Volume 15, Issue 7

Feature Importance-Based Machine Learning Classification of Distribution Trans-former Health Conditions Using Oil Test Data

Author

Omar Ahmed Mohammed Hamood Al-Shaikh, Arfah Ahmad, Muhammad Sharil Yahaya and Ahmad Jazlan Haja Mohideen

Abstract

Transformer health condition assessment is essential for improving the reliability of electric power distribution networks. This paper presents a feature-importance-based machine learning framework for classifying the health condition of oil-immersed distribution transformers using routine oil-test data. The dataset contained 3,373 cleaned diagnostic records after removing exact duplicates and incomplete key identifiers. Thirteen diagnostic inputs were used, including dissolved gas analysis variables, dielectric breakdown strength, moisture, neutralization value, interfacial tension, color and 2-furfural. The continuous transformer health index was converted into five practical classes: Good, Acceptable, Need Caution, Poor and Critical. Seven classifiers were compared using an 80:20 stratified train-test split, namely logistic regression, k-nearest neighbours, support vector machine, multilayer perceptron, random forest, extra trees and gradient boosting. The best model was Gradient Boosting, which achieved 85.04% accuracy and 0.851 weighted F1-score on the independent test set. Feature importance analysis indicated that 2-furfural was the most influential diagnostic variable, followed by dissolved gas indicators such as C2H2, C2H4, C2H6 and CH4, as well as oil-quality variables including dielectric breakdown strength, interfacial tension, neutralization value and moisture. The results show that machine learning can provide a practical decision-support layer for rapid transformer health screening and maintenance prioritization.

Keywords: Transformer Health Index, Distribution Transformer, Machine Learning, Oil Test Data, Feature Importance, Condition Assessment.

DOI: https://doi.org/10.62226/ijarst20262730

 

References:

[1]          I. IEC, "60599—Mineral Oil-Impregnated Electrical Equipment in Service–Guide to the Interpretation of Dissolved and Free Gases Analysis," International Electrotechnical Commission: Geneva, Switzerland, 2015.

[2]          P. T. Committee, "IEEE guide for the interpretation of gases generated in mineral oil-immersed transformers," IEEE Std C, vol. 57, pp. 40–42.

[3]          I. C. 106-, "IEEE guide for acceptance and maintenance of insulating mineral oil in electrical equipment," ed: Institution of Electrical and Electronics Engineers Piscataway, 2015.

[4]          B. EN, "60422: 2013 Mineral insulating oils in electrical equipment. Supervision and maintenance guidance," International Electrotechnical Commission, Geneva, Switzerland, 2013.

[5]          M. I. Oils, "Methods for the Determination of 2-Furfural and Related Compounds," Standard IEC, vol. 61198, 1993.

[6]          B. IEC, "60076-7: 2018," Power Transformers, Part, vol. 7, 2018.

[7]          M. Duval, "A review of faults detectable by gas-in-oil analysis in transformers," IEEE electrical Insulation magazine, vol. 18, no. 3, pp. 8–17, 2002.

[8]          A. Jahromi, R. Piercy, S. Cress, J. Service, and W. Fan, "An approach to power transformer asset management using health index," IEEE Electrical Insulation Magazine, vol. 25, no. 2, pp. 20–34, 2009.

[9]          A. Naderian, S. Cress, R. Piercy, F. Wang, and J. Service, "An approach to determine the health index of power transformers," in Conference Record of the 2008 IEEE International Symposium on Electrical Insulation, 2008: IEEE, pp. 192–196.

[10]        A. Esmaeili Nezhad and M. H. Samimi, "A review of vibration-based techniques for the condition assessment and failure detection of transformers," Journal of Vibration Engineering & Technologies, vol. 13, no. 1, p. 95, 2025.

[11]        M. Arshad and S. M. Islam, "Power transformer condition monitoring and assessment for strategic benefits," Curtin University of Technology Department of Electrical & Computer Engineering, Perth, 2003.

[12]        A. Abu-Siada and S. Islam, "A new approach to identify power transformer criticality and asset management decision based on dissolved gas-in-oil analysis," IEEE Transactions on Dielectrics and Electrical Insulation, vol. 19, no. 3, pp. 1007–1012, 2012.

[13]        M.-H. Wang, "A novel extension method for transformer fault diagnosis," IEEE transactions on power delivery, vol. 18, no. 1, pp. 164–169, 2003.

[14]        M. Wang, A. J. Vandermaar, and K. D. Srivastava, "Review of condition assessment of power transformers in service," IEEE Electrical insulation magazine, vol. 18, no. 6, pp. 12–25, 2003.

[15]        T. K. Saha, "Review of modern diagnostic techniques for assessing insulation condition in aged transformers," IEEE transactions on dielectrics and electrical insulation, vol. 10, no. 5, pp. 903–917, 2003.

[16]        J. Faiz and M. Soleimani, "Assessment of computational intelligence and conventional dissolved gas analysis methods for transformer fault diagnosis," IEEE Transactions on Dielectrics and Electrical Insulation, vol. 25, no. 5, pp. 1798–1806, 2018.

[17]        I. B. Taha, S. S. Ghoneim, and H. G. Zaini, "Improvement of Rogers four ratios and IEC Code methods for transformer fault diagnosis based on Dissolved Gas Analysis," in 2015 North American Power Symposium (NAPS), 2015: IEEE, pp. 1–5.

[18]        A. E. Abu-Elanien, M. Salama, and M. Ibrahim, "Calculation of a health index for oil-immersed transformers rated under 69 kV using fuzzy logic," IEEE transactions on power delivery, vol. 27, no. 4, pp. 2029–2036, 2012.

[19]        W. Cigré, "A2. 37; Transformer Reliability Survey," Technical Brochure, vol. 642, 2015.

[20]        L. A. Zadeh, "Fuzzy sets," Information and control, vol. 8, no. 3, pp. 338–353, 1965.

[21]        T. Hastie, "The elements of statistical learning: data mining, inference, and prediction," ed: springer, 2009.

[22]        A. Emsley and G. Stevens, "Review of chemical indicators of degradation of cellulosic electrical paper insulation in oil-filled transformers," IEE Proceedings-Science, Measurement and Technology, vol. 141, no. 5, pp. 324–334, 1994.

[23]        A. de Pablo, "Furfural and ageing: How are they related," in IEE Colloquium on Insulating Liquids (Ref. No. 1999/119), 1999: IET, pp. 5/1–5/4.

[24]        L. Breiman, "Random forests," Machine learning, vol. 45, no. 1, pp. 5–32, 2001.

[25]        P. Geurts, D. Ernst, and L. Wehenkel, "Extremely randomized trees," Machine learning, vol. 63, no. 1, pp. 3–42, 2006.

[26]        C. Cortes and V. Vapnik, "Support-vector networks Machine learning Vol. 20," ed: Kluwer Academic Publisher, Boston, MA, 1995.

[27]        T. Cover and P. Hart, "Nearest neighbor pattern classification," IEEE transactions on information theory, vol. 13, no. 1, pp. 21–27, 1967.

[28]        J. H. Friedman, "Greedy function approximation: a gradient boosting machine," Annals of statistics, pp. 1189–1232, 2001.

[29]        D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors," nature, vol. 323, no. 6088, pp. 533–536, 1986.

[30]        J. Bergstra and Y. Bengio, "Random search for hyper-parameter optimization," Journal of machine learning research, vol. 13, no. 2, 2012.

[31]        M. Sokolova and G. Lapalme, "A systematic analysis of performance measures for classification tasks," Information processing & management, vol. 45, no. 4, pp. 427–437, 2009.

[32]        H. He and E. A. Garcia, "Learning from imbalanced data," IEEE Transactions on knowledge and data engineering, vol. 21, no. 9, pp. 1263–1284, 2009.

[33]        I. Guyon and A. Elisseeff, "An introduction to variable and feature selection," Journal of machine learning research, vol. 3, no. Mar, pp. 1157–1182, 2003.

DOI

https://doi.org/10.62226/ijarst20262730

PAGES : 2169-2173 | 5 VIEWS | 3 DOWNLOADS

Download Full Article