Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

Feature extraction of partial discharge signals using the wavelet packet transform and classification with a probabilistic neural network

Feature extraction of partial discharge signals using the wavelet packet transform and classification with a probabilistic neural network

For access to this article, please select a purchase option:

Buy article PDF
$19.95
(plus tax if applicable)
Buy Knowledge Pack
10 articles for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Science, Measurement & Technology — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Partial discharge (PD) classification in power cable accessories and high voltage equipment in general is essential in evaluating the severity of the damage in the insulation. In this article, the PD classification was realised as a two-fold process. Firstly, measurements taken from a high-frequency current transformer (HFCT) sensor were represented as features by means of a transformation to the classifier and secondly, the probabilistic neural network (PNN) classifier itself was capable of effectively recognising features coming from different types of discharges. The feature that was used as a fingerprint for PD characterisation was extracted from the moments of the probability density function (PDF) of the wavelet coefficients at various scales, obtained through the wavelet packets transformation. The PNN classifier was used to classify the PDs and assess the suitability of this feature vector in PD classification. Four types of artificial PDs were created in a high voltage laboratory, namely corona discharge in air, floating discharge in oil, internal discharge in oil and surface discharge in air, at different applied voltages, and were used to train the PNN algorithm. The results obtained here (97.49, 91.9, 100 and 99.8% for the corona, the floating, the internal and the surface discharges, respectively) are very encouraging for the use of PNN in PD classification with this particular feature vector. This article suggests a feature extraction and classification algorithm for PD classification, which when combined together reduced the dimensionality of the feature space to a manageable dimension, and achieved very high levels of classification.

References

    1. 1)
      • D. Donoho , I.M. Jonestone . Adapting to unknown smoothness via wavelet shrinkage. J. Am. Stat. Assoc. , 432 , 1200 - 1224
    2. 2)
      • Hao, L., Lewin, P.L., Dodd, S.J.: `Comparison of support vector machine based partial discharge identification parameters', IEEE Int. Symp. on Electrical Insulation, June 2006, Toronto, Canada, p. 110–113.
    3. 3)
      • A.M. Atto , D. Pastor , A. Isar . Review: on the statistical decorrelation of the wavelet packet coefficients of a band-limited wide-sense stationary random process. Signal Process. , 10 , 2320 - 2335
    4. 4)
      • S.J. Press . (1982) Applied multivariate analysis.
    5. 5)
      • A.P. Dempster , N.M. Laird , D.B. Rubin . Maximum likelihood from incomplete data via the em algorithm. Ann. Math. Stat. , 1 - 38
    6. 6)
      • R.B. Murphy . Non-parametric tolerance limits. Ann. Math. Stat. , 4 , 581 - 589
    7. 7)
      • R.L. Streit , T.E. Luginbuhl . Maximum likelihood training of probabilistic neural networks. IEEE Trans. Neural Netw. , 764 - 783
    8. 8)
      • Tian, Y., Lewin, P., Wang, P., Sutton, S.J., Swingler, S.G.: `Application of wavelet-based denoising to online measurement of partial discharges', Proc. Int. Conf. on Solid Dielectrics, July 2004.
    9. 9)
    10. 10)
      • Tian, Y., Lewin, P., Davies, A., Hathaway, G.: `Acoustic emission techniques for partial discharge detection within cable insulation', Eighth Int. Conf. on Dielectric Materials, Measurements and Applications, 2000, (IEE Conf. Publ. No. 473), September 2000, p. 503–508, doi: 00888169.
    11. 11)
    12. 12)
      • E. Carminati , L. Cristaldi , M. Lazzaroni , A. Monti . A neuro-fuzzy approach for the detection of partial discharge. IEEE Trans. Instrum. Meas. , 5 , 1413 - 1417
    13. 13)
      • D.L. Donoho , I.M. Johnstone . Ideal spatial adaptation by wavelet shrinkage. Biometrika , 3 , 425 - 455
    14. 14)
      • Poyhonen, S., Conti, M., Cavallini, A., Montanari, G., Filippetti, F.: `Insulation defect localization through partial discharge measurements and numerical classification', IEEE Int. Symp. on Industrial Electronics, May 2004, p. 417–422.
    15. 15)
      • T. Cacoullos . Estimation of a multivariate density. Ann. Math. Stat. , 2 , 179 - 189
    16. 16)
      • Hao, L., Lewin, P.L., Tian, Y., Dodd, S.J.: `Partial discharge identification using a support vector machine', IEEE Conf. on Electrical Insulation and Dielectric Phenomena, March 2005, p. 414–417.
    17. 17)
      • B. Fruth , L. Niemeyer . The importance of statistical characteristics of partial discharge data. IEEE Trans. Electr. Insul. , 1 , 60 - 69
    18. 18)
    19. 19)
      • Evagorou, D., Kyprianou, A., Lewin, P.L., Stavrou, A., Efthymiou, V., Georghiou, G.E.: `Classification of partial discharge signals using probabilistic neural network', IEEE Int. Conf. on Solid Dielectrics (ICSD), July 2007, p. 609–615.
    20. 20)
    21. 21)
      • Henningsen, C.G., Polster, K., Fruth, B.A., Gross, D.W.: `Experience with an on-line monitoring system for 400 kV xlpe cable', IEEE Proc. on Transmission and Distribution Conf., 1996, September 1996, p. 515–520, tDC.1996.547564.
    22. 22)
      • IEC 60270 Partial Discharge Measurements. International Electrotechnical Commission, 2000.
    23. 23)
      • A. Mazroua , M. Salama , R. Bartnikas . Neural network system using the multi-layer perceptron technique for the recognition of pd pulse shapes due to cavities and electrical trees. IEEE Trans. Power Deliv. , 1 , 92 - 96
    24. 24)
      • Meijer, S., Agoris, P., Seitz, P., Hermans, T.: `Condition assessment of power cable accessories using advanced vhf/uhf pd detection', Conf. Record 2006 IEEE Int. Symp. on Electrical Insulation, 2006, June 2006, p. 482–485.
    25. 25)
      • Cabletrend-continuous monitor for pd in power cables.
    26. 26)
      • R. Sharkawy , R. Mangoubi , T. Abdel-Galil , M. Salama , R. Bartnikas . Svm classification of contaminating particles in liquid dielectrics using higher order statistics of electrical and acoustic pd measurements. IEEE Trans. Dielectr. Electr. Insul. , 3 , 669 - 678
    27. 27)
      • Kemp, I.J.: `Developments in partial discharge plant-monitoring technology', Proc. Int. Conf. on Partial Discharge, 1993, p. 52–55.
    28. 28)
      • E. Gulski , A. Krivda . Neural networks as a tool for recognition of partial discharges. IEEE Trans. Electr. Insul. , 6 , 984 - 1001
    29. 29)
    30. 30)
      • Lemke, E., Strehl, T., Weissenberg, W., Herron, J.: `Practical experiences in on-site pd diagnosis tests of ', Conf. Record 2006 IEEE Int. Symp. on Electrical Insulation, 2006, June 2006, p. 498–501.
    31. 31)
      • H. Ota , M. Ichihara , N. Miyamoto . Application of advanced after-laying test to long-distance 275 kV xlpe cable lines. IEEE Trans. Power Deliv. , 2 , 567 - 579
    32. 32)
      • A. Cavallini , G. Montanari , F. Puletti , A. Contin , G. Pasini . Digital detection and fuzzy classification of partial discharge signals. IEEE Trans. Dielectr. Electr. Insul. , 3 , 335 - 348
    33. 33)
      • H. Zhang , T. Blackburn , B. Phung , D. Sen . A novel wavelet transform technique for on-line partial discharge measurements. 1. wt de-noising algorithm. IEEE Trans. Dielectr. Electr. Insula. , 1 , 3 - 14
    34. 34)
      • A. Mazroua , M. Salama , R. Bartnikas . Discrimination between pd pulse shapes using different neural network paradigms. IEEE Trans. Dielectr. Electr. Insul. , 6 , 1119 - 1131
    35. 35)
      • Hao, L., Lewin, P.L., Swingler, S.G.: `Identification of multiple partial discharge sources', Int. Conf. on Condition Monitoring and Diagnosis, April 2008, p. 118–121.
    36. 36)
      • Jang, J.-K., Kim, S.-H., Lee, Y.-S., Kim, J.-H.: `Classification of partial discharge electrical signals using wavelet transforms', Proc. 1999 IEEE 13th Int. Conf. on Dielectric Liquids, June 1999, p. 552–555.
    37. 37)
      • Hao, L., Lewin, P., Dodd, S.: `Comparison of support vector machine based partial discharge identification parameters', Conf. Record of the 2006 IEEE Int. Symp. on Electrical Insulation, June 2006, p. 110–113.
    38. 38)
      • R. Candela , G. Mirelli , R. Schifani . Pd recognition by means of statistical and fractal parameters and a neural network. IEEE Trans. Dielectr. Electr. Insul. , 1 , 87 - 94
    39. 39)
      • E. Gulski . Computer-aided measurement of partial discharges in hv equipment. IEEE Trans. Electr. Insul. , 6 , 969 - 983
    40. 40)
      • H. Zhang , T. Blackburn , B. Phung , D. Sen . A novel wavelet transform technique for on-line partial discharge measurements. 2. on-site noise rejection application. IEEE Trans. Dielectr. Electr. Insula. , 1 , 15 - 22
    41. 41)
      • C. Chang , J. Jin , S. Kumar , Q. Su , T. Hoshino , M. Hanai , N. Kobayashi . Denoising of partial discharge signals in wavelet packets domain. IEE Proc. Sci. Measur. Technol. , 3 , 129 - 140
    42. 42)
      • A. Mazroua , M. Salama , R. Bartnikas . Pd pattern recognition with neural networks using the multilayer perceptron technique. IEEE Trans. Dielectr. Electr. Insul. , 6 , 1082 - 1089
    43. 43)
      • V. Vapnik . (1995) The nature of statistical learning theory.
    44. 44)
      • P. Morshuis . Assessment of dielectric degradation by ultrawide band pd detection. IEEE Trans. Dielectr. Electr. Insul. , 5 , 744 - 760
    45. 45)
      • Plath, R., Herrmann, U., Polster, K., Spiegelberg, J., Coors, P.: `After laying tests of 400 kV xlpe cable systems for bewag berlin', 11thInt. Symp. on High Voltage Engineering, 1999, (Conf. Publ. No. 467), August 1999, 5, no. 2, pp. 276–279, doi: 00818291.
    46. 46)
      • N.H. Ahmed , N.N. Srinivas . On-line partial discharge detection in cables. IEEE Trans. Dielectr. Electr. Insul. , 2 , 181 - 188
    47. 47)
      • Zhang, H., Blackburn, T., Phung, B., , L.Z.: `Application of signal processing techniques to on-line partial discharge detection in cables', Proc. Int. Conf. on Power System Technology – POWERCON 2004, 2004.
    48. 48)
      • E. Gulski . Digital analysis of partial discharges. IEEE Trans. Dielectr. Electr. Insul. , 5 , 822 - 837
    49. 49)
      • M. Salama , R. Bartnikas . Determination of neural-network topology for partial discharge pulse pattern recognition. IEEE Trans. Neural Netw. , 2 , 446 - 456
    50. 50)
      • N. Sahoo , M. Salama , R. Bartnikas . Trends in partial discharge pattern classification: a survey. IEEE Trans. Dielectr. Electr. Insul. , 2 , 248 - 264
    51. 51)
      • Y. Tian , P. Lewin , A. Davies . Comparison of on-line partial discharge detection methods for hv cable joints. IEEE Trans. Dielectr. Electr. Insul. , 4 , 604 - 615
    52. 52)
      • Tu, Y., Wang, Z., Crossley, P.: `Partial discharge pattern recognition based on 2-d wavelet transform and neural network techniques', IEEE Power Engineering Society Summer Meeting, 2002, June 2002, 1, p. 411–416.
    53. 53)
      • B. Scholkopf , A. Smola . (2002) Learning with kernels: support vector machines, regularization, optimization and beyond.
    54. 54)
      • V. Kecman . (2001) Learning and soft computing: support vector machines, neural networks and Fuzzy logic models.
    55. 55)
      • J.T. Tou , R.C. Gonzales . (1974) Pattern recognition principles.
    56. 56)
      • E. Parzen . On the estimation of a probability density function and mode. Ann. Math. Stat. , 1065 - 1076
    57. 57)
      • D. Specht . Generation of polynomial discriminant functions for pattern recognition. IEEE Trans. Electron. Comput. , 3 , 308 - 319
    58. 58)
      • Evagorou, D., Kyprianou, A., Lewin, P., Stavrou, A., Efthymiou, V., Georghiou, G.: `An investigation into the parameters affecting the success of the wavelet packets method for denoising partial discharge signals', Fifth Mediterranean Conf. on Power Generation, Transmission and Distribution, November 2006.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-smt.2009.0023
Loading

Related content

content/journals/10.1049/iet-smt.2009.0023
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address