Transformer Fault Diagnosis Based on Adaptive Boosting and Bidirectional Long Short-Term Memory Neural Network.
Saved in:
| Title: | Transformer Fault Diagnosis Based on Adaptive Boosting and Bidirectional Long Short-Term Memory Neural Network. |
|---|---|
| Authors: | Shang, Liqun1 851973009@qq.com, Ma, Chuang1 2643742102@qq.com, Li, Aolong1 1754797676@qq.com, Li, Jie1 2516935990@qq.com, Zhu, Yixuan1 3214318417@qq.com |
| Source: | IAENG International Journal of Computer Science. May2026, Vol. 53 Issue 5, p1846-1854. 9p. |
| Subjects: | Fault diagnosis, Boosting algorithms, Long short-term memory, Gas chromatography, Recurrent neural networks, Ensemble learning, Optimization algorithms, Principal components analysis |
| Abstract: | To enhance the performance of transformer fault diagnosis models based on Dissolved Gas Analysis (DGA), this paper proposes a method that optimizes a Bidirectional Long Short-Term Memory (BiLSTM) neural network using an Improved Sparrow Search Algorithm (ISSA) and Adaptive Boosting (AdaBoost). Initially, the Halton sequence and Lévy flight strategy are incorporated into the Sparrow Search Algorithm (SSA), and the resulting ISSA is employed to optimize the key parameters of the BiLSTM network, thereby constructing an ISSA-BiLSTM-based transformer fault diagnosis model. Subsequently, Kernel Principal Component Analysis (KPCA) is applied to the collected oil chromatography data for dimensionality reduction. The reduced-dimensional data are then fed into various transformer fault diagnosis models for simulation and validation. Finally, an ensemble learning model is developed using the AdaBoost algorithm to improve the diagnostic performance of the base classifiers. Experimental results demonstrate that the proposed method achieves excellent performance in terms of diagnostic accuracy and classification effectiveness, enabling accurate identification of fault types in power transformers. [ABSTRACT FROM AUTHOR] |
| Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) 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 | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 193482039 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Transformer Fault Diagnosis Based on Adaptive Boosting and Bidirectional Long Short-Term Memory Neural Network. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Shang%2C+Liqun%22">Shang, Liqun</searchLink><relatesTo>1</relatesTo><i> 851973009@qq.com</i><br /><searchLink fieldCode="AR" term="%22Ma%2C+Chuang%22">Ma, Chuang</searchLink><relatesTo>1</relatesTo><i> 2643742102@qq.com</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Aolong%22">Li, Aolong</searchLink><relatesTo>1</relatesTo><i> 1754797676@qq.com</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Jie%22">Li, Jie</searchLink><relatesTo>1</relatesTo><i> 2516935990@qq.com</i><br /><searchLink fieldCode="AR" term="%22Zhu%2C+Yixuan%22">Zhu, Yixuan</searchLink><relatesTo>1</relatesTo><i> 3214318417@qq.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22IAENG+International+Journal+of+Computer+Science%22">IAENG International Journal of Computer Science</searchLink>. May2026, Vol. 53 Issue 5, p1846-1854. 9p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Fault+diagnosis%22">Fault diagnosis</searchLink><br /><searchLink fieldCode="DE" term="%22Boosting+algorithms%22">Boosting algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Long+short-term+memory%22">Long short-term memory</searchLink><br /><searchLink fieldCode="DE" term="%22Gas+chromatography%22">Gas chromatography</searchLink><br /><searchLink fieldCode="DE" term="%22Recurrent+neural+networks%22">Recurrent neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Ensemble+learning%22">Ensemble learning</searchLink><br /><searchLink fieldCode="DE" term="%22Optimization+algorithms%22">Optimization algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Principal+components+analysis%22">Principal components analysis</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: To enhance the performance of transformer fault diagnosis models based on Dissolved Gas Analysis (DGA), this paper proposes a method that optimizes a Bidirectional Long Short-Term Memory (BiLSTM) neural network using an Improved Sparrow Search Algorithm (ISSA) and Adaptive Boosting (AdaBoost). Initially, the Halton sequence and Lévy flight strategy are incorporated into the Sparrow Search Algorithm (SSA), and the resulting ISSA is employed to optimize the key parameters of the BiLSTM network, thereby constructing an ISSA-BiLSTM-based transformer fault diagnosis model. Subsequently, Kernel Principal Component Analysis (KPCA) is applied to the collected oil chromatography data for dimensionality reduction. The reduced-dimensional data are then fed into various transformer fault diagnosis models for simulation and validation. Finally, an ensemble learning model is developed using the AdaBoost algorithm to improve the diagnostic performance of the base classifiers. Experimental results demonstrate that the proposed method achieves excellent performance in terms of diagnostic accuracy and classification effectiveness, enabling accurate identification of fault types in power transformers. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) 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=193482039 |
| RecordInfo | BibRecord: BibEntity: Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 9 StartPage: 1846 Subjects: – SubjectFull: Fault diagnosis Type: general – SubjectFull: Boosting algorithms Type: general – SubjectFull: Long short-term memory Type: general – SubjectFull: Gas chromatography Type: general – SubjectFull: Recurrent neural networks Type: general – SubjectFull: Ensemble learning Type: general – SubjectFull: Optimization algorithms Type: general – SubjectFull: Principal components analysis Type: general Titles: – TitleFull: Transformer Fault Diagnosis Based on Adaptive Boosting and Bidirectional Long Short-Term Memory Neural Network. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Shang, Liqun – PersonEntity: Name: NameFull: Ma, Chuang – PersonEntity: Name: NameFull: Li, Aolong – PersonEntity: Name: NameFull: Li, Jie – PersonEntity: Name: NameFull: Zhu, Yixuan IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 05 Text: May2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 1819656X Numbering: – Type: volume Value: 53 – Type: issue Value: 5 Titles: – TitleFull: IAENG International Journal of Computer Science Type: main |
| ResultId | 1 |
