350 rub
Journal Highly available systems №2 for 2025 г.
Article in number:
Wavelet neural networks mean square error synthesis of multidimensional linear nonstationary stochastic system with high availability
Type of article: scientific article
DOI: https://doi.org/10.18127/j20729472-202502-03
UDC: 621
Keywords: Canonical expansion; covariance function; covariance matrix; mean square error; neural network; optimal synthesis; stochastic process; stochastic system with high availability; wavelet; wavelet neural network
Authors:

I.N. Sinitsyn1, V.I. Sinitsyn2, E.R. Korepanov3, T.D. Konashenkova4

1–4 FRC «Computer Science and Control» of RAS (Moscow, Russia)
1 sinitsin@dol.ru, 2 vsinitsin@ipiran.ru, 3 ekorepanov@ipiran.ru, 4 tkonashenkova64@mail.ru

Abstract:

Paper is devoted to problem of mean square error (MSE) synthesis of multidimensional linear nonstationary stochastic system with high availability (StSHA) using wavelet neural networks (WNN) technologies. StSHA input stochastic process (StP) being the sum of useful signal linear dependent from vector random structural parameters and additive gaussian noise independent from structural parameters is known. For synthesis of StSHA output special algorithm based on multilayer WNN. Activation function are constructed using orthonormal wavelets with compact carrier. Modeling nonstationary StS is realized by canonical expansions (CE) and realized by WNN preference with wavelet CE.

Pages: 35-45
For citation

Sinitsyn I.N., Sinitsyn V.I., Korepanov E.R., Konashenkova T.D. Wavelet neural networks mean square error synthesis of multidimensional linear nonstationary stochastic system with high availability. Highly Available Systems. 2025. V. 21. № 2. P. 35−45. DOI: https://doi.org/ 10.18127/j20729472-202502-03 (in Russian)

References
  1. Pugachyov V.S. Teoriya sluchajny`x funkcij i eyo primenenie k zadacham avtomaticheskogo upravleniya. M.: Fizmatgiz. 1962. 884 s.
  2. Sinicyn I.N. Kanonicheskie predstavleniya sluchajny`x funkcij. Teoriya i primeneniya. Izd. 2-e. M.: Torus Press. 2023. 816 s.
  3. Sinitsyn I.N. Developing the theory of stochastic canonic expansions. Pattern Recognition and Image Analysis. 2023. V. 33. Iss. 4. P. 862–887. doi: 10.1134/S1054661823040429. EDN: QOWFBU.
  4. Xajkin S. Nejronny`e seti: polny`j kurs / Per. s angl. 2-e izd. SPb.: Dialektika. 2020. 1104 s.
  5. Feofilov S.V., Kozy`r` A.V., Xapkin D.L. Strukturno-parametricheskij sintez nejrosetevy`x regulyatorov dlya ob``ektov upravleniya s ogranichitelyami. Mexatronika, avtomatizaciya, upravlenie. 2023. T. 24. № 11. S. 563–572. https://doi.org/10.17587/mau.24.563-572. EDN: FWCBEO.
  6. Docenko A.V. Avtomaticheskij sintez neprery`vnoj dinamicheskoj sistemy` stabilizacii na osnove iskusstvenny`x nejronny`x setej. Vestnik moskovskogo gosudarstvennogo texnicheskogo universiteta im. N.E`. Baumana. Seriya priborostroenie. 2020. № 3(132). S. 66–83. DOI: 10.18698/0236-3933-2020-3-66-83. EDN: ADEEYU.
  7. Cherny`shev L.S. Identifikaciya nejrosetevoj modeli texnicheskoj sistemy` ili processa s cel`yu sinteza optimal`nogo upravleniya. Texnologii e`lektromagnitnoj sovmestimosti. 2023. № 2(85). S. 74–78. EDN: UVOUMK.
  8. Druzhinina O.V. Nejrosetevy`e algoritmy` dlya modelirovaniya pereklyuchaemy`x texnicheskix system. Nejrokomp`yutery`: razrabotka, primenenie. 2024. T. 26. № 5. S. 72–79. DOI: 10.18127/j19998554-202405-07. EDN: MOWCOT.
  9. Andreeva E.A., Ciruleva V.M. Matematicheskoe modelirovanie optimal`nogo upravleniya dinamicheskimi sistemami s pomoshh`yu iskusstvenny`x nejronny`x setej. Modelirovanie, optimizaciya i informacionny`e texnologii, 2018. № 2(21). S. 119–131. EDN: LXRMIX.
  10. Sinicyn I.N., Sinicyn V.I., Korepanov E`.R., Konashenkova T.D. Modelirovanie nestacionarnogo stoxasticheskogo processa posredstvom ego kanonicheskogo razlozheniya na osnove vejvlet-nejronnoj seti. Sistemy` i sredstva informatiki, 2024. T. 34. № 2. S. 21–39. doi: 10.14357/08696527240202. EDN: YFHFIN.
  11. Sinicyn I.N., Sinicyn V.I., Korepanov E`.R., Konashenkova T.D. Algoritm modelirovaniya vektornogo stoxasticheskogo processa posredstvom ego kanonicheskogo razlozheniya na osnove mnogoslojnoj vejvlet-nejronnoj seti // Sistemy` i sredstva informatiki. 2025. T. 35. № 1 (V pechati).
  12. Sinicyn I.N., Sinicyn V.I., Korepanov E`.R. Konashenkova T.D. Nejrosetevoj sintez optimal`noj linejnoj stoxasticheskoj sistemy` po kriteriyu minimuma srednekvadratichnoj oshibki. Sistemy` i sredstva informatiki. 2024. T. 34. № 3. S. 87–108. doi: 10.14357/08696527240307. EDN: FVQWBN.
  13. Sinicyn I.N., Sinicyn V.I., Korepanov E`.R., Konashenkova T.D. Nejrosetevoj algoritm sinteza optimal`noj linejnoj stoxasticheskoj sistemy` vy`sokoj dostupnosti po e`nergeticheskomu kriteriyu. Sistemy` vy`sokoj dostupnosti. 2024. T. 20. № 4. S. 5–14. doi: 10.18127/ j20729472-202404-01. EDN: PRWOPG.
  14. Terexov S.A. Vejvlety` i nejronny`e seti. Nauchnaya sessiya MIFI – 2001: III Vseros. nauchn.-texn. konf. «Nejroinformatika-2001»: lekcii po nejroinformatike. M.: MIFI. 2001. S. 142–181.
  15. Veitch D. Wavelet Neural Networks and their application in the study of dynamical system. Networks. 2005. V. 1. № 8. P. 313–320.
  16. Dobeshi I. Desyat` lekcij po vejvletam. M.; Izhevsk: NICz «Regulyarnaya i xaoticheskaya dinamika». 2004. 464 s.
  17. Sinicyn I.N., Shalamov A.S. Lekcii po teorii sistem integrirovannoj logisticheskoj podderzhki. Izd. 2-e. M.: Torus Press. 2019. 1072 s.
Date of receipt: 17.04.2025
Approved after review: 30.04.2025
Accepted for publication: 30.05.2025