Studies on the prediction of power transformer condition immersed in mineral insulating oil by applied mathematical fitting models

Authors

DOI:

https://doi.org/10.47456/bjpe.v10i4.46503

Keywords:

Fit, maintenance, performance index, power transformer, prediction

Abstract

Power transformers are fundamental to the electrical system regarding the continuous supply of energy, thus requiring effective tools for predictive maintenance. Therefore, the objective of this work is the accurate prediction of performance indices for non-invasive predictive techniques applied to the evaluation of transformers, offering an innovative approach applicable to different scenarios. Additionally, the overall performance index of the equipment is used as a reference to support decision-making. In this sense, the methodology adopted includes curve fitting for three predictive techniques: dissolved gas analysis, physical-chemical tests, and degree of polymerization/2FAL-Furfuraldehydes. In the results, five types of fittings were tested (linear, quadratic, exponential, Gaussian, and sum of sines), and the analytical expressions that best modeled the data were determined. The worst-case scenario criterion was considered to calculate the time intervals for each classification. Validation was carried out with training/testing data splits, using the Root Mean Square Error (RMSE) as a performance metric. It is concluded that the second-degree polynomial fit is the best fit for modeling performance indices, proving the effectiveness of the methodology developed in this work.

Downloads

Download data is not yet available.

Author Biographies

  • Vinicius Faria Costa Mendanha, Federal University of Goiás

    Born on May 19, 1998. He is currently a master's student in the Postgraduate Program in Electrical and Computer Engineering at the Federal University of Goiás. He graduated in Electrical Engineering from the Federal University of Goiás (UFG) in 2023. In 2018-2019, he joined the Polytechnic Association of UFG, in the area of ​​Administration. In 2019, he joined the PET (Tutorial Education Program) Engenharias Conexão de Saberes, also carrying out Scientific Initiation. He studied signal analysis and Gibbs phenomenon (2019-2020). He is dedicated to the study of Computational Intelligence applied to the area of ​​power transformer maintenance and is a member of the High Voltage Engineering Research Laboratory - LAPEAT UFG Team.

  • André Pereira Marques, Federal University of Goiás

    Was born on February 25, 1961 in Araguari, Minas Gerais, Brazil. He earned his PhD (2018) in Electrical Engineering from the School of Electrical, Mechanical and Computing Engineering School (EMC) of the Federal University of Goiás (UFG). He is full Professor at the Federal Institute of Education, Science and Technology of Goiás (IFG) since 1990, working in the Courses of Electrical Engineering, Automation Engineering and Electrotechnical Course. His is also the Technical Manager of APMarques Consultoria e Capacitação em Engenharia Elétrica (Consulting and Training in Electrical Engineering) since 2019, specialist in power transformer diagnostics and loading studies and is member of the High Voltage Engineering Research Laboratory Team - LAPEAT UFG.

  • Yuri Andrade Dias, Federal University of Goiás

    Was born on October 25, 1994 in Goiânia, Goiás, Brazil. He earned his PhD (2023) in Electrical Engineering from the School of Electrical, Mechanical and Computer Engineering of the Federal University of Goiás. Currently, he is manager in the Department of Maintenance Engineering of High Voltage Substations at Equatorial Energia Goiás and a member of the High Voltage Research Laboratory Team at EMC/UFG

  • Cacilda de Jesus Ribeiro, Federal University of Goiás

    Was born on August 8, 1971 in Matão, São Paulo, Brazil. She earned her PhD (2002) and postdoctoral degree (2004) in Electrical Engineering from the São Carlos School of Engineering, University of São Paulo. She is full professor at the School of Electrical, Mechanical and Computer Engineering (EMC) at the Federal University of Goiás (UFG) and is Coordinator of the High Voltage Engineering Research Laboratory - LAPEAT UFG.

References

Aizpurua, J. I., McArthur, S. D. J., Stewart, B. G., Lambert, B., Cross, J. G., & Catterson, V. M. (2019). Adaptive Power Transformer Lifetime Predictions Through Machine Learning and Uncertainty Modeling in Nuclear Power Plants. IEEE Transactions on Industrial Electronics, 66(6), 4726-4737. https://doi.org/10.1109/TIE.2018.2860532 DOI: https://doi.org/10.1109/TIE.2018.2860532

Azmi, A., Jasni, J., Azis, N., & Kadir, M. Z. A. Ab. (2017). Evolution of transformer health index in the form of mathematical equation. Renewable and Sustainable Energy Reviews, 76, 687-700. https://doi.org/10.1016/j.rser.2017.03.094 DOI: https://doi.org/10.1016/j.rser.2017.03.094

Dias, Y. (2019). Rede Bayesiana para Estimativa da Confiabilidade de Transformadores e Potência Imersos em Óleo Mineral Isolante Utilizando Técnicas Preditivas de Manutenção [Dissertação (Mestrado)]. Universidade Federal de Goiás.

Dias, Y. A. (2022). Índice de desempenho em transformador de potência [Relatório interno]. Universidade Federal de Goiás.

Dutta, S., Dey, J., Mishra, D., Baral, A., & Chakravorti, S. (2022). Prediction of Insulation Sensitive Parameters of Power Transformer Using Detrended Fluctuation Analysis Based Method. IEEE Transactions on Power Delivery, 37(3), 1963-1973. https://doi.org/10.1109/TPWRD.2021.3102075 DOI: https://doi.org/10.1109/TPWRD.2021.3102075

Faveri, R. de. (2021). Modelagem Térmica de Transformadores – Método de Regressão Linear Múltipla para Previsão de Variáveis. [Dissertação (Mestrado)].

Ferreira, A. M. J. (2015). Cálculo de índices de saúde, vida restante e probabilidade de falha de transformadores de potência AT/MT. [Dissertação (Mestrado)]. Universidade do Porto.

Fortes, M. Z., Junior, H. D. P. A., Atair Cesar Domingueti Junior, Abrita, R. M., & Albquerque, C. J. M. (2006). Lógica fuzzy como ferramenta para diagnóstico de falhas em transformadores. https://doi.org/10.13140/RG.2.1.3446.2242

Gouda, O. E. & El Dein, A. Z. (2019). Prediction of Aged Transformer Oil and Paper Insulation. Electric Power Components and Systems, 47(4-5), 406-419. https://doi.org/10.1080/15325008.2019.1604848 DOI: https://doi.org/10.1080/15325008.2019.1604848

Karunasingha, D. S. K. (2022). Root mean square error or mean absolute error? Use their ratio as well. Information Sciences, 585, 609-629. https://doi.org/10.1016/j.ins.2021.11.036 DOI: https://doi.org/10.1016/j.ins.2021.11.036

Lin, J., Su, L., Yan, Y., Sheng, G., Xie, D., & Jiang, X. (2018). Prediction Method for Power Transformer Running State Based on LSTM_DBN Network. Energies, 11(7), 1880. https://doi.org/10.3390/en11071880 DOI: https://doi.org/10.3390/en11071880

Luo, D., Fang, J., He, H., Lee, W.-J., Zhang, Z., Zai, H., Chen, W., & Zhang, K. (2022). Prediction for Dissolved Gas in Power Transformer Oil Based on TCN and GCN. IEEE Transactions on Industry Applications, 58(6), 7818-7826. https://doi.org/10.1109/TIA.2022.3197565 DOI: https://doi.org/10.1109/TIA.2022.3197565

Marques, A. P. (2018). Diagnóstico otimizado de transformadores de potência mediante a integração de técnicas preditivas [Tese (Doutorado)]. Universidade Federal de Goiás.

Press, W. H., Teukolsky, S. A., Vetterling, W. T., & Flannery, B. P. (2011). Métodos numéricos aplicados: Rotinas em C++. 3. Ed. Porto Alegre: Bookman, 2011. 1261 p. Tradução técnica: Sílvio Renato Dahmen e Roberto da Silva. (3a ed). Bookman.

Ribeiro, V. M. A. (2016). Desenvolvimento e Análise de Indicadores de Condição de Transformadores de Potência. [Dissertação (Mestrado)]. Universidade do Porto.

Serrano, L. F. L., De Azevêdo, V. M., & Carneiro Lins, A. J. D. C. (2020). Ferramenta de Aprendizado de Máquina para Previsão de Falha de Transformadores de Rede Elétrica. Revista de Engenharia e Pesquisa Aplicada, 5(2), 44-50. https://doi.org/10.25286/repa.v5i2.1351 DOI: https://doi.org/10.25286/repa.v5i2.1351

Silva, D. G. T. da. (2020). Índice de saúde aprimorado para diagnóstico de transformadores de potência. Universidade Estadual de São Paulo.

Silva, D. G. T. da, Braga Da Silva, H. J., Marafão, F. P., Paredes, H. K. M., & Gonçalves, F. A. S. (2021). Enhanced health index for power transformers diagnosis. Engineering Failure Analysis, 126, 105427. https://doi.org/10.1016/j.engfailanal.2021.105427 DOI: https://doi.org/10.1016/j.engfailanal.2021.105427

Sodré, B. R., G. Sotelo, G., & Ferreira, V. H. (2020, agosto 13). Estimativa do Tempo para Falha de Transformadores de Potência Utilizando Dados do Centro de Operação e Redes Neurais Artificiais. Anais do Simpósio Brasileiro de Sistemas Elétricos 2020. Simpósio Brasileiro de Sistemas Elétricos - SBSE2020. https://doi.org/10.48011/sbse.v1i1.2149 DOI: https://doi.org/10.48011/sbse.v1i1.2149

Soni, R. & Mehta, B. (2022). Evaluation of power transformer health analysis by internal fault criticalities to prevent premature failure using statistical data analytics approach. Engineering Failure Analysis, 136, 106213. https://doi.org/10.1016/j.engfailanal.2022.106213 DOI: https://doi.org/10.1016/j.engfailanal.2022.106213

Suñe, J. & Heredia, L. A. (2013). Guia de Manutenção para Transformadores de Potência. Cigré Brasil. https://cigre.org.br/brochuras/

Taghikhani, M. A. & Gholami, A. (2009). Prediction of hottest spot temperature in power transformer windings with non-directed and directed oil-forced cooling. International Journal of Electrical Power & Energy Systems, 31(7-8), 356-364. https://doi.org/10.1016/j.ijepes.2009.03.009 DOI: https://doi.org/10.1016/j.ijepes.2009.03.009

Xie, P. (2019). Analysis of fault of insulation aging of oiled paper of a large‐scale power transformer and the prediction of its service life. IEEJ Transactions on Electrical and Electronic Engineering, 14(8), 1139-1144. https://doi.org/10.1002/tee.22911 DOI: https://doi.org/10.1002/tee.22911

Downloads

Published

2024-12-10

Issue

Vol. 10 No. 4 (2024): Regular Issue (October - December)

Section

ENERGY

License

Copyright (c) 2024 Vinicius Faria Costa Mendanha, André Pereira Marques, Yuri Andrade Dias, Cacilda de Jesus Ribeiro (Autor)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

All works published in the Brazilian Journal of Production Engineering (BJPE) are licensed under Creative Commons Attribution 4.0 International (CC BY 4.0).

This means that:

Anyone can copy, distribute, display, adapt, remix, and even commercially use the content published in the journal;

Provided that due credit is given to the authors and to BJPE as the original source;

No additional permission is required for reuse, as long as the license terms are respected.

This policy complies with the principles of open access, promoting the broad dissemination of scientific knowledge.

🔗 Click here to access the full license

How to Cite

Mendanha, V. F. C., Marques, A. P., Dias, Y. A., & Ribeiro, C. de J. (2024). Studies on the prediction of power transformer condition immersed in mineral insulating oil by applied mathematical fitting models. Brazilian Journal of Production Engineering, 10(4), 226-240. https://doi.org/10.47456/bjpe.v10i4.46503

Similar Articles

1-10 of 856

You may also start an advanced similarity search for this article.