Academic Journal

Bearing Dynamics Identification with SINDy-Based Neural Network and Physics Model.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Bearing Dynamics Identification with SINDy-Based Neural Network and Physics Model.
Συγγραφείς: Fang, Yu, Li, Zhaorong, Zhu, Liang, Wu, Zhen, Ping, Yan, Zhou, Kai
Πηγή: Machines; Jun2026, Vol. 14 Issue 6, p620, 23p
Θεματικοί όροι: Nonlinear dynamical systems, Mechanical vibration research, Model validation, Software libraries (Computer programming), Finite difference method, Rotor dynamics
Περίληψη: Deep neural networks can fit nonlinear bearing vibration responses, but their learned parameters are difficult to relate to contact deformation, rolling element angular position, and other acceleration-generating mechanisms. To improve physical traceability in data-driven bearing dynamics identification, this study develops a physics-informed SINDy-NN with a mechanism-guided feature library. This paper presents a novel approach for constructing a physics-informed SINDy-NN (Sparse Identification of Nonlinear Dynamics-based Neural Network) and demonstrates its application in identifying bearing dynamics. A 5-DoF (five Degrees of Freedom) bearing dynamics model is built, and the primary components influencing the acceleration response are analyzed. This analysis forms the basis for defining a physics-explainable basis function library for the SINDy-NN. For comparison, widely used polynomial and Fourier libraries are also employed to evaluate modeling accuracy and convergence speed. Furthermore, to address the limited number of bearing data, virtual states are generated by applying multiple finite differences to the acceleration signal, expanding the dimensionality of the model and enabling the use of a Multi-Input–Multi-Output (MIMO) model in SINDy-NN. Finally, experimental data from the FEMTO bearing test bench are utilized for validation. The results demonstrate that the physics-informed SINDy-NN offers superior modeling efficiency, with sufficient accuracy and improved interpretability compared to general SINDy-NN. [ABSTRACT FROM AUTHOR]
Copyright of Machines is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Βάση Δεδομένων: Complementary Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:edb&genre=article&issn=20751702&ISBN=&volume=14&issue=6&date=20260601&spage=620&pages=620-642&title=Machines&atitle=Bearing%20Dynamics%20Identification%20with%20SINDy-Based%20Neural%20Network%20and%20Physics%20Model.&aulast=Fang%2C%20Yu&id=DOI:10.3390/machines14060620
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: edb
DbLabel: Complementary Index
An: 194908192
RelevancyScore: 1082
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1082.4189453125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Bearing Dynamics Identification with SINDy-Based Neural Network and Physics Model.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Fang%2C+Yu%22">Fang, Yu</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Zhaorong%22">Li, Zhaorong</searchLink><br /><searchLink fieldCode="AR" term="%22Zhu%2C+Liang%22">Zhu, Liang</searchLink><br /><searchLink fieldCode="AR" term="%22Wu%2C+Zhen%22">Wu, Zhen</searchLink><br /><searchLink fieldCode="AR" term="%22Ping%2C+Yan%22">Ping, Yan</searchLink><br /><searchLink fieldCode="AR" term="%22Zhou%2C+Kai%22">Zhou, Kai</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Machines; Jun2026, Vol. 14 Issue 6, p620, 23p
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Nonlinear+dynamical+systems%22">Nonlinear dynamical systems</searchLink><br /><searchLink fieldCode="DE" term="%22Mechanical+vibration+research%22">Mechanical vibration research</searchLink><br /><searchLink fieldCode="DE" term="%22Model+validation%22">Model validation</searchLink><br /><searchLink fieldCode="DE" term="%22Software+libraries+%28Computer+programming%29%22">Software libraries (Computer programming)</searchLink><br /><searchLink fieldCode="DE" term="%22Finite+difference+method%22">Finite difference method</searchLink><br /><searchLink fieldCode="DE" term="%22Rotor+dynamics%22">Rotor dynamics</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Deep neural networks can fit nonlinear bearing vibration responses, but their learned parameters are difficult to relate to contact deformation, rolling element angular position, and other acceleration-generating mechanisms. To improve physical traceability in data-driven bearing dynamics identification, this study develops a physics-informed SINDy-NN with a mechanism-guided feature library. This paper presents a novel approach for constructing a physics-informed SINDy-NN (Sparse Identification of Nonlinear Dynamics-based Neural Network) and demonstrates its application in identifying bearing dynamics. A 5-DoF (five Degrees of Freedom) bearing dynamics model is built, and the primary components influencing the acceleration response are analyzed. This analysis forms the basis for defining a physics-explainable basis function library for the SINDy-NN. For comparison, widely used polynomial and Fourier libraries are also employed to evaluate modeling accuracy and convergence speed. Furthermore, to address the limited number of bearing data, virtual states are generated by applying multiple finite differences to the acceleration signal, expanding the dimensionality of the model and enabling the use of a Multi-Input–Multi-Output (MIMO) model in SINDy-NN. Finally, experimental data from the FEMTO bearing test bench are utilized for validation. The results demonstrate that the physics-informed SINDy-NN offers superior modeling efficiency, with sufficient accuracy and improved interpretability compared to general SINDy-NN. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label:
  Group: Ab
  Data: <i>Copyright of Machines is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=194908192
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/machines14060620
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 23
        StartPage: 620
    Subjects:
      – SubjectFull: Nonlinear dynamical systems
        Type: general
      – SubjectFull: Mechanical vibration research
        Type: general
      – SubjectFull: Model validation
        Type: general
      – SubjectFull: Software libraries (Computer programming)
        Type: general
      – SubjectFull: Finite difference method
        Type: general
      – SubjectFull: Rotor dynamics
        Type: general
    Titles:
      – TitleFull: Bearing Dynamics Identification with SINDy-Based Neural Network and Physics Model.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Fang, Yu
      – PersonEntity:
          Name:
            NameFull: Li, Zhaorong
      – PersonEntity:
          Name:
            NameFull: Zhu, Liang
      – PersonEntity:
          Name:
            NameFull: Wu, Zhen
      – PersonEntity:
          Name:
            NameFull: Ping, Yan
      – PersonEntity:
          Name:
            NameFull: Zhou, Kai
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20751702
          Numbering:
            – Type: volume
              Value: 14
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Machines
              Type: main
ResultId 1