The reliably stable neural network controllers' synthesis with the transient process parameters optimization

The subject of this paper is to develop a method for synthesizing stable neural network controllers with optimization of transient process parameters. The goal is to develop a method for synthesizing a neural network controller for control systems that guarantees the closed-loop system stability thr...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Radìoelektronnì ì komp'ûternì sistemi (Online) Ročník 2024; číslo 4; s. 178 - 191
Hlavní autoři: Vladov, Serhii, Sachenko, Anatoliy, Vysotska, Victoria, Volkanin, Yevhen, Kukharenko, Dmytro, Severynenko, Danylo
Médium: Journal Article
Jazyk:angličtina
Vydáno: National Aerospace University «Kharkiv Aviation Institute 21.11.2024
Témata:
ISSN:1814-4225, 2663-2012
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The subject of this paper is to develop a method for synthesizing stable neural network controllers with optimization of transient process parameters. The goal is to develop a method for synthesizing a neural network controller for control systems that guarantees the closed-loop system stability through automated selection of Lyapunov function with the involvement of an additional neural network trained on the data obtained in the solving process the integer linear programming problem. The tasks to be solved are: study the stability of a closed-loop control system with a neural network controller, train the neurocontroller and Lyapunov neural network function, create an optimization model for the loss function minimization, and conduct a computational experiment as an example of the neural network stabilizing controller synthesis. The methods used are: a neural network-based control object simulator training method described by an equations system taking into account the SmoothReLU activation function, a direct Lyapunov method to the closed-loop system stability guarantee, and a mixed integer programming method that allows minimizing losses and ensuring stability and minimum time regulation for solving the optimization problem. The following results were obtained: the neural network used made it possible to obtain results related to the transient process time reduction to 3.0 s and a 2.33-fold reduction in overregulation compared to the traditional controller (on the example of the TV3-117 turboshaft engine fuel consumption model). The results demonstrate the proposed approach's advantages, remarkably increasing the dynamic stability and parameter maintenance accuracy, and reducing fuel consumption fluctuations. Conclusions. This study is the first to develop a method for synthesizing a stabilizing neural network controller for helicopter turboshaft engines with guaranteed system stability based on Lyapunov theory. The proposed method's novelty lies in its linear approximation of the SmoothReLU activation function using binary variables, which allowed us to reduce the stability problem to an optimization problem using the mixed integer programming method. A system of constraints was developed that considers the control signal and stability conditions to minimize the system stabilization time. The results confirmed the proposed approach's effectiveness in increasing engine adaptability and energy efficiency in various operating modes.
AbstractList The subject of this paper is to develop a method for synthesizing stable neural network controllers with optimization of transient process parameters. The goal is to develop a method for synthesizing a neural network controller for control systems that guarantees the closed-loop system stability through automated selection of Lyapunov function with the involvement of an additional neural network trained on the data obtained in the solving process the integer linear programming problem. The tasks to be solved are: study the stability of a closed-loop control system with a neural network controller, train the neurocontroller and Lyapunov neural network function, create an optimization model for the loss function minimization, and conduct a computational experiment as an example of the neural network stabilizing controller synthesis. The methods used are: a neural network-based control object simulator training method described by an equations system taking into account the SmoothReLU activation function, a direct Lyapunov method to the closed-loop system stability guarantee, and a mixed integer programming method that allows minimizing losses and ensuring stability and minimum time regulation for solving the optimization problem. The following results were obtained: the neural network used made it possible to obtain results related to the transient process time reduction to 3.0 s and a 2.33-fold reduction in overregulation compared to the traditional controller (on the example of the TV3-117 turboshaft engine fuel consumption model). The results demonstrate the proposed approach's advantages, remarkably increasing the dynamic stability and parameter maintenance accuracy, and reducing fuel consumption fluctuations. Conclusions. This study is the first to develop a method for synthesizing a stabilizing neural network controller for helicopter turboshaft engines with guaranteed system stability based on Lyapunov theory. The proposed method's novelty lies in its linear approximation of the SmoothReLU activation function using binary variables, which allowed us to reduce the stability problem to an optimization problem using the mixed integer programming method. A system of constraints was developed that considers the control signal and stability conditions to minimize the system stabilization time. The results confirmed the proposed approach's effectiveness in increasing engine adaptability and energy efficiency in various operating modes.
Author Sachenko, Anatoliy
Volkanin, Yevhen
Kukharenko, Dmytro
Severynenko, Danylo
Vysotska, Victoria
Vladov, Serhii
Author_xml – sequence: 1
  givenname: Serhii
  orcidid: 0000-0001-8009-5254
  surname: Vladov
  fullname: Vladov, Serhii
– sequence: 2
  givenname: Anatoliy
  orcidid: 0000-0002-0907-3682
  surname: Sachenko
  fullname: Sachenko, Anatoliy
– sequence: 3
  givenname: Victoria
  orcidid: 0000-0001-6417-3689
  surname: Vysotska
  fullname: Vysotska, Victoria
– sequence: 4
  givenname: Yevhen
  orcidid: 0000-0003-3507-1987
  surname: Volkanin
  fullname: Volkanin, Yevhen
– sequence: 5
  givenname: Dmytro
  orcidid: 0000-0002-2845-6881
  surname: Kukharenko
  fullname: Kukharenko, Dmytro
– sequence: 6
  givenname: Danylo
  orcidid: 0000-0002-1708-316X
  surname: Severynenko
  fullname: Severynenko, Danylo
BookMark eNo9kE1LAzEQhoNUsGrPXnPztDWTTTa7Ryl-geClnsN0d2JTt5uSREr99W6teHqGgXle5r1kkyEMxNgNiHkpKynuIn2muRRSzdUc9BmbyqoqCylATtgUalCFklJfsFlKGyGErI0GU09Zv1wTj9R7XPUHnvII4gN9RexH5H2In7wNQ46h7ymmW54OQ15T8onvfV7zceY54pA8DZnvYmgpJb7DiFvK4wEPu-y3_huzD8M1O3fYJ5r98Yq9Pz4sF8_F69vTy-L-tWglGF1IUp2rzco1lcMSoCuxhlVZCWhQG1mZDsh1bny2gwbauqkNlspoMk50Wqnyir2cvF3Ajd1Fv8V4sAG9_V2E-GExZt_2ZNFgCxKloFapxqjVGOkqjdKMceTM6Lo7udoYUork_n0g7G_39ti9PXZvlQVd_gBerXws
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.32620/reks.2024.4.15
DatabaseName CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: Open Access资源_DOAJ
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2663-2012
EndPage 191
ExternalDocumentID oai_doaj_org_article_a7ac12a20ec44974b6faf65a27601ef7
10_32620_reks_2024_4_15
GroupedDBID AAYXX
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
9MQ
ID FETCH-LOGICAL-c2175-2e4df87bf96fa311d3a81b36019a57267d1efdf024d191c8987a3475e7f0d5443
IEDL.DBID DOA
ISSN 1814-4225
IngestDate Fri Oct 03 12:44:17 EDT 2025
Sat Nov 29 06:59:26 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2175-2e4df87bf96fa311d3a81b36019a57267d1efdf024d191c8987a3475e7f0d5443
ORCID 0000-0002-2845-6881
0000-0001-8009-5254
0000-0003-3507-1987
0000-0002-0907-3682
0000-0002-1708-316X
0000-0001-6417-3689
OpenAccessLink https://doaj.org/article/a7ac12a20ec44974b6faf65a27601ef7
PageCount 14
ParticipantIDs doaj_primary_oai_doaj_org_article_a7ac12a20ec44974b6faf65a27601ef7
crossref_primary_10_32620_reks_2024_4_15
PublicationCentury 2000
PublicationDate 2024-11-21
PublicationDateYYYYMMDD 2024-11-21
PublicationDate_xml – month: 11
  year: 2024
  text: 2024-11-21
  day: 21
PublicationDecade 2020
PublicationTitle Radìoelektronnì ì komp'ûternì sistemi (Online)
PublicationYear 2024
Publisher National Aerospace University «Kharkiv Aviation Institute
Publisher_xml – name: National Aerospace University «Kharkiv Aviation Institute
SSID ssj0002875178
ssib044757823
ssib052605930
ssib038076033
Score 2.274349
Snippet The subject of this paper is to develop a method for synthesizing stable neural network controllers with optimization of transient process parameters. The goal...
SourceID doaj
crossref
SourceType Open Website
Index Database
StartPage 178
SubjectTerms controller
lyapunov function
mixed integer programming
neural network
optimization
Title The reliably stable neural network controllers' synthesis with the transient process parameters optimization
URI https://doaj.org/article/a7ac12a20ec44974b6faf65a27601ef7
Volume 2024
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: Open Access资源_DOAJ
  customDbUrl:
  eissn: 2663-2012
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002875178
  issn: 1814-4225
  databaseCode: DOA
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2663-2012
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044757823
  issn: 1814-4225
  databaseCode: M~E
  dateStart: 20030101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV09T8MwELUQYoAB8SnKlzwgwZI2dhzbGQFRMaCKAVC3yE5sqZCmVVOQ-u-5S9IqGwtbEiVR_HTyvXPuPRNyY2XilXSoxvEOChTmAi2iMLA6kl7ImIta5frxokYjPR4nr52tvrAnrLEHboAbGGUyxg0PXSYEkF8rvfEyNhybOZyvdeShSjrFFEQSuqjLzv85dLWDVLg5j5HFr_cA_KyXmFTM6mkbMp4IBER54wMUoWH7YOG-0Nqbi77o4wa6nRTWcfqvU9LwgOy3XJLeN2M4JFuuPCJ7HYfBY1JAGNCFKybGFisKTNAWjqKHJTxXNh3gtO1WL4AI3tJqVQIlrCYVxRVaCsd0iekMZZN03qgKKPqFT7GPpqIzmHKmrZbzhLwPn94en4N2g4Ugg0okDrgTudfK-gRAjRjLIwMsNgJgExMrLlUOCOcexp1DWZfpRCsTAZRO-TBH47xTsl3OSndGaOh4ojMmuPVGJCK02mToZRYybU1kZY_crTFL542PRgr1Rw1vivCmCG8qUhb3yANiurkNDbDrCxAWaRsW6V9hcf4fL7kgu_hVKD3k7JJsLxff7orsZD_LSbW4riPuF2XU1iQ
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=The+reliably+stable+neural+network+controllers%27+synthesis+with+the+transient+process+parameters+optimization&rft.jtitle=Rad%C3%ACoelektronn%C3%AC+%C3%AC+komp%27%C3%BBtern%C3%AC+sistemi+%28Online%29&rft.au=Vladov%2C+Serhii&rft.au=Sachenko%2C+Anatoliy&rft.au=Vysotska%2C+Victoria&rft.au=Volkanin%2C+Yevhen&rft.date=2024-11-21&rft.issn=1814-4225&rft.eissn=2663-2012&rft.volume=2024&rft.issue=4&rft.spage=178&rft.epage=191&rft_id=info:doi/10.32620%2Freks.2024.4.15&rft.externalDBID=n%2Fa&rft.externalDocID=10_32620_reks_2024_4_15
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1814-4225&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1814-4225&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1814-4225&client=summon