Skip to main content
SpringerLink
Log in

Using counterpropagation neural networks for partial discharge diagnosis

  • Articles
  • Published:
Neural Computing & Applications Aims and scope Submit manuscript

Abstract

In high voltage engineering, various methods of non-destructive fault diagnosis are applied for investigating the quality of insulating materials and systems. The methods are aimed at classifying patterns derived from the measured characteristics of the electrical signals typically resulting from insulation defects. In this paper, variants of the counterpropagation neural network architecture are used to classify patterns representing various properties of partial discharges. It is shown that the classification quality can be improved considerably when an extended counterpropagation network with a dynamically changing network topology, and an additional vigilance unit for monitoring the behaviour of the network during the learning phase is applied. The extended network has significant advantages over the standard counterpropagation network in cases where outliers in the training data seriously degrade the approximation quality of the standard network. When using the proposed network in conjunction with physically motivated discharge data, input patterns from defect categories not considered during training can be rejected more reliably. This rejection problem is particularly important for practical applications where misclassifications cannot be tolerated.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Gulski E. Computer-aided Recognition of Partial Discharges Using Statistical Tools. PhD Thesis, Delft University of Technology, The Netherlands, 1991

    Google Scholar 

  2. Kranz H-G, Krump R. Partial discharge diagnosis using statistical optimization on a PC based system. IEEE Trans Electrical Insulation 1992; 27(1): 93–98

    Google Scholar 

  3. Hücker T, Kranz H-G. Requirements of automated PD diagnosis systems for fault identification in noisy conditions. IEEE Trans Dielectrics and Electrical Insulation 1995; 2(4): 544–556

    Google Scholar 

  4. Krivda A. Automated recognition of partial discharges. IEEE Trans Dielectrics and Electrical Insulation 1995; 2(5): 796–821

    Google Scholar 

  5. CIGRE Working Group 21.03. Recognition of Discharges. Electra 1969; 11: 61–98

    Google Scholar 

  6. Hozumi N, Okamoto T, Imajo T. Discrimination of partial discharge patterns using a neural network. IEEE Trans Electrical Insulation 1992; 27(3): 550–556

    Google Scholar 

  7. Satish L, Gururaj BI. Partial discharge pattern classification using multilayer neural networks. IEE Proc A 1993; 140(4): 323–330

    Google Scholar 

  8. Mazroua AA, Salama MMA, Bartnikas R. PD pattern recognition with neural networks using the multilayer perceptron technique. IEEE Trans Electrical Insulation 1993; 28(6): 1082–1089

    Google Scholar 

  9. Satish L, Zaengl WS. Artificial neural networks for recognition of 3-D partial discharge patterns. IEEE Trans Dielectrics and Electrical Insulation 1994; 1(2): 265–275

    Google Scholar 

  10. Oyama M, Hanai E, Aoyagi H, Murase H, Ohshima I, Menju S. Development of detection and diagnostic techniques for partial discharge in GIS. IEEE Trans Power Delivery 1994; 9(2): 811–818

    Google Scholar 

  11. Mazroua AA, Bartnikas R, Salama MMA. Discrimination between PD pulse shapes using different neural network paradigms. IEEE Trans Dielectrics and Electrical Insulation 1994; 1(6): 1119–1131

    Google Scholar 

  12. Okamoto T, Tanaka T. Partial discharge pattern recognition for three kinds of model electrodes with a neural network. IEE Proc Sci Meas Technol 1995; 142(1): 75–84

    Google Scholar 

  13. Cachin C, Wiesmann HJ. PD recognition with knowledge-based preprocessing and neural networks. IEEE Trans Dielectrics and Electrical Insulation 1995; 2(4): 578–589

    Google Scholar 

  14. Krivda A. Recognition of discharges discrimination and classification. PhD Thesis, Delft University of Technology, The Netherlands, 1995

    Google Scholar 

  15. Schnettler A, Tryba V. Artificial self-organizing neural network for partial discharge source recognition. Archiv für Elektrotechnik 1993; 76(2): 149–154.

    Google Scholar 

  16. Engel K, Peier D. Influence of PD fault development on fault type recognition using an artificial neural network. Int Symp on High Voltage Engineering, Graz, Austria, 1995: 5861-1-4

  17. Hoof M, Freisleben B, Patsch R. PD source identification with novel discharge parameters using counterpropagation neural networks. IEEE Trans Dielectrics and Electrical Insulation 1997; 4(1): 17–32

    Google Scholar 

  18. Borsi H, Gockenbach E, Wenzel D. Separation of partial discharges from pulse-shaped noise signals with the help of neural networks. IEE Proc Sci Meas Technol 1995; 12(1): 69–74.

    Google Scholar 

  19. Hecht-Nielsen R. Counterpropagation networks. Applied Optics 1987; 26: 4979–1984

    Google Scholar 

  20. Hecht-Nielsen R. Applications of counterpropagation networks. Neural Networks 1988; 1: 131–139

    Google Scholar 

  21. Rumelhart DE, Hinton G, Williams RE. Learning internal representations by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructures of Cognition, Vol 1, MIT Press, 1986: 318–362

  22. Carpenter GA, Grossberg S. The ART of adaptive pattern recognition by a self-organizing neural network. IEEE Computer 1988; 3: 77–88

    Google Scholar 

  23. Hoof M. Pulse-sequence-analysis: A new method of partial discharge diagnosis (in German). PhD Thesis, Universität-GH Siegen, Germany, 1997

    Google Scholar 

  24. Mason JH. The deterioration and breakdown of dielectrics resulting from internal discharges. Proc IEEE, Part 1 1951; 98: 44–59

    Google Scholar 

  25. Morshuis PHF. Partial discharge mechanisms. PhD Thesis, Delft University of Technology, The Netherlands, 1993

    Google Scholar 

  26. Van Brunt RJ. Physics and chemistry of partial discharge and corona — recent advances and future challenges. IEEE Trans Dielectrics and Electrical Insulation 1994; 1(5): 761–784

    Google Scholar 

  27. Niemeyer L. A generalised approach to partial discharge modeling. IEEE Trans Dielectrics and Electrical Insulation 1995; 2(4): 510–528

    Google Scholar 

  28. Kreuger FH. Partial discharge detection in high voltage equipment. Butterworth & Co, 1989

  29. Crichton GC, Karlsson PW, Pedersen A. Partial discharges in ellipsoidal and spheroidal voids. IEEE Trans Electrical Insulation 1989; 24(2): 335–342

    Google Scholar 

  30. Fruth B, Fuhr J. Partial discharge pattern recognition — a tool for diagnosis and monitoring of aging. CIGRE, Paris, France, Paper 15/33-12, 1990

    Google Scholar 

  31. Stone GC. The use of partial discharge measurements to assess the condition of rotating machine insulation. IEEE Electrical Insulation Magazine 1996; 12(4): 23–27

    Google Scholar 

  32. Komori F, Hikita M, Suzuoki Y, Mizutani T. Study of partial discharge occurrence patterns for construction of degradation diagnosis system. Int Conf on Properties and Applications of Dielectric Materials, Seoul, Korea, 1997; 224–227

  33. Florkowska B. Analysis of partial discharge mechanisms and their patterns for diagnosis of insulation systems. Int Conf on Properties and Applications of Dielectric Materials, Seoul, Korea, 1997; 279–282

  34. Krivda A, Halén S. Recognition of PD patterns in generators. Int Conf on Properties and Applications of Dielectric Materials, Seoul, Korea, 1997; 206–211

  35. Hoof M, Patsch R. Pulse-sequence-analysis: A new method to investigate the physics of PD-induced ageing. IEE Proc Sci Meas Technol 1995; 142(1): 95–101

    Google Scholar 

  36. Hoof M, Patsch R. Voltage-difference analysis, a tool for partial discharge source identification. IEEE Int Symp on Electrical Insulation, Montreal, Canada, 1996; 401–406

  37. Kohonen T. Self-Organization and Associative Memory. Springer-Verlag, 1989

  38. Grossberg S. Embedding fields: A theory of learning with physiological implications. J Mathematical Psychology 1969; 6: 209–239

    Google Scholar 

  39. Hecht-Nielsen R. Neurocomputing. Addison-Wesley, 1990

  40. Freisleben B. Pattern classification with vigilant counterpropagation. 2nd IEE Int Conf Artificial Neural Networks, Bournemouth, UK, 1991; 252–256

  41. Freisleben B, Gleichmann G. Controlling airline seat allocations with neural networks. 26th Annual Hawaii Int Conf on System Sciences (HICSS-26), 1993; 635–642

  42. Zell A. Simulation of neural networks (in German). Addison-Wesley, 1994

  43. Kramer MA, Leonard JA. Diagnosis using backpropagation neural networks — analysis and criticism. Computers and Chemical Eng 1990; 14(12): 1323–1338

    Google Scholar 

  44. Hoof M, Patsch R. Investigation of PD resulting from transformers using the PSA method. Conference on Electrical Insulation and Dielectric Materials, Minneapolis, USA, 1997

Download references

Author information

Authors and Affiliations

  1. Department of Electrical Engineering and Computer Science (FB 12), University of Siegen, Hölderlinstr. 3, D-57068, Siegen, Germany

    B. Freisleben, M. Hoof & R. Patsch

Authors
  1. B. Freisleben
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. Hoof
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. R. Patsch
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to B. Freisleben.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Freisleben, B., Hoof, M. & Patsch, R. Using counterpropagation neural networks for partial discharge diagnosis. Neural Comput & Applic 7, 318–333 (1998). https://doi.org/10.1007/BF01428123

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01428123

Keywords

Search

Navigation