View in EDS

Fault diagnosis of high-speed train suspension systems under variable speeds based on dynamic transfer loss weight-deep subdomain adaptation network.

Saved in:
Bibliographic Details
Title: Fault diagnosis of high-speed train suspension systems under variable speeds based on dynamic transfer loss weight-deep subdomain adaptation network.
Authors: Yang, Funing1 (AUTHOR), Hua, Chunrong1 (AUTHOR), Mu, Junyi1 (AUTHOR), Huang, Yan1 (AUTHOR), Liu, Weiqun1 (AUTHOR), Dong, Dawei1 (AUTHOR)
Source: Advanced Engineering Informatics. Mar2025, Vol. 64, pN.PAG-N.PAG. 1p.
Subjects: Machine learning, Fault diagnosis, Motor vehicle springs & suspension, High speed trains, Visual learning
Abstract: • The requirement of one single sensor, which greatly reduced the complexity of sensor and data management. • Implementing unsupervised training-based fault diagnosis. • A new method for automatically updating transfer loss weight for DSAN has been developed, which is generalizable and applicable to other domain adaptation-based transfer learning algorithms and application areas. Fault diagnosis of suspension systems under variable speeds is crucial for the safe operation of high-speed trains. However, the machine learning-based fault diagnosis of suspension systems is hindered by the requirements for multiple sensors, supervised training, and reliance on expert experience for setting the transfer loss weight in domain adaptation methods. Using the wavelet packet energy method and the coefficient of variation, this study developed a sensitivity indicator for vibration signals at different locations to suspension components faults, and determined the center of the bogie frame as the optimal single sensor location. Based on the Euclidean distance between feature tensors output by the backbone network, an approach to dynamically update the transfer loss weight suitable for domain adaptation was proposed. A dynamic transfer loss weight-deep subdomain adaptation network (DTLW-DSAN) was constructed to dynamically adjust the network's focus on source domain feature extraction and target domain adaptation, which can realize accurate and rapid network fitting. The proposed DTLW-DSAN achieved an average diagnosis accuracy of 93.09 % for the primary cylindrical spring, primary damper, and air spring of a high-speed train suspension system under wide-range speed variations (between 100, 200, and 300 km/h). The DTLW-DSAN's generality was validated using the visual transfer learning public dataset Office-31. [ABSTRACT FROM AUTHOR]
Copyright of Advanced Engineering Informatics is the property of Elsevier B.V. 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.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 183242149
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Fault diagnosis of high-speed train suspension systems under variable speeds based on dynamic transfer loss weight-deep subdomain adaptation network.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yang%2C+Funing%22">Yang, Funing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hua%2C+Chunrong%22">Hua, Chunrong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Mu%2C+Junyi%22">Mu, Junyi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Huang%2C+Yan%22">Huang, Yan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Weiqun%22">Liu, Weiqun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Dong%2C+Dawei%22">Dong, Dawei</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Advanced+Engineering+Informatics%22">Advanced Engineering Informatics</searchLink>. Mar2025, Vol. 64, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Fault+diagnosis%22">Fault diagnosis</searchLink><br /><searchLink fieldCode="DE" term="%22Motor+vehicle+springs+%26+suspension%22">Motor vehicle springs & suspension</searchLink><br /><searchLink fieldCode="DE" term="%22High+speed+trains%22">High speed trains</searchLink><br /><searchLink fieldCode="DE" term="%22Visual+learning%22">Visual learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: • The requirement of one single sensor, which greatly reduced the complexity of sensor and data management. • Implementing unsupervised training-based fault diagnosis. • A new method for automatically updating transfer loss weight for DSAN has been developed, which is generalizable and applicable to other domain adaptation-based transfer learning algorithms and application areas. Fault diagnosis of suspension systems under variable speeds is crucial for the safe operation of high-speed trains. However, the machine learning-based fault diagnosis of suspension systems is hindered by the requirements for multiple sensors, supervised training, and reliance on expert experience for setting the transfer loss weight in domain adaptation methods. Using the wavelet packet energy method and the coefficient of variation, this study developed a sensitivity indicator for vibration signals at different locations to suspension components faults, and determined the center of the bogie frame as the optimal single sensor location. Based on the Euclidean distance between feature tensors output by the backbone network, an approach to dynamically update the transfer loss weight suitable for domain adaptation was proposed. A dynamic transfer loss weight-deep subdomain adaptation network (DTLW-DSAN) was constructed to dynamically adjust the network's focus on source domain feature extraction and target domain adaptation, which can realize accurate and rapid network fitting. The proposed DTLW-DSAN achieved an average diagnosis accuracy of 93.09 % for the primary cylindrical spring, primary damper, and air spring of a high-speed train suspension system under wide-range speed variations (between 100, 200, and 300 km/h). The DTLW-DSAN's generality was validated using the visual transfer learning public dataset Office-31. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Advanced Engineering Informatics is the property of Elsevier B.V. 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=egs&AN=183242149
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.aei.2024.103091
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Fault diagnosis
        Type: general
      – SubjectFull: Motor vehicle springs & suspension
        Type: general
      – SubjectFull: High speed trains
        Type: general
      – SubjectFull: Visual learning
        Type: general
    Titles:
      – TitleFull: Fault diagnosis of high-speed train suspension systems under variable speeds based on dynamic transfer loss weight-deep subdomain adaptation network.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yang, Funing
      – PersonEntity:
          Name:
            NameFull: Hua, Chunrong
      – PersonEntity:
          Name:
            NameFull: Mu, Junyi
      – PersonEntity:
          Name:
            NameFull: Huang, Yan
      – PersonEntity:
          Name:
            NameFull: Liu, Weiqun
      – PersonEntity:
          Name:
            NameFull: Dong, Dawei
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 03
              Text: Mar2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 14740346
          Numbering:
            – Type: volume
              Value: 64
          Titles:
            – TitleFull: Advanced Engineering Informatics
              Type: main
ResultId 1