Cluster Computing

, Volume 22, Supplement 4, pp 8363–8370 | Cite as

Fault diagnosis for oil-filled transformers using voting based extreme learning machine

  • Liwei ZhangEmail author
  • Jian Zhai


Extreme learning machine (ELM) based fault diagnosis for oil-filled transformers overcomes some drawbacks faced by that using traditional learning algorithms. Since the randomized hidden nodes are used and they remain unchanged during the training phase, some samples may be misclassified near the classification boundary. To reduce the number of such misclassified samples, fault diagnosis using voting based ELM (V-ELM) was proposed in this paper. The V-ELM-based diagnosis method incorporates multiple independent ELMs to improve the classification performance. Firstly, the user-specified parameter of individual ELM was chosen for dissolved gas analysis samples through experiment. Then, the unstable performance of individual ELM was demonstrated on testing samples. Finally, the network complexities and performance of V-ELM-based diagnosis were compared with original ELM approaches. Experimental results show that the proposed method achieves a much higher correct classification rate and the performance is more reliable.


Power transformers Fault diagnosis Dissolved gas analysis Extreme learning machine Majority voting method 



The authors acknowledge the Doctoral Scientific Research Foundation of Northeast Electric Power University (no. BSJXM-201401), China.


  1. 1.
    Miceli, R., Favuzza, S., Genduso, F.: A perspective on the future of distribution: smart grids, state of the art, benefits and research plans. Energy Power Eng. 5(1), 36–42 (2013)CrossRefGoogle Scholar
  2. 2.
    Zeinoddini-Meymand, H., Vahidi, B.: Techno-economical lifetime assessment of power transformers rated over 50 MVA using artificial intelligence models. IET Gener. Transm. Distrib. 10(15), 3885–3892 (2016)CrossRefGoogle Scholar
  3. 3.
    Bakar, N., Abu-Siada, A., Islam, S.: A review of dissolved gas analysis measurement and interpretation techniques. IEEE Electr. Insul. Mag. 30(3), 39–49 (2014)CrossRefGoogle Scholar
  4. 4.
    Degeratu, S., Rotaru, P., Rizescu, S., et al.: Condition monitoring of transformer oil using thermal analysis and other techniques. J. Therm. Anal. Calorim. 119(3), 1679–1692 (2015)CrossRefGoogle Scholar
  5. 5.
    Abu-Siada, A., Islam, S.: A new approach to identify power transformer criticality and asset management decision based on dissolved gas-in-oil analysis. IEEE Trans. Dielectr. Electr. Insul. 19(3), 1007–1012 (2012)CrossRefGoogle Scholar
  6. 6.
    Mansour, D.E.A.: Development of a new graphical technique for dissolved gas analysis in power transformers based on the five combustible gases. IEEE Trans. Dielectr. Electr. Insul. 22(5), 2507–2512 (2015)CrossRefGoogle Scholar
  7. 7.
    Mani, G., Jerome, J.: Intuitionistic fuzzy expert system based fault diagnosis using dissolved gas analysis for power transformer. J. Electr. Eng. Technol. 9(6), 2058–2064 (2014)CrossRefGoogle Scholar
  8. 8.
    Bhalla, D., Bansal, R.K., Gupta, H.O.: Function analysis based rule extraction from artificial neural networks for transformer incipient fault diagnosis. Int. J. Electr. Power Energy Syst. 43(1), 1196–1203 (2012)CrossRefGoogle Scholar
  9. 9.
    Illias, H., Chai, X., Abu Bakar, A.: Hybrid modified evolutionary particle swarm optimisation-time varying acceleration coefficient-artificial neural network for power transformer fault diagnosis. J. Int. Meas. Confed. 90, 94–102 (2016)CrossRefGoogle Scholar
  10. 10.
    Khan, S., Equbal, M., Islam, T.: A comprehensive comparative study of DGA based transformer fault diagnosis using fuzzy logic and ANFIS models. IEEE Trans. Dielectr. Electr. Insul. 22(1), 590–596 (2015)CrossRefGoogle Scholar
  11. 11.
    Huang, Y.C., Sun, H.C.: Dissolved gas analysis of mineral oil for power transformer fault diagnosis using fuzzy logic. IEEE Trans. Dielectr. Electr. Insul. 20(3), 974–981 (2013)CrossRefGoogle Scholar
  12. 12.
    Li, J., Zhang, Q., Wang, K., et al.: Optimal dissolved gas ratios selected by genetic algorithm for power transformer fault diagnosis based on support vector machine. IEEE Trans. Dielectr. Electr. Insul. 23(2), 1198–1206 (2016)CrossRefGoogle Scholar
  13. 13.
    Wei, C., Tang, W., Wu, Q.: Dissolved gas analysis method based on novel feature prioritisation and support vector machine. IET Electr. Power Appl. 8(8), 320–328 (2014)CrossRefGoogle Scholar
  14. 14.
    Ghoneim, S.S.M., Taha, I.B.M., Elkalashy, N.I.: Integrated ANN-based proactive fault diagnostic scheme for power transformers using dissolved gas analysis. IEEE Trans. Dielectr. Electr. Insul. 23(3), 1838–1845 (2016)CrossRefGoogle Scholar
  15. 15.
    Huang, G.B., Zhou, H., Ding, X., et al.: Extreme learning machine for regression and multiclass classification. IEEE Trans. Syst. Man Cybern. Part B 42(2), 513–529 (2012)CrossRefGoogle Scholar
  16. 16.
    Malik, H., Mishra, S., Mittal, A.: Selection of most relevant input parameters using waikato environment for knowledge analysis for gene expression programming based power transformer fault diagnosis. Electr. Power Compon. Syst. 42(16), 1849–1861 (2014)CrossRefGoogle Scholar
  17. 17.
    Cao, J., Lin, Z., Huang, G.B., et al.: Voting based extreme learning machine. Inf. Sci. 185(1), 66–77 (2014)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70(1–3), 489–501 (2006)CrossRefGoogle Scholar
  19. 19.
    Roncero-Clemente, C., Roanes-Lozano, E.: A multi-criteria computer package for power transformer fault detection and diagnosis. Appl. Math. Comput. 319, 153–164 (2018)zbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Electrical EngineeringNortheast Electric Power UniversityJilinChina
  2. 2.State Grid Xi’an Electric Power Supply CompanyXi’anChina

Personalised recommendations