Bosh sahifa / Maqolalar / 2026 (62) 2 / Maqola
TEXNIKA FANLARI

VEKTOR KVANTLANGAN VAQTINCHALIK ASSOTSIATIV XOTIRA ASOSIDA DINAMIK OBYEKTLARNI IDENTIFIKATSIYALASH ALGORITMI

Shukurova Oysara Pula tovna Shukurova O.P.

Referat

Avtomatlashtirilgan boshqaruv obyektlarining texnologik parametrlarining o‘rtasidagi munosabatlarni identifikatsiyalash masalalarida neyron tarmoqlar imkoniyatlaridan foydalaniladi. Bunday identifikatsiyalash masalalarida qaraladigan muhim muammolardan biri modellashtirilayotgan dinamik obyektning neyron tarmog‘i arxitekturasini tanlash hisoblanadi. Ushbu maqolada vektor kvantlangan vaqtinchalik assotsiativ xotira asosida dinamik obyektlarni identifikatsiyalash algoritmi qarab chiqilgan. Neyron tarmoqlarida kirish va chiqish parametrlari, identifikatsiyalash sxemasi, o‘zini o‘qitish tarmog‘idagi berilgan funksiya approksimatsiyasi masalasini hal qilish usuli berilgan. Identifikatsiyalash uchun o‘zini o‘qituvchi tarmoqni qo‘llash sxemasi va foydalaniladigan Kohonen tarmog‘i arxitekturasi keltirilgan. Tarmoq parametrlarini o‘qitish algoritmi yozilgan.

Kalit so'zlar

o‘zini o‘qituvchi tarmoq neyron tarmoq Kohonen vaqt momenti model parametr vazn vektori sinaptik koeffitsiyentlar vektori g‘olib-neyron dinamik obyekt identifikatsiyalash.
Mualliflar
Shukurova Oysara Pula tovna
Qarshi davlat texnika universiteti, Qarshi
ORCID: 0000-0002-6357-6547

Iqtibos keltirish tartibi

Jurnal uslubi
Shukurova, O. P. t. VEKTOR KVANTLANGAN VAQTINCHALIK ASSOTSIATIV XOTIRA ASOSIDA DINAMIK OBYEKTLARNI IDENTIFIKATSIYALASH ALGORITMI. Innovatsion texnologiyalar, 2026, 62(2), 83-88. https://doi.org/10.70769/2181-4732.ITJ.2026-2.11
TXT (joriy uslub) BibTeX RIS

Adabiyotlar

  1. Husan Z. Igamberdiyev, Azizbek N.Yusupbekov, Orıpcan O. Zaripov, Jasur U.Sevinov. Algorithms of adaptive identification of uncertain operated objects in dynamical models. 9th International Conference on Theory and Application of Soft Computing, Computing with Words and Perception, ICSCCW 2017, 24-25 August 2017, Budapest, Hungary. Procedia Computer Science 120 (2017) 854 – 861 pp.
  2. Zaripov O. O., Sevinov J. U., Shukurova O.P. Algorithms for identification of linear dynamic control objects based on the ps eudo - concept concept. International Journal of Psychosocial Rehabilitation. Volume 24. Issue 3. 2020. 261 - 267 pp. DOI: 10.37200/IJPR/V24I3/PR200778
  3. Shukurova O.P. Nochiziqli tizim larni identifikatsiyalash va boshqarish. O‘zbekiston agrar fani xabarnomasi. No 6 (18) 2024. 214 -217 bet.
  4. . Saraev P.V. Chislennye metody intervalnogo analiza v obuchenii neyron- nykh setey [Numerical methods of interval analysis in learning neural network]. Autom. Remote Control, 2012, no. 11, pp. 129-143.
  5. . Gabitov R.F. Mnogomernoe modelno-prediktornoe upravlenie prokalkoy katalizatorov krekinga, osnovannoe na algoritme s intervalnoy neopredelennostyu [Multivariate model-predictive control calcination cracking catalysts based on an algorithm with interval uncertainty]: abstract thesis of the candidate of technical sciences. Ufa, 2012. 19 pp.
  6. . Zaripov O.O., Sevinov J.U., Shukurova O.P. Algorithms for recurrent identification of control objects by m eans of multiple models and adaptation of parameters. I nternational J ournal of A dvanced R esearch In S cience, E ngineering And T echnology. Vol. 6, Issue 3, Mar 2019. pp. 8479 - 8483.
  7. . Shumikhin A.G., Boyarshinova A.S., Orekhov M.S. Primenenie neyro - setevy kh modeley pri avtomatizirovannom upravlenii slozhnymi khimiko - tekhnologicheskimi sistemami. Polzunovskiy vest - nik, 2012, no. 3/2, pp. 9 - 12.
  8. Осовский С. Нейронные сети для обработки информации. – М.: Финансы и статистика, 2002.
  9. Sevinov, J.U., Boborayimov, O.K., Bobomurodov, N.H. (2024). Algorithms for Synthesis of Adaptive Neural Network Control Systems Based on the Velocity Gradient Me thod. In: Aliev, R.A., Kacprzyk, J., Pedrycz, W., Jamshidi, M., Babanli, M., Sadikoglu, F.M. (eds) 16th International Conference on Applications of Fuzzy Systems, Soft Computing and Artificial Intelligence Tools – ICAFS - 2023. ICAFS 2023. Lecture Notes in N etworks and Systems, vol 1141. Springer, Cham. https://doi.org/10.1007/978- 3-031-76283-3_34
  10. . Льюнг, Л. Идентификация систем. Теория для пользователя / Л. Льюнг. – М.: Гл. ред. физ. - мат. лит., 1991.
  11. Игамбердиев Х.З., Севинов Ж.У., Зарипов О.О. Регулярные методы и алгоритмы синтеза адаптивных систем управления с настраиваемыми моделями. – Т.: ТашГТУ, 2014. - 160 с. (Igamberdiev H.Z., Sevinov Zh.U., Zaripov O.O. (2014). Reguljarnye metody i algoritmy sinteza adaptivnyh sistem upravlenija s nastraivaemymi modeljami. – T.: TashGTU, – 160 s. (in. Russian)).
  12. T. Koskela. Neural network methods in analyzing and modeling time varying processes. Espoo. (2003), pp. 1-72.
  13. Shukurova, O.P. (2025). Intellektual neyron tarmoqlar matematik modelini qurish algoritmi. Innovatsion texnologiyalar. Ilmiy - texnik jurnal. 2025/4(60). 103 - 108.
  14. Гайимназаров, И. Х. (2024). НАТУРНЫЕ ИССЛЕДОВАНИЯ ПО ОПРЕДЕЛЕНИЮ РАСХОДА НАНОСОВ В УСЛОВИЯХ НЕСТАЦИОНАРНОГО ТЕЧЕНИЯ. Oriental renaissance: Innovative, educational, natural and social sciences, 4(4), 317-324.
  15. Yusupbekov, A.N., Sevinov, J.U., Mamirov, U.F., Botirov, T.V. (2021). Synthesis Algorithms for Neural Network Regulator of Dynamic System Control. Advances in Intelligent Systems and Computing, vol 1306. pp. 723 – 730. Springer, Cham. https://doi.org/10.1007/978-3-030-64058-3_90.
  16. Shuku rova, O.P., Bekmurodov A.X., Baratov A.K. (2022). Tabi i y gazni absorbsiyali quritish texnologik jarayonnini modellashtirish va boshqarish. Innovatsion texnologiyalar. Ilmiy - texnik jurnal – QMII. Maxsus son. 57 - 61.