Deep Neural Networks with Application to Transformer Failure Diagnosis

  • Hugo Riviere S. Moraes UFPA
  • Adriana Rosa Garcez Castro UFPA


This paper presents the outcomes of an application research of deep neural networks to diagnosis incipient faults in power transformer through dissolved gas-in-oil analysis (DGA). Two models was proposed, first, using a Stacked Autoencoder Network and later a Convolucional Neural Network. To the development of the system was used the database TC10 which contains data of faults usually found in electrical equipment in service. This database are described in norm IEC 60599. The outcomes achieved, considering the testing data was 100% and 96,5% of accuracy, showed that this models containing a wide applicability to the problem.


Bacha, K., Souahlia, S., & Gossa, M. (2012). Power transformer fault diagnosis based on dissolved gas analysis by support vector machine. Electric power systems research, 83(1), 73-79.

Cheng, L., & Yu, T. (2018). Dissolved Gas Analysis Principle-Based Intelligent Approaches to Fault Diagnosis and Decision Making for Large Oil-Immersed Power Transformers: A Survey. Energies, 11(4), 913.

Cristopher, M., & Bishop, S. (2006). Pattern recognition and machine learning. Springer, New York, NY.

Castro, A. R. G., Miranda, V., & Lima, S. (2011, September). Transformer fault diagnosis based on autoassociative neural networks. 16th International Conference on Intelligent System Application to Power Systems (ISAP), (pp. 1-5). IEEE.

Castro, A., & Miranda, V. (2010, May). Sistema inteligente para diagnóstico de faltas incipientes em transformadores baseado em redes neurais auto-associativas. In Proceedings of SBSE 2010-Simpósio Brasileiro de Sistemas Elétricos.

da Silva, A. C. M., Castro, A. R. G., & Miranda, V. (2012). Transformer failure diagnosis by means of fuzzy rules extracted from Kohonen Self-Organizing Map. International Journal of Electrical Power & Energy Systems, 43(1), 1034-1042.

de Paiva Penha, D., & Castro, A. R. G. (2017). Convolutional neural network applied to the identification of residential equipment in non-intrusive load monitoring systems. In 3rd International Conference on Artificial Intelligence and Applications (pp. 11-21).

Duval, M., & dePabla, A. (2001). "Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases," in IEEE Electrical Insulation Magazine, vol. 17, no. 2, pp. 31-41.

Fei, S. W., & Zhang, X. B. (2009). Fault diagnosis of power transformer based on support vector machine with genetic algorithm. Expert Systems with Applications, 36(8), 11352-11357.

IEC Publ. 60599. (1999, March). Interpretation of the analysis of gases in transformers and other oil-filled electrical equipment in service.

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).

Japkowicz, N. (2000, July). Learning from imbalanced data sets: a comparison of various strategies. In AAAI workshop on learning from imbalanced data sets (Vol.68, pp. 10-15).

LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436.

LeCun, Y., Haffner, P., Bottou, L., & Bengio, Y. (1999). Object recognition with gradient-based learning. In Shape, contour and grouping in computer vision (pp. 319-345). Springer, Berlin, Heidelberg.

Murphy, K. P. (2012). Machine Learning: A Probabilistic Perspective. Adaptive Computation and Machine Learning. The MIT Press, Cambridge, Massachusetts.

Rao, S., de Medeiros Martins, A., & Príncipe, J. C. (2009). Mean shift: An information theoretic perspective. Pattern Recognition Letters, 30(3), 222-230.

Sanger, T. D. (1989). Optimal unsupervised learning in a single-layer linear feedforward neural network. Neural networks, 2(6), 459-473.

Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for largescale image recognition. arXiv preprint arXiv:1409.1556.

V. Miranda, A. R. G. Castro & S. Lima. (2012, April). Diagnosing Faults in Power Transformers With Autoassociative Neural Networks and Mean Shift. IEEE Transactions on Power Delivery, vol. 27, no. 3, pp. 1350-1357.

Vargas, A. C. G., Paes, A., & Vasconcelos, C. N. (2016, July). Um estudo sobre redes neurais convolucionais e sua aplicação em detecção de pedestres. In Proceedings of the XXIX Conference on Graphics, Patterns and Images (pp. 1-4).

V. Miranda and A. R. G. Castro. (2005, Oct.). "Improving the IEC table for transformer failure diagnosis with knowledge extraction from neural networks," in IEEE Transactions on Power Delivery, vol. 20, no. 4, pp. 2509-2516.

Yang, H. T., & Liao, C. C. (1999). Adaptive fuzzy diagnosis system for dissolved gas analysis of power transformers. IEEE Transactions on Power Delivery, 14(4), 1342-1350.

MORAES, Hugo Riviere S.; CASTRO, Adriana Rosa Garcez. Deep Neural Networks with Application to Transformer Failure Diagnosis. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 15. , 2018, São Paulo. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2018 . p. 287-298. ISSN 2763-9061. DOI: