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

access icon openaccess Towards automated statistical partial discharge source classification using pattern recognition techniques

This study presents a comprehensive review of the automated classification in partial discharge (PD) source identification and probabilistic interpretation of the classification results based on the relationship between the variation of the phase-resolved PD (PRPD) patterns and the source of the PD. The proposed automated classification system consists of modern, high-performance statistical feature extraction methods and classifier algorithms. Their application in online monitoring and recognition of the PD patterns is investigated based on their low-processing time and high-performance evaluation. The application of modern statistical algorithms and pre-processing methods configured in this automated classification system improves the pattern recognition accuracy of the different PD sources that are suitable to be employed in different high-voltage (HV) insulation media. To evaluate the performance of the different combinations of the feature extraction/classier pairs, laboratory setups are designed and built that simulate various types of PDs. The test cells include three sources of PD in , two sources of PD in transformer oil, and corona in the air. Data samples for different classes of PD sources are captured under two levels of voltage and two different levels of noise. The results of this study evaluate the suitability of the proposed classification systems for probabilistic source identification in various insulation media. Furthermore, of importance to the problem of the PD source identification is to assign a ‘degree of membership’ to each PRPD pattern, besides assigning a class label to it. Some of the classifier algorithms studied in this study, such as fuzzy classifiers, are not only able to show high classification accuracy rate, but they also calculate the ‘degree of membership’ of a sample to a class of data. This enables probabilistic interpretation of a new PRPD pattern that is being classified. The determination of the degree of membership for future PRPD samples allows safer decision making based on the risk associated with the different sources of PD in HV apparatus.

References

    1. 1)
      • 20. Contin, A., Rabach, G.: ‘PD analysis of rotating ac machines’, IEEE Trans. Electr. Insul., 1993, 28, (6), pp. 10331042.
    2. 2)
      • 11. Gulski, E., Kreuger, F.H.: ‘Computer-aided recognition of discharge sources’, IEEE Trans. Electr. Insul., 1992, 27, (1), pp. 8292.
    3. 3)
      • 15. Chan, J.C., Saha, T.K., Ekanayake, C.: ‘Pattern recognition techniques and their applications for automatic classification of artificial partial discharge sources’, IEEE Trans. Dielectr. Electr. Insul., 2013, 20, (2), pp. 468478.
    4. 4)
      • 37. Hinton, G.E., Roweis, S.T.: ‘Stochastic neighbor embedding’, Adv. Neural. Inf. Process. Syst., 2002, 15, pp. 833840.
    5. 5)
      • 8. Salama, M.M.A., Bartnikas, R.: ‘Determination of neural-network topology for partial discharge pulse pattern recognition’, IEEE Trans. Neural Netw., 2002, 13, (2), pp. 446456.
    6. 6)
      • 12. Lalitha, E.M., Satish, L.: ‘Wavelet analysis for classification of multi-source PD patterns’, IEEE Trans. Dielectr. Electr. Insul., 2000, 7, (1), pp. 4047.
    7. 7)
      • 10. Cachin, C., Wiesmann, H.J.: ‘PD recognition with knowledge-based preprocessing and neural networks’, IEEE Trans. Dielectr. Electr. Insul., 1995, 2, (4), pp. 578589.
    8. 8)
      • 40. He, X., Cai, D., Yan, S., et al: ‘Neighborhood preserving embedding’. Tenth IEEE Int. Conf. on Computer Vision (ICCV 2005), Beijing, China, October 2005, vol. 2, pp. 12081213.
    9. 9)
      • 39. He, X., Niyogi, P.: ‘Locality preserving projections’, Neural Inf. Process. Syst., 2004, 16, p. 153.
    10. 10)
      • 27. Janani, H., Kordi, B., Jozani, M.J.: ‘Classification of simultaneous multiple partial discharge sources based on probabilistic interpretation using a two-step logistic regression algorithm’, IEEE Trans. Dielectr. Electr. Insul., 2017, 24, (1), pp. 5465.
    11. 11)
      • 7. Kranz, H.-G., Krump, R.: ‘Partial discharge diagnosis using statistical optimization on a PC-based system’, IEEE Trans. Electr. Insul., 1992, 27, (1), pp. 9398.
    12. 12)
      • 29. Reid, A., Judd, M., Fouracre, R., et al: ‘Simultaneous measurement of partial discharges using IEC60270 and radio-frequency techniques’, IEEE Trans. Dielectr. Electr. Insul., 2011, 18, (2), pp. 444455.
    13. 13)
      • 31. Fisher, R.: ‘The use of multiple measurements in taxonomic problems’, Ann. Eugen., 1936, 7, (2), pp. 179188.
    14. 14)
      • 34. Cox, T.F., Cox, M.A.A.: ‘Multidimensional scaling’ (Chapman & Hall, London, UK, 1994).
    15. 15)
      • 42. Keller, J., Gray, J.M., Givens, M.R.: ‘A fuzzy K-nearest neighbor algorithm’, IEEE Trans. Syst. Man Cybern., 1985, SMC-15, (4), pp. 580585.
    16. 16)
      • 43. Bishop, C.: ‘Neural networks for pattern recognition’, vol. 92, (Oxford Univ. Press, New York, NY, 1995).
    17. 17)
      • 28. Hampton, B.F., Meats, R.J.: ‘Diagnostic measurements at UHF in gas insulated substations’, IEE Proc., Gener. Transm. Distrib., 1988, 135, (2), pp. 137144.
    18. 18)
      • 22. Peng, X., Zhou, C., Hepburn, D., et al: ‘Application of K-means method to pattern recognition in on-line cable partial discharge monitoring’, IEEE Trans. Dielectr. Electr. Insul., 2013, 20, (3), pp. 754761.
    19. 19)
      • 3. Robinson, D.M.: ‘Dielectric phenomena in high voltage cables’ (Chapman and Hall, London, 1936).
    20. 20)
      • 41. Lin, C.-F., Wang, S.-D.: ‘Fuzzy support vector machines’, IEEE Trans. Neural Netw., 2002, 13, (2), pp. 464471.
    21. 21)
      • 24. Duda, R., Hart, P., Stork, D.: ‘Pattern classification’ (John Wiley & Sons, New York, 2001, 2nd edn.).
    22. 22)
      • 16. Sharkawy, R.M., Mangoubi, R.S., Abdel-Galil, T.K., et al: ‘SVM classification of contaminating particles in liquid dielectrics using higher order statistics of electrical and acoustic PD measurements’, IEEE Trans. Dielectr. Electr. Insul., 2007, 14, (3), pp. 669678.
    23. 23)
      • 6. Krivda, A.: ‘Automated recognition of partial discharges’, IEEE Trans. Dielectr. Electr. Insul., 1995, 2, (5), pp. 796821.
    24. 24)
      • 38. Roweis, S.T., Saul, L.K.: ‘Nonlinear dimensionality reduction by locally linear embedding’, Science, 2000, 290, (5500), pp. 23232326.
    25. 25)
      • 13. Wang, M.-H.: ‘Partial discharge pattern recognition of current transformers using an ENN’, IEEE Trans. Power Deliv., 2005, 20, (3), pp. 19841990.
    26. 26)
      • 23. Theodoridis, K.K.S.: ‘Pattern recognition’ (Elsevier Inc., Burlington, MA, 2009, 4th edn.).
    27. 27)
      • 2. Arman, A., Starr, A.: ‘The measurement of discharges in dielectrics’, J. Inst. Electr. Eng., 1936, 79, (475), pp. 6781.
    28. 28)
      • 32. Schölkopf, B., Smola, A., Müller, K.-R.: ‘Nonlinear component analysis as a kernel eigenvalue problem’, 1998, pp. 12991319.
    29. 29)
      • 44. Specht, D.F.: ‘Probabilistic neural networks’, Neural Netw., 1990, 3, (1), pp. 109118.
    30. 30)
      • 5. Sahoo, N.C., Salama, M.M.A., Bartnikas, R.: ‘Trends in partial discharge pattern classification: a survey’, IEEE Trans. Dielectr. Electr. Insul., 2005, 12, (2), pp. 248264.
    31. 31)
      • 45. Freund, Y., Schapire, R.: ‘A decision-theoretic generalization of on-line learning and an application to boosting’, Comput. Learn. Theory, 1995, 55, (1), pp. 119139.
    32. 32)
      • 25. Jain, A., Duin, R.P.W., Mao, J.: ‘Statistical pattern recognition: a review’, IEEE Trans. Pattern Anal. Mach. Intell., 2000, 22, (1), pp. 437.
    33. 33)
      • 17. Satish, L., Gururaj, B.: ‘Use of hidden Markov models for partial discharge pattern classification’, IEEE Trans. Electr. Insul., 1993, 28, (2), pp. 172182.
    34. 34)
      • 4. James, R.E., Phung, B.T.: ‘Development of computer-based measurements and their application to PD pattern analysis’, IEEE Trans. Dielectr. Electr. Insul., 1995, 2, (5), pp. 838856.
    35. 35)
      • 21. Abdel-Galil, T., Sharkawy, R., Salama, M., et al: ‘Partial discharge pulse pattern recognition using an inductive inference algorithm’, IEEE Trans. Dielectr. Electr. Insul., 2005, 12, (2), pp. 320327.
    36. 36)
      • 19. Zhang, X., Ren, J., Tang, J., et al: ‘Kernel statistical uncorrelated optimum discriminant vectors algorithm for GIS PD recognition’, IEEE Trans. Dielectr. Electr. Insul., 2009, 16, (1), pp. 206213.
    37. 37)
      • 35. Agrafiotis, D.K.: ‘Stochastic proximity embedding’, J. Comput. Chem., 2003, 24, (10), pp. 12151221.
    38. 38)
      • 26. IEC 60270: ‘High-voltage test techniques – partial discharge measurements’, Tech. Rep., 2001.
    39. 39)
      • 30. Van Der Maaten, L.J.P., Postma, E.O., Van Den Herik, H.J.: ‘Dimensionality reduction: a comparative review’, J. Mach. Learn. Res., 2009, 10, pp. 141.
    40. 40)
      • 33. Baudat, G., Anouar, F.: ‘Generalized discriminant analysis using a kernel approach’, Neural Comput., 2000, 12, (10), pp. 23852404.
    41. 41)
      • 18. Zhang, X., Xiao, S., Shu, N., et al: ‘GIS partial discharge pattern recognition based on the chaos theory’, IEEE Trans. Dielectr. Electr. Insul., 2014, 21, (2), pp. 783790.
    42. 42)
      • 36. Tenenbaum, J.B., de Silva, V., Langford, J.C.: ‘A global geometric framework for nonlinear dimensionality reduction’, Science, 2000, 290, (5500), pp. 23192323.
    43. 43)
      • 1. Fothergill, J.C.: ‘Ageing, space charge and nanodielectrics: ten things we don't know about dielectrics’. 2007 Int. Conf. on Solid Dielectrics (ICSD), Winchester, UK, 2007, pp. 110.
    44. 44)
      • 14. Contin, A., Cavallini, A., Montanari, G.C., et al: ‘Digital detection and fuzzy classification of partial discharge signals’, IEEE Trans. Dielectr. Electr. Insul., 2002, 9, (3), pp. 335348.
    45. 45)
      • 9. Petrov, L., Lewin, P., Czaszejko, T.: ‘On the applicability of nonlinear time series methods for partial discharge analysis’, IEEE Trans. Dielectr. Electr. Insul., 2014, 21, (1), pp. 284293.
http://iet.metastore.ingenta.com/content/journals/10.1049/hve.2018.5048
Loading

Related content

content/journals/10.1049/hve.2018.5048
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address