Multiclass Fault Diagnosis in Power Transformers Using Dissolved Gas Analysis and Grid Search-Optimized Machine Learning
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...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/18/13/3535 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839631839153618944 |
|---|---|
| author | Andrew Adewunmi Adekunle Issouf Fofana Patrick Picher Esperanza Mariela Rodriguez-Celis Oscar Henry Arroyo-Fernandez Hugo Simard Marc-André Lavoie |
| author_facet | Andrew Adewunmi Adekunle Issouf Fofana Patrick Picher Esperanza Mariela Rodriguez-Celis Oscar Henry Arroyo-Fernandez Hugo Simard Marc-André Lavoie |
| author_sort | Andrew Adewunmi Adekunle |
| collection | DOAJ |
| description | 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<sub>2</sub>/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. |
| format | Article |
| id | doaj-art-af8c3f5f4dc044f9830e70c342e6f0e5 |
| institution | Matheson Library |
| issn | 1996-1073 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-af8c3f5f4dc044f9830e70c342e6f0e52025-07-11T14:39:22ZengMDPI AGEnergies1996-10732025-07-011813353510.3390/en18133535Multiclass Fault Diagnosis in Power Transformers Using Dissolved Gas Analysis and Grid Search-Optimized Machine LearningAndrew Adewunmi Adekunle0Issouf Fofana1Patrick Picher2Esperanza Mariela Rodriguez-Celis3Oscar Henry Arroyo-Fernandez4Hugo Simard5Marc-André Lavoie6Canada Research Chair Tier 1, in Aging of Oil-Filled Equipment on High Voltage Lines (ViAHT), University of Quebec at Chicoutimi, Chicoutimi, QC G7H 2B1, CanadaCanada Research Chair Tier 1, in Aging of Oil-Filled Equipment on High Voltage Lines (ViAHT), University of Quebec at Chicoutimi, Chicoutimi, QC G7H 2B1, CanadaHydro Quebec Research Institute, Varennes, QC J3X 1S1, CanadaHydro Quebec Research Institute, Varennes, QC J3X 1S1, CanadaHydro Quebec Research Institute, Varennes, QC J3X 1S1, CanadaRio Tinto, Saguenay, QC G7S 2H8, CanadaRio Tinto, Saguenay, QC G7S 2H8, CanadaDissolved 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<sub>2</sub>/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.https://www.mdpi.com/1996-1073/18/13/3535power transformerdissolved gas analysisdiagnostic techniquesphysicochemical and dielectric propertiesmachine learning models |
| spellingShingle | Andrew Adewunmi Adekunle Issouf Fofana Patrick Picher Esperanza Mariela Rodriguez-Celis Oscar Henry Arroyo-Fernandez Hugo Simard Marc-André Lavoie Multiclass Fault Diagnosis in Power Transformers Using Dissolved Gas Analysis and Grid Search-Optimized Machine Learning Energies power transformer dissolved gas analysis diagnostic techniques physicochemical and dielectric properties machine learning models |
| title | Multiclass Fault Diagnosis in Power Transformers Using Dissolved Gas Analysis and Grid Search-Optimized Machine Learning |
| title_full | Multiclass Fault Diagnosis in Power Transformers Using Dissolved Gas Analysis and Grid Search-Optimized Machine Learning |
| title_fullStr | Multiclass Fault Diagnosis in Power Transformers Using Dissolved Gas Analysis and Grid Search-Optimized Machine Learning |
| title_full_unstemmed | Multiclass Fault Diagnosis in Power Transformers Using Dissolved Gas Analysis and Grid Search-Optimized Machine Learning |
| title_short | Multiclass Fault Diagnosis in Power Transformers Using Dissolved Gas Analysis and Grid Search-Optimized Machine Learning |
| title_sort | multiclass fault diagnosis in power transformers using dissolved gas analysis and grid search optimized machine learning |
| topic | power transformer dissolved gas analysis diagnostic techniques physicochemical and dielectric properties machine learning models |
| url | https://www.mdpi.com/1996-1073/18/13/3535 |
| work_keys_str_mv | AT andrewadewunmiadekunle multiclassfaultdiagnosisinpowertransformersusingdissolvedgasanalysisandgridsearchoptimizedmachinelearning AT issouffofana multiclassfaultdiagnosisinpowertransformersusingdissolvedgasanalysisandgridsearchoptimizedmachinelearning AT patrickpicher multiclassfaultdiagnosisinpowertransformersusingdissolvedgasanalysisandgridsearchoptimizedmachinelearning AT esperanzamarielarodriguezcelis multiclassfaultdiagnosisinpowertransformersusingdissolvedgasanalysisandgridsearchoptimizedmachinelearning AT oscarhenryarroyofernandez multiclassfaultdiagnosisinpowertransformersusingdissolvedgasanalysisandgridsearchoptimizedmachinelearning AT hugosimard multiclassfaultdiagnosisinpowertransformersusingdissolvedgasanalysisandgridsearchoptimizedmachinelearning AT marcandrelavoie multiclassfaultdiagnosisinpowertransformersusingdissolvedgasanalysisandgridsearchoptimizedmachinelearning |