Application of Principal Component Analysis (PCA) and SVMs for Discharges Radiated Fields Discrimination

  • Mohamed GueraichiEmail author
  • Azzedine Nacer
  • Hocine Moulai
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 858)


This paper proposes the use of a fast method of discriminating magnetic signals radiated from electrical discharges occurring in overhead lines string insulations. Two types of electrical discharges exist: dangerous that can lead to arcing discharges and those without danger that auto extinguish. We propose as a new method of discriminating and classifying partial discharges principal component analysis (PCA) combined with support vector machines (SVMs) which have proved their robustness in several disciplines. However, the used database is composed of two classes, the majority representing 130 harmless radiated magnetic field signals, while the second minority class represents 31 dangerous signals. The learning and test sets correspond respectively to 2/3 and 1/3 of the database. The SVMs application to the test set shows that no dangerous signal is detected, this being due to the fact that the two classes are unbalanced. We were then asked to apply the Principal Component Analysis (PCA) even before classification, which made it able to select the most relevant variables. The results show that by using PCA and then SVMs, the detection rate of a dangerous signal is 90%.


Partial discharges (PD) Insulation systems Support Vector Machines (SVMs) Principal component analysis (PCA) 


  1. 1.
    Aberkane, F., Moulai, H., Benyahia, F., Nacer, A., Beroual, A.: Pre-breakdown current discrimination diagnose technique for transformer mineral oil. In: IEEE Conference on Electrical Insulation and Dielectric Phenomena, 14–17 October 2012, Montreal, Quebec, Canada (2012)Google Scholar
  2. 2.
    Aberkane, F., Nacer, A., Moulai, H., Benyahia, F., Beroual, A.: ANN and multilinear regression line based discrimination technique between discharge currents for power transformers diagnosis. In: 2nd International Advances in Applied Physics and Material Science Congress, 26–29 April 2012, Antalya, Turkey (2012)Google Scholar
  3. 3.
    Aberkane, F., Moulai, H., Nacer, A., Benyahia, F., Beroual, A.: ANN and wavelet based discrimination technique between discharge currents in transformers mineral oil. Eur. Phys. J. Appl. Phys. 58, 20801 (2012)CrossRefGoogle Scholar
  4. 4.
    Moulai, H.: Etude des Courants de Préclaquage dans les Diélectriques Liquides. Thèse de Doctorat d’Etat, Ecole Nationale Polytechnique, Alger, Algerie (2001)Google Scholar
  5. 5.
    Aberkane, F.: Etude des Processus de Décharges Electriques dans les Diélectriques Liquides. Université des Sciences et de la Technologie Houari Boumèdiene, Alger, Algérie, Thèse de Doctorat (2015)Google Scholar
  6. 6.
    Schenk, A.: Surveillance Continue des Transformateurs de Puissance par Réseaux de Neurones Auto-Organiséés. Thèse de Doctorat, Ecole Polytechnique Fédérale de Lausanne (2001)Google Scholar
  7. 7.
    Sanchez, J.: Aide au Diagnostic de défauts des Transformateurs de Puissance. Université de Grenoble, Thèse de Doctorat (2006)Google Scholar
  8. 8.
    Marques de Sá, J.P.: Pattern Recognition, Concepts, Methods and Applications, pp. 21–39. Springer, Heidelberg (2001), pp 147–239Google Scholar
  9. 9.
    Cheriet, M., Kharma, N., Liu, C.L., Suen, C.Y.: Character Recognition System, pp. 129–199. Wiley, New York (2007)Google Scholar
  10. 10.
    Vapnik, V.: The Nature of Statistical Learning Theory, 2nd edn. Springer, New York (1999)zbMATHGoogle Scholar
  11. 11.
    Platt, J.C.: Fast training of support vector machines using sequential minimal optimisation. In: Scholkopf, B., Burges, C., Smola, A. (eds.) Advances in Kernel Methods-Support Vector Machines, pp. 185–208. MIT Press, Cambridge (1999). Chap 12Google Scholar
  12. 12.
    Abidine, M.B., Fergani, B., Oussalah, M., Fergani, L.: A new classification strategy for human activity recognition using cost sensitive support vector machines for imbalanced data. Kybernet J. 43(8), 1150–1164 (2014)Google Scholar
  13. 13.
    Webb, A.R.: Statistical Pattern Recognition, 2nd edn., pp. 319–329. Wiley, Hoboken (2002)Google Scholar
  14. 14.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn., pp 114–115 (2002)Google Scholar
  15. 15.
    Chawla, N.V., Japkowicz, N., Kotcz, A.: Editorial: special issue on learning from imbalanced data sets. SIGKDD Explor. 6(1), 1–6 (2004)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Mohamed Gueraichi
    • 1
    Email author
  • Azzedine Nacer
    • 1
  • Hocine Moulai
    • 1
  1. 1.Laboratory of Electrical and Industrial Systems, Faculty of Electronic and Computer ScienceUniversity of Sciences and Technology Houari Boumediene (USTHB)Bab Ezzouar, AlgiersAlgeria

Personalised recommendations