Dissolved gas analysis (DGA) has been widely used for the detection of incipient faults in oil-filled transformers. This research presents a novel approach to DGA feature prioritisation and classification, which considers not only the relations between a fault type and specific gas ratios but also their statistical characteristics based on data derived from onsite inspections. Firstly, new gas features are acquired based on the analysis of current international gas interpretation standards. Combined with conventional gas ratios, all features are then prioritised by using the Kolmogorov–Smirnov test. The rankings are obtained by using their values of maximum statistic distance. The first three features in ranking are employed as input vectors to a multi-layer support vector machine, whose tuning parameters are acquired by particle swarm optimisation. In the experiment, a bootstrap technique is implemented to approximately equalise sample numbers of different fault cases. A common 10-fold cross-validation technique is employed for performance assessment. Typical artificial intelligence classifiers with gas features extracted from genetic programming are evaluated for comparison purposes.

References

1. 1)
  - 31. Vapnik, V.N.: ‘The nature of statistical learning theory’ (Springer, 1999, 2nd edn.).
2. 2)
  - 6. ‘IEEE guide for the interpretation of gases generated in oil-immersed transformers’, IEEE Std., 2008, C57.104.
3. 3)
  - 11. Liao, R.J., Bian, J.P., Yang, L.J.: ‘Forecasting dissolved gases content in power transformer oil based on weakening buffer operator and least square support vector machine – Markov’, IET Gener. Transm. Distrib., 2012, 6, (2), pp. 142–151 (doi: 10.1049/iet-gtd.2011.0165).
4. 4)
  - 6. Zhang, G., Wang, X., Liang, Y.C., Liu, J.: ‘Fast and robust spectrum sensing via Kolmogorov-Smirnov test’, IEEE Trans. Commun., 2010, 58, (12), pp. 3410–3416 (doi: 10.1109/TCOMM.2010.11.090209).
5. 5)
  - 12. Tang, W.H., Almas, S., Wu, Q.H.: ‘Transformer dissolved gas analysis using least square support vector machine and bootstrap’. Control Conf.Hun Nan, China, 2007, pp. 482–468.
6. 6)
  - 29. Vapnik, V.N.: ‘Statistical learning theory’ (Wiley-Blackwell, 1998, 1st edn.).
7. 7)
  - A. Shintemirov , W.H. Tang , Q.H. Wu . Power transformer fault classification based on dissolved gas analysis by implementing bootstrap and genetic programming. IEEE Trans. Syst. Man Cybern. C, Appl. Rev. , 1 , 69 - 79
8. 8)
  - W. Wu , Z.D. Wang , A. Revell , H. Iacovides , P. Jarman . CFD calibration for network modelling of transformer cooling oil flows – Part I: heat transfer in oil ducts. IET Electr. Power Appl. , 1 , 19 - 27
9. 9)
  - 16. Liao, R.J., Zheng, H.B., Grzybowski, S., Yang, L.J., Tang, C., Zhang, Y.Y.: ‘Fuzzy information granulated particle swarm optimisation-support vector machine regression for the trend forecasting of dissolved gases in oil-filled transformers’, IET Electr. Power Appl., 2011, 5, (2), pp. 230–237 (doi: 10.1049/iet-epa.2010.0103).
10. 10)
  - 13. Wang, Z.Y., Liu, Y.L., Griffin, P.J.: ‘A combined ANN and expert system tool for transformer fault diagnosis’. IEEE Power Eng. Society Winter Meeting, New York, USA, 1999, 2, pp. 1261–1269.
11. 11)
  - 23. Arshad, K., Moessner, K.: ‘Robust spectrum sensing based on statistical tests’, IET. Commun., 2013, 7, (9), pp. 808–817 (doi: 10.1049/iet-com.2012.0499).
12. 12)
  - 32. Kennedy, J., Eberhart, R.: ‘Particle swarm optimisation’. Proc. IEEE Int. Conf. Neural Network, Perth, Australia, 1995, pp. 1942–1948.
13. 13)
  - 24. Ivanov, A., Riccardi, G.: ‘Kolmogorov-Smirnov test for feature selection in emotion recognition from speech’. IEEE Int. Conf. Acoustics, Speech and Signal Processing, 2012, pp. 5125–5128.
14. 14)
  - 18. Karthik, R., Sree, R.R.T., Iruthayarajan, M.W.: ‘Investigations of furanic derivatives in transformer oil using ultra-violet light absorption property’, IET Electr. Power Appl., 2012, 7, (2), pp. 123–130 (doi: 10.1049/iet-epa.2012.0177).
15. 15)
  - 17. Morais, D.R., Rolim, J.G.: ‘A hybrid tool for detection of incipient faults in transformer based on dissolved gas analysis of insulation oil’, IEEE Trans. Power Deliv., 2006, 21, (2), pp. 673–680 (doi: 10.1109/TPWRD.2005.864044).
16. 16)
  - 21. Wei, C.H., Tang, W.H., Wu, Q.H.: ‘A hybrid least-square support vector machine approach to incipient fault detection for oil-immersed power transformer’, Electr. Power Compon. Syst., 2014, 42, (5), pp. 453–463 (doi: 10.1080/15325008.2013.857180).
17. 17)
  - 25. Han, H., Wang, H.J., Dong, X.C.: ‘Transformer fault diagnosis based on feature selection and parameter optimisation’, Energy Proc., 2011, 12, (0), pp. 662–668 (doi: 10.1016/j.egypro.2011.10.090).
18. 18)
  - 3. Weinlader, A., Wu, W., Tenbohlen, S., Wang, Z.D.: ‘Prediction of the oil flow distribution in oil-immersed transformer windings by network modelling and computational fluid dynamics’, IET Electr. Power Appl., 2012, 2, (6), pp. 82–90 (doi: 10.1049/iet-epa.2011.0122).
19. 19)
  - 27. David, J.S.: ‘Handbook of parametric and nonparametric statistical procedures’ (Chapman and Hall, 2011, 5st edn.).
20. 20)
  - P.S. Georgilakis , J.A. Katsigiannis , K.P. Valavanis . A systematic stochastic Petri net based methodology for transformer fault diagnosis and repair actions. J. Intell. Robot. Syst. , 181 - 201
21. 21)
  - 30. Cortes, C., Vapnik, V.N.: ‘Support-vector networks’, Mach. Learn., 1995, 20, (6), pp. 273–297.
22. 22)
  - W. Wu , Z.D. Wang , A. Revell , P. Jarman . CFD calibration for network modelling of transformer cooling oil flows – Part II: pressure loss at junction nodes. IET Electr. Power Appl. , 1 , 28 - 34
23. 23)
  - 28. Eghbali, H.J.: ‘K-S test for detecting changes from landsat imagery data’, IEEE Trans. Syst. Man Cybern., 1979, 9, (1), pp. 17–23 (doi: 10.1109/TSMC.1979.4310069).
24. 24)
  - Q. Su , C. Mi , L.L. Lai , P. Austin . A fuzzy dissolved gas analysis method for the diagnosis of multiple incipient faults in a transformer. IEEE Trans. Power Syst. , 2 , 593 - 598
25. 25)
  - J.L. Guardado , J.L. Naredo , P. Moreno , C.R. Fuerte . A comparative study of neural network efficiency in power transformers diagnosis using dissolved gas analysis. IEEE Trans. Power Deliv. , 4 , 643 - 647
26. 26)
  - 4. Xu, J.Z., Kubis, A., Zhuo, K., Ye, Z.J., Luo, L.F.: ‘Electromagnetic field and thermal distribution optimisation in shell-type traction transformers’, IET Electr. Power Appl., 2013, 7, (8), pp. 627–632.
27. 27)
  - 15. Dong, M., Xu, D.K., Li, M.H., Yan, Z.: ‘Fault diagnosis model for power transformer based on statistical learning theory and dissolved gas analysis’. IEEE Int. Symp. on Electr. Insul., 2004, pp. 85–88.
28. 28)
  - 5. Narayana, G.S., Badgujar, K.P., Kulkarni, S.V.: ‘Factorisation-based transfer function estimation technique for deformation diagnostics of windings in transformers’, IET Electr. Power Appl., 2013, 7, (1), pp. 39–46 (doi: 10.1049/iet-epa.2012.0148).
29. 29)
  - M. Duval . A review of faults detectable by gas-in-oil analysis in transformers. IEEE Electr. Insul. Mag. , 3 , 8 - 17
30. 30)
  - 26. Charalambous, C.A., Wang, Z.D., Jarman, P., Sturgess, J.P.: ‘Frequency domain analysis of a power transformer experiencing sustained ferroresonance’, IET Gener. Transm. Distrib., 2011, 5, (6), pp. 640–649 (doi: 10.1049/iet-gtd.2010.0233).
31. 31)
  - 26. Efron, B., Tibshirani, R.: ‘An introduction to the bootstrap’ (Chapman and Hall, 1994, 1st edn.).
32. 32)
  - L.L. Lai , A.G. Sichanie , B.J. Gwyn . A comparison between evolutionary programming and genetic algorithm for fault section estimation. IEE Proc., Gener., Transm. Distrib. , 5 , 616 - 620

Dissolved gas analysis method based on novel feature prioritisation and support vector machine

References

Related content