Multiclass Fault Diagnosis in Power Transformers Using Dissolved Gas Analysis and Grid Search-Optimized Machine Learning

Andrew Adewunmi Adekunle (), Issouf Fofana (), Patrick Picher, Esperanza Mariela Rodriguez-Celis, Oscar Henry Arroyo-Fernandez, Hugo Simard and Marc-André Lavoie
Additional contact information
Andrew Adewunmi Adekunle: Canada Research Chair Tier 1, in Aging of Oil-Filled Equipment on High Voltage Lines (ViAHT), University of Quebec at Chicoutimi, Chicoutimi, QC G7H 2B1, Canada
Issouf Fofana: Canada Research Chair Tier 1, in Aging of Oil-Filled Equipment on High Voltage Lines (ViAHT), University of Quebec at Chicoutimi, Chicoutimi, QC G7H 2B1, Canada
Patrick Picher: Hydro Quebec Research Institute, Varennes, QC J3X 1S1, Canada
Esperanza Mariela Rodriguez-Celis: Hydro Quebec Research Institute, Varennes, QC J3X 1S1, Canada
Oscar Henry Arroyo-Fernandez: Hydro Quebec Research Institute, Varennes, QC J3X 1S1, Canada
Hugo Simard: Rio Tinto, Saguenay, QC G7S 2H8, Canada
Marc-André Lavoie: Rio Tinto, Saguenay, QC G7S 2H8, Canada

Energies, 2025, vol. 18, issue 13, 1-30

Abstract: Dissolved gas analysis remains the most widely utilized non-intrusive diagnostic method for detecting incipient faults in insulating liquid-immersed transformers. Despite their prevalence, conventional ratio-based methods often suffer from ambiguity and limited potential for automation applicrations. To address these limitations, this study proposes a unified multiclass classification model that integrates traditional gas ratio features with supervised machine learning algorithms to enhance fault diagnosis accuracy. The performance of six machine learning classifiers was systematically evaluated using training and testing data generated through four widely recognized gas ratio schemes. Grid search optimization was employed to fine-tune the hyperparameters of each model, while model evaluation was conducted using 10-fold cross-validation and six performance metrics. Across all the diagnostic approaches, ensemble models, namely random forest, XGBoost, and LightGBM, consistently outperformed non-ensemble models. Notably, random forest and LightGBM classifiers demonstrated the most robust and superior performance across all schemes, achieving accuracy, precision, recall, and F1 scores between 0.99 and 1, along with Matthew correlation coefficient values exceeding 0.98 in all cases. This robustness suggests that ensemble models are effective at capturing complex decision boundaries and relationships among gas ratio features. Furthermore, beyond numerical classification, the integration of physicochemical and dielectric properties in this study revealed degradation signatures that strongly correlate with thermal fault indicators. Particularly, the CIGRÉ-based classification using a random forest classifier demonstrated high sensitivity in detecting thermally stressed units, corroborating trends observed in chemical deterioration parameters such as interfacial tension and CO 2 /CO ratios. Access to over 80 years of operational data provides a rare and invaluable perspective on the long-term performance and degradation of power equipment. This extended dataset enables a more accurate assessment of ageing trends, enhances the reliability of predictive maintenance models, and supports informed decision-making for asset management in legacy power systems.

Keywords: power transformer; dissolved gas analysis; diagnostic techniques; physicochemical and dielectric properties; machine learning models (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/13/3535/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/13/3535/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:13:p:3535-:d:1694570

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().