View in EDS HTML Full Text PDF Full Text

Power Transformer Breathing System Condition Monitoring Based on Pressure–Temperature Optical Sensing and Deep Learning Method.

Saved in:
Bibliographic Details
Title: Power Transformer Breathing System Condition Monitoring Based on Pressure–Temperature Optical Sensing and Deep Learning Method.
Authors: Liang, Jiabi1 (AUTHOR), Shao, Jian1,2 (AUTHOR), Wu, Peng1 (AUTHOR), Li, Qun1,2 (AUTHOR), Lu, Yuncai1 (AUTHOR), Wang, Yalin2 (AUTHOR), Lei, Zhaokai2 (AUTHOR) yikeanee@163.com
Source: Energies (19961073). Mar2026, Vol. 19 Issue 5, p1130. 24p.
Subject Terms: *Power transformers, *Deep learning, *Fabry-Perot interferometers, *Convolutional neural networks, *Fault diagnosis, *Transformer models, *Optical fiber detectors, *Fiber Bragg gratings
Abstract: During long-term operation of power transformers, oil temperature and pressure exhibit strong non-stationarity and multi-scale coupling, which makes early-stage breathing system faults difficult to detect accurately. To address this issue, this paper proposes an integrated diagnosis and early-warning method for transformer breathing systems. It combines a multi-parameter optical sensor with a deep-learning algorithm. The pressure–temperature optical sensing system based on Fabry–Pérot (F–P) interferometry and fiber Bragg grating (FBG) technology is developed to achieve high-precision synchronous measurement of pressure and temperature. To handle the non-stationary and multi-scale characteristics of the measured signals, a swarm-intelligence-optimized variational mode decomposition (VMD) method is employed to adaptively decompose time series temperature and pressure data. On this basis, a joint forecasting model integrating a temporal convolutional network (TCN) and an inverted Transformer (iTransformer) is constructed to capture both local temporal dynamics and long-term dependencies. Furthermore, based on the pressure equilibrium mechanism of transformer breathing systems, oil temperature and equivalent oil level are inferred, and abnormality criteria suitable for both multi-point and single-point monitoring are established. Experimental and field tests on a 220 kV transformer demonstrate that the proposed method outperforms conventional models in prediction accuracy. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 192640855
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Power Transformer Breathing System Condition Monitoring Based on Pressure–Temperature Optical Sensing and Deep Learning Method.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Liang%2C+Jiabi%22">Liang, Jiabi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Shao%2C+Jian%22">Shao, Jian</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wu%2C+Peng%22">Wu, Peng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Qun%22">Li, Qun</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lu%2C+Yuncai%22">Lu, Yuncai</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Yalin%22">Wang, Yalin</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lei%2C+Zhaokai%22">Lei, Zhaokai</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> yikeanee@163.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energies+%2819961073%29%22">Energies (19961073)</searchLink>. Mar2026, Vol. 19 Issue 5, p1130. 24p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Power+transformers%22">Power transformers</searchLink><br />*<searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Fabry-Perot+interferometers%22">Fabry-Perot interferometers</searchLink><br />*<searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br />*<searchLink fieldCode="DE" term="%22Fault+diagnosis%22">Fault diagnosis</searchLink><br />*<searchLink fieldCode="DE" term="%22Transformer+models%22">Transformer models</searchLink><br />*<searchLink fieldCode="DE" term="%22Optical+fiber+detectors%22">Optical fiber detectors</searchLink><br />*<searchLink fieldCode="DE" term="%22Fiber+Bragg+gratings%22">Fiber Bragg gratings</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: During long-term operation of power transformers, oil temperature and pressure exhibit strong non-stationarity and multi-scale coupling, which makes early-stage breathing system faults difficult to detect accurately. To address this issue, this paper proposes an integrated diagnosis and early-warning method for transformer breathing systems. It combines a multi-parameter optical sensor with a deep-learning algorithm. The pressure–temperature optical sensing system based on Fabry–Pérot (F–P) interferometry and fiber Bragg grating (FBG) technology is developed to achieve high-precision synchronous measurement of pressure and temperature. To handle the non-stationary and multi-scale characteristics of the measured signals, a swarm-intelligence-optimized variational mode decomposition (VMD) method is employed to adaptively decompose time series temperature and pressure data. On this basis, a joint forecasting model integrating a temporal convolutional network (TCN) and an inverted Transformer (iTransformer) is constructed to capture both local temporal dynamics and long-term dependencies. Furthermore, based on the pressure equilibrium mechanism of transformer breathing systems, oil temperature and equivalent oil level are inferred, and abnormality criteria suitable for both multi-point and single-point monitoring are established. Experimental and field tests on a 220 kV transformer demonstrate that the proposed method outperforms conventional models in prediction accuracy. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=192640855
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/en19051130
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 1130
    Subjects:
      – SubjectFull: Power transformers
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Fabry-Perot interferometers
        Type: general
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Fault diagnosis
        Type: general
      – SubjectFull: Transformer models
        Type: general
      – SubjectFull: Optical fiber detectors
        Type: general
      – SubjectFull: Fiber Bragg gratings
        Type: general
    Titles:
      – TitleFull: Power Transformer Breathing System Condition Monitoring Based on Pressure–Temperature Optical Sensing and Deep Learning Method.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Liang, Jiabi
      – PersonEntity:
          Name:
            NameFull: Shao, Jian
      – PersonEntity:
          Name:
            NameFull: Wu, Peng
      – PersonEntity:
          Name:
            NameFull: Li, Qun
      – PersonEntity:
          Name:
            NameFull: Lu, Yuncai
      – PersonEntity:
          Name:
            NameFull: Wang, Yalin
      – PersonEntity:
          Name:
            NameFull: Lei, Zhaokai
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 03
              Text: Mar2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 19961073
          Numbering:
            – Type: volume
              Value: 19
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: Energies (19961073)
              Type: main
ResultId 1