KIEE International Transactions on Electrophysics and Applications

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

Neural Network Based Dissolved Gas Analysis Using Gas Composition Patterns Against Fault Causes

  • J. H. Sun (Industry Application Research Center, KERI) ;
  • Kim, K. H. (Industry Application Research Center, KERI) ;
  • P. B. Ha (Dept. of Electronics Engineering, Changwon National University)
  • Published : 2003.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

This study describes neural network based dissolved gas analysis using composition patterns of gas concentrations for transformer fault diagnosis. DGA samples were gathered from related literatures and classified into six types of faults and then a neural network was trained using the DGA samples. Diagnosis tests were performed by the trained neural network with DGA samples of serviced transformers, fault causes of which were identified by actual inspection. Diagnosis results by the neural network were in good agreement with actual faults.

Keywords

References

  1. Sheppard. H. R.. 'Why is gas generated in oil filled transformer', Transmission and Distribution, Vol. 20, No.1, pp. 63-65, 1968
  2. T. O. Haupert, F. Jakob, E. J. Hubacher, 'Application of a new technique for the interpretation of dissolved gas analysis data', 11th annual technical conference of international electric testing association, pp. 43-51, 1989
  3. ML. Surakka, 'Gas analysis oil monitors transformer condition', Modern power systems (USA), Vol. 3, No. 4, pp. 60-61, April, 1983
  4. E. Dornenburg et al., 'Monitoring oil-cooled transformers by gas analysis', Brown-Boveri Rev. 61, pp. 238-247, May, 1974
  5. ANSI/IEEE C57.104-1978, 'Guide for the detection and determination of generated gases in oil-immersed transformer and their relation to the serviceability of the equipment'.
  6. IEC Publication 60599, Interpretation of the Analysis of Gases in Transformers and Other Oil_Filled Electrical Equipment in service, First Edition, 1999
  7. R. R. Rogers, 'UK Experience in the Interpretation of Incipient Faults in Power Transformers By Dissolved Gas-in-Oil Chromatographic Analysis', Doble Client Conference 1975 Paper 42 AIC 75
  8. R. R. Rogers, 'IEEE and IEC Codes to Interpret Incipient Faults in Transformers using Gas in Oil Analysis.' IEEE Transactions on Electrical Insulation. Vol. 13. No.5. pp. 349-354. October, 1978
  9. J. J. Kelly, 'Transformer Fault Diagnosis by Dissolved Gas Analysis' IEEE Transactions on Industry Application. Vol. 16. No. 6. pp. 777-782, November, 1980
  10. X. Ding et al, 'ANN Based transformer fault diagnosis using gas-in-oil analysis', 57th American Power Conference, April 1995, Chicago IL.
  11. S. K. Bhattacharyya et al., 'A neural network approach to transformer fault diagnosis using dissolved gas analysis data', NAPS, 1993
  12. C. E. Lin, J. M. Ling and C. L. Huang, 'An Expert System for Transformer Fault Diagnosis Using Dissolved Gas Analysis', IEEE Trans. on Power Delivery, Vol. , No.1, January, 1993
  13. W. D. Halstead, 'A thermodynamic assessment of the formation of gaseous hydrocarbons in faulty transformers', J. Inst. Petroleum 59 (Sept. 1973) 569 pp. 239-241
  14. Paul J. Griffin, 'Criteria for the interpretation of data for dissolved gases in oil from transformer', Electrical Insulating Oil, STP 998, ASTM, pp. 89-106, 1988
  15. J. J. Kelly, S. D. Meyers, 'The value of gas in oil analysis as a guide to the operational conditions existing in a power transformer', Conference record of 1972 thirty-fourth annual conference of electrical engineering problems in the rubber and plastics industries