Differential Neural Network Identifier for Dynamical Systems With Time-Varying State Constraints
This study presents a state nonparametric identifier based on neural networks with continuous dynamics, also known as differential neural networks (DNNs). The laws for adjusting their parameters are developed using a control barrier Lyapunov functions (BLFs). The motivation for using the BLF comes f...
Saved in:
| Published in | IEEE transaction on neural networks and learning systems Vol. 36; no. 1; pp. 407 - 418 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
IEEE
01.01.2025
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 2162-237X 2162-2388 2162-2388 |
| DOI | 10.1109/TNNLS.2023.3326450 |
Cover
| Abstract | This study presents a state nonparametric identifier based on neural networks with continuous dynamics, also known as differential neural networks (DNNs). The laws for adjusting their parameters are developed using a control barrier Lyapunov functions (BLFs). The motivation for using the BLF comes from the preliminary information of the system states, which remain in a predefined time-depending set characterized by state or purely time-dependent functions. In this study, time-dependent state constraints are supposed to be known in advance continuous-time functions. The obtained learning laws require solving differential continuous-time Riccati equations and nonlinear differential equations for the learning laws that depend on the identification error and the state restrictions. The developed identifier was evaluated concerning the identifier that does not consider the state restrictions. This comparison included the numerical evaluation of the identifier for a robotic arm intended to reproduce a nonstandard flight simulator. This evaluation confirmed that the identification results were improved using the proposed learning laws and considering that the state limits were not transgressed. The quality indicators based on the mean square error were more minor by 4.2 times. |
|---|---|
| AbstractList | This study presents a state nonparametric identifier based on neural networks with continuous dynamics, also known as differential neural networks (DNNs). The laws for adjusting their parameters are developed using a control barrier Lyapunov functions (BLFs). The motivation for using the BLF comes from the preliminary information of the system states, which remain in a predefined time-depending set characterized by state or purely time-dependent functions. In this study, time-dependent state constraints are supposed to be known in advance continuous-time functions. The obtained learning laws require solving differential continuous-time Riccati equations and nonlinear differential equations for the learning laws that depend on the identification error and the state restrictions. The developed identifier was evaluated concerning the identifier that does not consider the state restrictions. This comparison included the numerical evaluation of the identifier for a robotic arm intended to reproduce a nonstandard flight simulator. This evaluation confirmed that the identification results were improved using the proposed learning laws and considering that the state limits were not transgressed. The quality indicators based on the mean square error were more minor by 4.2 times.This study presents a state nonparametric identifier based on neural networks with continuous dynamics, also known as differential neural networks (DNNs). The laws for adjusting their parameters are developed using a control barrier Lyapunov functions (BLFs). The motivation for using the BLF comes from the preliminary information of the system states, which remain in a predefined time-depending set characterized by state or purely time-dependent functions. In this study, time-dependent state constraints are supposed to be known in advance continuous-time functions. The obtained learning laws require solving differential continuous-time Riccati equations and nonlinear differential equations for the learning laws that depend on the identification error and the state restrictions. The developed identifier was evaluated concerning the identifier that does not consider the state restrictions. This comparison included the numerical evaluation of the identifier for a robotic arm intended to reproduce a nonstandard flight simulator. This evaluation confirmed that the identification results were improved using the proposed learning laws and considering that the state limits were not transgressed. The quality indicators based on the mean square error were more minor by 4.2 times. This study presents a state nonparametric identifier based on neural networks with continuous dynamics, also known as differential neural networks (DNNs). The laws for adjusting their parameters are developed using a control barrier Lyapunov functions (BLFs). The motivation for using the BLF comes from the preliminary information of the system states, which remain in a predefined time-depending set characterized by state or purely time-dependent functions. In this study, time-dependent state constraints are supposed to be known in advance continuous-time functions. The obtained learning laws require solving differential continuous-time Riccati equations and nonlinear differential equations for the learning laws that depend on the identification error and the state restrictions. The developed identifier was evaluated concerning the identifier that does not consider the state restrictions. This comparison included the numerical evaluation of the identifier for a robotic arm intended to reproduce a nonstandard flight simulator. This evaluation confirmed that the identification results were improved using the proposed learning laws and considering that the state limits were not transgressed. The quality indicators based on the mean square error were more minor by 4.2 times. |
| Author | Nachevsky, Ilya Andrianova, Olga Chairez, Isaac Poznyak, Alexander |
| Author_xml | – sequence: 1 givenname: Ilya orcidid: 0009-0000-1503-296X surname: Nachevsky fullname: Nachevsky, Ilya organization: V. A. Trapeznikov Institute of Control Sciences, Russian Academy of Sciences (RAS), Moscow, Russia – sequence: 2 givenname: Olga orcidid: 0000-0002-8407-1046 surname: Andrianova fullname: Andrianova, Olga organization: V. A. Trapeznikov Institute of Control Sciences, Russian Academy of Sciences (RAS), Moscow, Russia – sequence: 3 givenname: Isaac orcidid: 0000-0002-7157-2052 surname: Chairez fullname: Chairez, Isaac email: ichairezo@gmail.com organization: Institute of Advanced Materials for Sustainable Manufacturing, Tecnológico de Monterrey, Zapopan, Jalisco, Mexico – sequence: 4 givenname: Alexander surname: Poznyak fullname: Poznyak, Alexander organization: Automatic Control Department, CINVESTAV-IPN, 2508 Av. Instituto Politécnico Nacional, Mexico City, Mexico |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37903049$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkMlOwzAQhi1UREvpCyCEcuSS4i22c0Rlq1SVQ8tyC44zAUOTgO0K9e1JFyrmMqPR949G3zHq1E0NCJ0SPCQEp5fz6XQyG1JM2ZAxKniCD1CPEkFjypTq7Gf50kUD7z9wWwIngqdHqMtkihnmaQ-9XtuyBAd1sHoRTWHpNi38NO4zGhfrfWnBRWXjoutVrStrWmC28gEqHz3b8B7NbQXxk3YrW79Fs6ADRKOm9sFpWwd_gg5LvfAw2PU-ery9mY_u48nD3Xh0NYkNlUmIJeM5M0qVhBZcU5obqUwuMCO5KlJmuEzKQuciAUkpM5hIIlKR54YTlSgOrI8utne_XPO9BB-yynoDi4WuoVn6jCrFhZStpxY936HLvIIi-3K2at_P_qy0AN0CxjXeOyj3CMHZ2n62sZ-t7Wc7-23obBuyAPAvQNNUCMJ-AcKigDg |
| CODEN | ITNNAL |
| Cites_doi | 10.1109/ICRA.2017.7989693 10.1109/tnnls.2022.3164948 10.3182/20130902-3-CN-3020.00122 10.1109/TAC.2012.2191174 10.1109/ACC.2006.1656440 10.1109/TFUZZ.2018.2833822 10.1007/978-1-4612-0349-0_4 10.2514/1.G004363 10.1016/j.automatica.2012.05.003 10.1109/ECC.2016.7810398 10.1090/S0002-9947-98-02083-2 10.1142/4703 10.1007/s00498-021-00277-z 10.1080/00207179.2011.631192 10.1007/978-3-030-72016-2_20 10.1016/j.actaastro.2006.11.012 10.1109/TCYB.2016.2554621 10.1109/TNN.2009.2024203 10.1007/s12555-018-0745-y 10.1109/CDC.2007.4434165 10.1016/S0005-1098(01)00051-6 10.1109/ACC.1997.612023 10.1016/j.automatica.2003.08.009 10.1515/9781400841042 10.1016/j.automatica.2008.11.017 10.1109/MED.2012.6265706 10.1007/978-3-319-10277-1 10.1109/TETCI.2022.3146332 10.1063/5.0088748 10.1016/j.automatica.2004.08.019 10.1007/978-3-642-16684-6 10.1109/MED.2008.4602041 10.1109/TAC.1981.1102785 10.1016/j.automatica.2011.08.044 10.1109/TAC.2009.2013013 10.1016/j.jde.2008.11.010 10.1016/j.automatica.2019.108740 10.1109/CDC.2008.4738704 10.23919/ACC.2019.8814758 10.1007/978-3-319-55036-7 10.1137/100799903 10.1109/TNNLS.2021.3137883 10.3182/20070822-3-za-2920.00006 10.1109/TAC.2010.2074590 10.1016/c2016-0-03865-2 10.1016/j.sysconle.2013.07.003 10.1016/j.sysconle.2009.08.004 10.1016/j.ifacol.2015.11.268 10.1177/0142331217737596 10.1109/TFUZZ.2022.3184048 10.1177/0278364917712421 10.1109/CDC.2012.6426196 10.1007/s12555-014-0018-3 |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7X8 |
| DOI | 10.1109/TNNLS.2023.3326450 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Xplore url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2162-2388 |
| EndPage | 418 |
| ExternalDocumentID | 37903049 10_1109_TNNLS_2023_3326450 10299661 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: Tecnológico de Monterrey Challenge-Based Research Program grantid: IJXT070-22TE60001 funderid: 10.13039/501100004961 |
| GroupedDBID | 0R~ 4.4 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK ACPRK AENEX AFRAH AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF M43 MS~ O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION RIG NPM 7X8 |
| ID | FETCH-LOGICAL-c275t-734b3c88f12d4a22bc78cb6031b8d93c475fdab65e7223c0171696bbc418584e3 |
| IEDL.DBID | RIE |
| ISSN | 2162-237X 2162-2388 |
| IngestDate | Thu Jul 10 17:36:23 EDT 2025 Mon Jul 21 06:03:47 EDT 2025 Tue Jul 01 00:27:54 EDT 2025 Wed Aug 27 01:57:59 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c275t-734b3c88f12d4a22bc78cb6031b8d93c475fdab65e7223c0171696bbc418584e3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-8407-1046 0009-0000-1503-296X 0000-0002-7157-2052 |
| PMID | 37903049 |
| PQID | 2884677450 |
| PQPubID | 23479 |
| PageCount | 12 |
| ParticipantIDs | proquest_miscellaneous_2884677450 ieee_primary_10299661 pubmed_primary_37903049 crossref_primary_10_1109_TNNLS_2023_3326450 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2025-Jan. 2025-1-00 2025-Jan 20250101 |
| PublicationDateYYYYMMDD | 2025-01-01 |
| PublicationDate_xml | – month: 01 year: 2025 text: 2025-Jan. |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | IEEE transaction on neural networks and learning systems |
| PublicationTitleAbbrev | TNNLS |
| PublicationTitleAlternate | IEEE Trans Neural Netw Learn Syst |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref13 ref12 ref15 ref14 ref53 ref52 ref11 ref10 ref54 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 Khalil (ref49) 2002; 3 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 |
| References_xml | – ident: ref21 doi: 10.1109/ICRA.2017.7989693 – ident: ref37 doi: 10.1109/tnnls.2022.3164948 – ident: ref44 doi: 10.3182/20130902-3-CN-3020.00122 – ident: ref9 doi: 10.1109/TAC.2012.2191174 – ident: ref7 doi: 10.1109/ACC.2006.1656440 – ident: ref53 doi: 10.1109/TFUZZ.2018.2833822 – ident: ref2 doi: 10.1007/978-1-4612-0349-0_4 – ident: ref15 doi: 10.2514/1.G004363 – ident: ref10 doi: 10.1016/j.automatica.2012.05.003 – ident: ref26 doi: 10.1109/ECC.2016.7810398 – ident: ref34 doi: 10.1090/S0002-9947-98-02083-2 – ident: ref33 doi: 10.1142/4703 – ident: ref31 doi: 10.1007/s00498-021-00277-z – ident: ref43 doi: 10.1080/00207179.2011.631192 – ident: ref5 doi: 10.1007/978-3-030-72016-2_20 – ident: ref11 doi: 10.1016/j.actaastro.2006.11.012 – ident: ref45 doi: 10.1109/TCYB.2016.2554621 – ident: ref36 doi: 10.1109/TNN.2009.2024203 – ident: ref42 doi: 10.1007/s12555-018-0745-y – ident: ref14 doi: 10.1109/CDC.2007.4434165 – ident: ref6 doi: 10.1016/S0005-1098(01)00051-6 – ident: ref23 doi: 10.1109/ACC.1997.612023 – ident: ref13 doi: 10.1016/j.automatica.2003.08.009 – ident: ref50 doi: 10.1515/9781400841042 – ident: ref46 doi: 10.1016/j.automatica.2008.11.017 – ident: ref28 doi: 10.1109/MED.2012.6265706 – ident: ref1 doi: 10.1007/978-3-319-10277-1 – ident: ref40 doi: 10.1109/TETCI.2022.3146332 – ident: ref39 doi: 10.1063/5.0088748 – ident: ref12 doi: 10.1016/j.automatica.2004.08.019 – ident: ref3 doi: 10.1007/978-3-642-16684-6 – ident: ref32 doi: 10.1109/MED.2008.4602041 – ident: ref51 doi: 10.1109/TAC.1981.1102785 – ident: ref25 doi: 10.1016/j.automatica.2011.08.044 – ident: ref30 doi: 10.1109/TAC.2009.2013013 – ident: ref52 doi: 10.1016/j.jde.2008.11.010 – ident: ref54 doi: 10.1016/j.automatica.2019.108740 – ident: ref17 doi: 10.1109/CDC.2008.4738704 – ident: ref22 doi: 10.23919/ACC.2019.8814758 – ident: ref27 doi: 10.1007/978-3-319-55036-7 – ident: ref29 doi: 10.1137/100799903 – ident: ref38 doi: 10.1109/TNNLS.2021.3137883 – volume: 3 volume-title: Nonlinear Systems year: 2002 ident: ref49 – ident: ref16 doi: 10.3182/20070822-3-za-2920.00006 – ident: ref18 doi: 10.1109/TAC.2010.2074590 – ident: ref35 doi: 10.1016/c2016-0-03865-2 – ident: ref47 doi: 10.1016/j.sysconle.2013.07.003 – ident: ref8 doi: 10.1016/j.sysconle.2009.08.004 – ident: ref19 doi: 10.1016/j.ifacol.2015.11.268 – ident: ref24 doi: 10.1177/0142331217737596 – ident: ref4 doi: 10.1109/TFUZZ.2022.3184048 – ident: ref20 doi: 10.1177/0278364917712421 – ident: ref41 doi: 10.1109/CDC.2012.6426196 – ident: ref48 doi: 10.1007/s12555-014-0018-3 |
| SSID | ssj0000605649 |
| Score | 2.4581385 |
| Snippet | This study presents a state nonparametric identifier based on neural networks with continuous dynamics, also known as differential neural networks (DNNs). The... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 407 |
| SubjectTerms | Barrier Lyapunov functions (BLFs) differential neural networks (DNNs) Electron tubes Mathematical models Neural networks nonlinear nonparametric identification Stability analysis time-varying state constraints Time-varying systems Trajectory Uncertainty |
| Title | Differential Neural Network Identifier for Dynamical Systems With Time-Varying State Constraints |
| URI | https://ieeexplore.ieee.org/document/10299661 https://www.ncbi.nlm.nih.gov/pubmed/37903049 https://www.proquest.com/docview/2884677450 |
| Volume | 36 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV09T8MwELWgEwufBcqXjMSGElrHjuMRUaoKQRda6BZixxEI1KI2Xfj13NlJBUiVmJIhjhLf2ffO9rtHyAWTEOO40YEQSRbwjKlAFzlMhhlkbhk3ihfIRn4YxP0RvxuLcUVWd1wYa607fGZDvHV7-fnULHCpDEY4Q3gOyc46-Jknay0XVNoAzGMHd1knZgGL5LgmybTV1XAwuH8MUSs8jACxcIEScJFUuDOofsUkJ7KyGm-6uNPbIoP6i_1xk_dwUerQfP0p5vjvX9ommxUCpdfeZXbImp3skq1a3YFWg32PvHQr7RSYAz4oFvFwF3dqnHp-bwExlQLqpV2vaw8PVBXQ6fNb-UqRXxI8ZTOkUlEHaykKhDpZinLeJKPe7fCmH1R6DIFhUpSBjLiOTJIUHZaDVZk2MjEaZap1kqvIcCmKPNOxsBJAh_GVeGKtDRbISbiN9kljMp3YQ0KNNiJTSAtimhcAimBi1kroOOYWMtq8RS5ri6SfvuxG6tKVtkqdKVM0ZVqZskWa2LM_nvSd2iLntRVTGDW4FZJN7HQxT1mCuEu6tgfevMvWtVccrXjrMdlgKALs1mFOSKOcLewpIJNSnzmP_AbPsdz4 |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8QgECZGD3rx_VifmHgzrbsUSjkaH1l1txdX3VstlEaj2TVu9-KvdwZaoyYmntoDkJYB5hvgm4-QIybBx3GjAyGSPOA5U4EuC1gMc4jccm4UL5GN3E_j7h2_HophTVZ3XBhrrbt8ZkN8dWf5xdhMcasMZjhDeA7Bzhw4fi48XetrS6UN0Dx2gJd1YhawSA4bmkxbnQzStHcbolp4GAFm4QJF4CKp8GxQ_fBKTmblb8TpPM_lEkmbb_YXTl7CaaVD8_ErneO_f2qZLNYYlJ76QbNCZuxolSw1-g60nu5r5PG8Vk-BVeCVYhoP93D3xqln-JbgVSngXnrule2hQJ0DnT48V08UGSbBff6OZCrqgC1FiVAnTFFN1snd5cXgrBvUigyBYVJUgYy4jkySlB1WgF2ZNjIxGoWqdVKoyHApyiLXsbASYIfxuXhirQ2myEm4jTbI7Gg8sluEGm1ErpAYxDQvARbB0qyV0HHMLcS0RYscNxbJ3nzijcwFLG2VOVNmaMqsNmWLrGPPfivpO7VFDhsrZjBv8DAkH9nxdJKxBJGXdHU3vXm_ajejYvuPVg_IfHfQ72W9q_RmhywwlAR2uzK7ZLZ6n9o9wCmV3nej8xONhOBF |
| 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=Differential+Neural+Network+Identifier+for+Dynamical+Systems+With+Time-Varying+State+Constraints&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Nachevsky%2C+Ilya&rft.au=Andrianova%2C+Olga&rft.au=Chairez%2C+Isaac&rft.au=Poznyak%2C+Alexander&rft.date=2025-01-01&rft.pub=IEEE&rft.issn=2162-237X&rft.volume=36&rft.issue=1&rft.spage=407&rft.epage=418&rft_id=info:doi/10.1109%2FTNNLS.2023.3326450&rft_id=info%3Apmid%2F37903049&rft.externalDocID=10299661 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon |