob'ektlarni boshqarish jarayoni samaradorligini oshirish yo'llaridan biri
zamonaviy tehnologiyalar asosida ahborot tehnologiyalarining yutuqlarini o'z ichiga olgan
yangi tizimlarni ishlab chiqish yoki mavjud tizimlarni takomillashtirishdir. Maqolada mavjud
real ob'ektlarni boshqarish uchun mo'ljallangan, noaniqlik sharoitida ishlaydigan tehnologik
ob'ektlarni yuqori samarali boshqarish algoritmlarini yaratish masalalari ko'rib chiqilgan. PIDrostlagich parametrlarini tarkibiy-parametrik moslashtirish algoritmi taklif etilgan, bu esa bo'sh
echimlarni kamaytirish orqali noqat'iy-mantiq hulosa algoritmini o'rganish jarayonida
iteraciyalar sonini kamaytirish imkon beradi. Bo'sh echimlarni aniqlash uchun gibrid
algoritmlar, shu jumladan sun'iy neyron tarmoq modellarining moslashuv parametrlarini
sozlash uchun modernizaciya qilingan genetik va immun algoritmlari ishlatilgan. Uning
tarkibiga parametrlarni nafaqat tuzatish blok moslashuvi, shuningdek neyro-noqat'iy tarmoqni
o'qitish natijasida hatolarni 8 % dan 1 % gacha kamaytirish imkonini beradigan boshqaruv
tizimining tuzilishi, avtomatlashtirilgan boshqarish tizimi ijrochi mehanizmlarining tizimli
shemasi taklif qilingan. Taklif qilingan algoritm mikrokontrollerlarda amalga oshirishning
soddaligi bilan ajralib turadi, bu esa uni operacion bos?qichida real sharoitlarda
ma'lumotlarning noaniqligi sharoitida jarayonni boshqarish vazifalarida bajarilishiga imkon
beradi.
One of the ways to increase the efficiency of the process of managing continuous
dynamic objects is to develop new or improve existing control systems based on modern methods
involving the achievements of information technology. The article deals with the creation of
highly efficient control algorithms for technological objects, operating in conditions of
uncertainty, designed to manage real-life objects. An algorithm is proposed for the structuralparametric adaptation of the PID parameters (proportional-integral-differential) -regulator,
which allows to reduce the number of iterations in the learning process of the fuzzy-logical
inference algorithm by reducing empty solutions. To determine the empty solutions, hybrid
algorithms are used, which include modernized genetic and immune algorithms, which in turn
allow you to configure the adaptation parameters of artificial neural network models. A block
diagram of an automated control system for executive mechanisms is proposed, which includes a
block for adapting the correction of not only parameters, but also the structure of the control
system, which allows to reduce the error in the results of training a neuro-fuzzy network from 8
to 1%. The proposed algorithm is simple to implement on microcontrollers, which allows it to
Electrical and Computer Engineering
155
be implemented in the tasks of process control in the conditions of information uncertainty in
real conditions at the operation stage.
Одним из путей повышения эффективности процесса управления непрерывными
динамическими объектами является разработка новых или усовершенствование
существующих систем управления на базе современных методов с привлечением
достижений информационной технологии. В статье рассмотрены вопросы создания
высокоэффективных алгоритмов управления технологическими объектами,
функционирующих в условиях неопределенности, предназначенных для управления реально
действующими объектами. Предложен алгоритм структурно-параметрической
адаптации параметров ПИД (пропорционально-интегрально-дифференциального)-регулятора, позволяющий уменьшить количество итераций в процессе обучения
алгоритма нечетко-логического вывода за счет сокращения пустых решений. Для
определения пустых решений использованы гибридные алгоритмы, включающие в себя
модернизированные генетические и иммунные алгоритмы, которые в свою очередь
позволяют настроить параметры адаптации моделей искусственной нейронной сети.
Предложена структурная схема автоматизированной системы управления
исполнительными механизмами, включающая в свой состав блок адаптации коррекции не
только параметров, но и структуры системы управления, который позволяет
уменьшить погрешность результатов обучения нейро-нечеткой сети с 8 до 1%.
Предложенный алгоритм отличается простотой реализации на микроконтроллерах, что
позволяет его реализовать в задачах управления технологическими процессами в условиях
неопределенности информации в реальных условиях на этапе эксплуатации.
№ | Имя автора | Должность | Наименование организации |
---|---|---|---|
1 | Siddikov I.K. | Professor | TDTU |
2 | Yadgarova D.B. | doctorant | TDTU |
№ | Название ссылки |
---|---|
1 | Bobir M.V. Modifitsirovannii algoritm nechetko-logicheskogo vivoda v zadachax upravleniya oborudovaniem s CHPU // Mexatronika , Avtomatizatsiya, Upravlenie. 2001. №4. S.26-32. 2. Bobir M.V., Titov V.S., Ansiferov A.V. Algoritm visokoskorostnoy obrabotki detaley na osnove nechetkoy logiki // Mexatronika, Avtomatizatsiya, Upravlenie, 2012. №6. S.21-26. 3. Otsenka dostovernosti pri modelirovanii nechetko-logicheskix sistem / Bobir M.V., Titov V.S., P.V. Globin, N.A. Milostnaya // Promishlennie ASU i kontrolleri, 2012. №7. S. 32-38. 4. Bobir M.V. Metodi postroeniya funksiy prinadlejnostey dlya nechetkix baz znaniy // Promishlennie ASU i kotrolleri, 2011. №2. S.27-33. 5. Bobir M.V., Titov V.S., CHervyakov L.M. Adaptatsiya slojnix sistem upravleniya s uchetom prognozirovaniya vozmojnix sostoyaniy // Avtomatizatsiya i sovremennie texnologii, 2012. №5. S.3-10. 6. Pupkov K.A., Barkin A.I., Voronov E.M. i dr.; Pod red. N.D. Egupova. Metodi klassicheskoy i sovremennoy teorii avtomaticheskogo upravleniya: Uchebnik dlya vuzov. V 3 t. -Moskva: Izd-vo MGTU im. N.E. Baumana, 2000. 7. Rutkovskaya D., Pilinskiy M., Rutkovskiy L. Neyronnie seti, geneticheskie algoritmi i nechetkie sistemi- M.: Goryachaya liniya-Telekom, 2006.- 452 s. 8. Pegat A. Nechetkoe modelirovanie i upravlenie.- M.: IUIT; BINOM, Laboratoriya znaniy, 2012. -798 s. 9. Antipin A.F. Sravnitelniy analiz bistrodeystviya diskretno-logicheskogo regulyatora // Programmnie produkti i sistemi. 2010. № 1 (89). S. 75–77. 10. Yurkevich V.D. Sintez nelineynix nestatsionarnix sistem upravleniya s raznotempovimi protsessami. SPb.: Nauka, 2000. 287 c. 11. Siddikov I., Iskandarov Z. Synthesis of adaptive-fuzzy control system of dynamic in conditions of uncertainty of information // International Journal of Advanced Research in Science, Engineering and Technology. Vol. 5. Issue 1. January 2018. pp. 5089-5093. 12. Zadeh, L.. Fuzzy Sets. Inf Cont, Vol. 8, Pp. 338–353, 1965. 13. Cox, E. , The Fuzzy Systems Handbook. Ap Professional - New York.1994. Electrical and Computer Engineering 161 14. Mehrotra, K., Mohan, C. K., And Ranka, S. ,Elements Of Artificial Neural Networks. The Mit Press, 1997 15. Lin, C-T., and C. S. George Lee. «Neural-network-based fuzzy logic control and decision system» Computers, IEEE Transactions on 40.12 (1991): 1320-1336. 16. Takagi, H. & Hayashi, I., Nn-Driven Fuzzy Reasoning. International Journal Of Approximate Reasoning, Vol. 5,Issue 3, 1991. 17. Rotach, V.Ya. (2008) The Theory of Automatic Control. Moscow: Publishing House Moscow Power Engineering Institute, - 396 p. 18. Pelusi, D., Mascella R. (2013) Optimal control algorithms for second order systems, Journal of Computer Science, vol. 9, no. 2, pp. 183–197. 19. Astrom, K.J. (2006) Advanced PID control/ K. J. Astrom, T. Hagglund – ISA (The instrumentation, Systems, and Automation Society), 2006 – 460 p. 20. Wang, L. And Mendel, J., Back-Propagation Fuzzy System As Nonlinear Dynamic System Identifiers. Proceedings Of Ieee International Conferenceon Fuzzy Systems, Pages 1409– 1416, 1992. |