Fault diagnosis in power transformers using Multilayer Perceptron Neural network models
Article Sidebar
Main Article Content
Abstract
Power transformers are among the most expensive and essential elements in the functioning of electrical networks. Dissolved gas analysis (DGA) enables the detection of dissolved gas concentrations in insulating oil, associated with thermal faults, partial discharges, and both high- and low-energy discharges. These gas correlations enable the assessment of the transformer’s condition. In recent years, the use of machine learning techniques, such as artificial neural networks, has seen an increase in the prediction, diagnosis, and management of faults, displaying high performance in spotting anomalies and aiding decision-making in the field of maintenance. The present study developed a multi-label Multilayer Perceptron (MLP) model, which considers transformer fault diagnoses calculated using the Dornenburg, Rogers, Duval triangle, and gas procedures recommended by IEC & IEEE standards. This enables the utilization of several fault diagnosis for each transformer via each approach. The model underwent validation by k-Fold cross-validation, achieving an exact match rate of 90.95%, which pertains to instances where the model aligned with all labels specified by each diagnostic procedure. The ROC curve, with an area under the curve of 99%, and the Accuracy-Completeness curve, with an average accuracy of 99.3%, were generated graphically.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Los autores conservan los derechos de autor y ceden a la revista el derecho de la primera publicación y pueda editarlo, reproducirlo, distribuirlo, exhibirlo y comunicarlo en el país y en el extranjero mediante medios impresos y electrónicos. Asimismo, asumen el compromiso sobre cualquier litigio o reclamación relacionada con derechos de propiedad intelectual, exonerando de responsabilidad a la Editorial Tecnológica de Costa Rica. Además, se establece que los autores pueden realizar otros acuerdos contractuales independientes y adicionales para la distribución no exclusiva de la versión del artículo publicado en esta revista (p. ej., incluirlo en un repositorio institucional o publicarlo en un libro) siempre que indiquen claramente que el trabajo se publicó por primera vez en esta revista.
References
[1] R. Zemouri, “Power Transformer Prognostics and Health Management Using Machine Learning: A Review and Future Directions,” Machines, vol. 13, no. 2, Art. no. 125, Feb. 2025, doi: 10.3390/machines13020125. Available: https://www.mdpi.com/2075-1702/13/2/125
[2] J. Zupan, “Introduction to Artificial Neural Network (ANN) Methods: What They Are and How to Use Them,” Acta Chimica Slovenica, vol. 41, no. 3, pp. 327–352, 1994. Available: https://acta.chem-soc.si
[3] W. Wu, G. C. Dandy, and H. R. Maier, “Protocol for Developing ANN Models and Its Application to the Assessment of the Quality of the ANN Model Development Process in Drinking Water Quality Modelling,” Environmental Modelling & Software, vol. 54, pp. 108–127, Apr. 2014, doi: 10.1016/j.envsoft.2013.12.016.
[4] P. H. Mukti, F. A. Pamuji, and B. S. Munir, “Implementation of Artificial Neural Networks for Determining Power Transformer Condition,” in Proc. 10th Int. Conf. Information Technology and Electrical Engineering (ICITEE), Surabaya, Indonesia, 2022, pp. 1–6, doi: 10.1109/ICITEE56409.2022.9970234.
[5] J. D. Moposita, D. G. Pujos, S. Marrero-Ramírez, and R. Salazar-Archig, “Aplicación de Redes Neuronales en el Análisis de Gases Disueltos para el Mantenimiento Preventivo de Transformadores de Potencia,” Revista Ibérica de Sistemas e Tecnologias de Informação (RISTI), no. E73, pp. 312–327, Sep. 2024. Available: https://www.risti.xyz
[6] E. Moradi, “A Data-Driven Based Robust Multilayer Perceptron Approach for Fault Diagnosis of Power Transformers,” in Proc. 20th CSI Int. Symp. Artificial Intelligence and Signal Processing (AISP), Babol, Iran, 2024, doi: 10.1109/AISP61396.2024.10445872.
[7] IEEE Power & Energy Society, IEEE Guide for the Interpretation of Gases Generated in Mineral Oil-Immersed Transformers, IEEE Std C57.104-2019, New York, NY, USA: IEEE, 2019, doi: 10.1109/IEEESTD.2019.8890040.
[8] International Electrotechnical Commission, Mineral Oil-Filled Electrical Equipment in Service — Guidance on the Interpretation of Dissolved and Free Gases Analysis, IEC 60599, 4th ed., Geneva, Switzerland: IEC, 2022. Available: https://webstore.iec.ch/publication/67220
[9] H.-C. Sun, Y.-C. Huang, and C.-M. Huang, “A Review of Dissolved Gas Analysis in Power Transformers,” Energy Procedia, vol. 14, pp. 1220–1225, 2012, doi: 10.1016/j.egypro.2011.12.1120.
[10] J. T. Sarria-Arias, N. A. Guerrero-Bello, and E. Rivas-Trujillo, “Estado del Arte del Análisis de Gases Disueltos en Transformadores de Potencia,” Revista Facultad de Ingeniería, no. 36, pp. 105–122, 2014. Available: https://revistas.udea.edu.co
[11] R. R. Rogers, “IEEE and IEC Codes to Interpret Incipient Faults in Transformers, Using Gas in Oil Analysis,” IEEE Transactions on Electrical Insulation, vol. EI-13, no. 5, pp. 349–354, Oct. 1978, doi: 10.1109/TEI.1978.298141.
[12] M. H. A. Hamid et al., “Dissolved Gas Analysis (DGA) of Natural Ester Oils under Arcing Faults,” Journal of Fundamental and Applied Sciences, vol. 9, no. 3S, pp. 105–115, Sep. 2017, doi: 10.4314/jfas.v9i3s.8.
[13] N. Abu Bakar, A. Abu-Siada, and S. Islam, “A Review of Dissolved Gas Analysis Measurement and Interpretation Techniques,” IEEE Electrical Insulation Magazine, vol. 30, no. 3, pp. 39–49, May–Jun. 2014, doi: 10.1109/MEI.2014.6804740.
[14] S. Etemadi, M. Khashei, and S. Tamizi, “Reliability-Based Multilayer Perceptrons for Classification and Forecasting,” Information Sciences, vol. 651, Art. no. 119716, 2023, doi: 10.1016/j.ins.2023.119716.
[15] A. Hashemi Fath, F. Madanifar, and M. Abbasi, “Implementation of Multilayer Perceptron (MLP) and Radial Basis Function (RBF) Neural Networks to Predict Solution Gas–Oil Ratio of Crude Oil Systems,” Petroleum, vol. 6, no. 1, pp. 80–91, 2020, doi: 10.1016/j.petlm.2018.12.002.
[16] A. D. Rasamoelina, F. Adjailia, and P. Sinčák, “A Review of Activation Function for Artificial Neural Network,” in Proc. IEEE 18th World Symp. Applied Machine Intelligence and Informatics (SAMI), Herľany, Slovakia, Jan. 2020, pp. 281–286, doi: 10.1109/SAMI48414.2020.9108717.
[17] M.-C. Popescu, V. E. Balas, L. Perescu-Popescu, and N. Mastorakis, “Multilayer Perceptron and Neural Networks,” WSEAS Transactions on Circuits and Systems, vol. 8, no. 7, pp. 579–588, Jul. 2009. Available: https://wseas.com
[18] N. V. G. Raju, K. P. Lakshmi, V. M. Jain, A. Kalidindi, and V. Padma, “Study the Influence of Normalization/Transformation Process on the Accuracy of Supervised Classification,” in Proc. 3rd Int. Conf. Smart Systems and Inventive Technology (ICSSIT), 2020, pp. 729–734, doi: 10.1109/ICSSIT48917.2020.9214263.
[19] S. M. Malakouti, M. B. Menhaj, and A. A. Suratgar, “The Usage of 10-Fold Cross-Validation and Grid Search to Enhance ML Methods Performance in Solar Farm Power Generation Prediction,” Cleaner Engineering and Technology, vol. 15, Art. no. 100664, 2023, doi: 10.1016/j.clet.2023.100664.
[20] R.-E. Fan and C.-J. Lin, “A Study on Threshold Selection for Multi-Label Classification,” Journal of Machine Learning Research, vol. 7, pp. 2115–2146, 2007. Available: https://www.jmlr.org
[21] G. A. Gómez-Ramírez, “Medición de Descargas Parciales en Transformadores de Potencia bajo los Estándares Internacionales IEC e IEEE,” Tecnología en Marcha, vol. 31, no. 1, pp. 70–80, 2018, doi: 10.18845/tm.v31i1.3498.
[22] S. A. Wani, D. Gupta, M. U. Farooque, and S. A. Khan, “Multiple Incipient Fault Classification Approach for Enhancing the Accuracy of Dissolved Gas Analysis (DGA),” IET Science, Measurement & Technology, vol. 13, no. 7, pp. 959–967, 2019, doi: 10.1049/iet-smt.2018.5135.