Grey relational analysis using Gaussian process regression method for dissolved gas concentration prediction

  • Shi Xiang Lu
  • Guoying Lin
  • Huakun que
  • Mark Jun Jie Li
  • Cheng Hao Wei
  • Ji Kui Wang
Original Article


The prediction of the dissolved gases content in an oil-immersed power transformer is very important for early fault detection. However, it is quite difficult to obtain accurate predictions due to the non-linearity of gas data. Different machine learning technics have been used to solve this problem, but they neither consider the relationship of different gases nor the sampling errors. In this paper, we propose to use Grey relational analysis (GRA) to calculate grey relational coefficients for gas feature selection and a Gaussian process regression (GPR) to predict dissolved gas value. In this method, both the relationship of gas features and sampling errors are considered. Four algorithms of ANN, SVM, LSSVM and GPR are used in gas prediction. We conducted experiments on eight dissolved gas datasets. The comparison results have shown that the GRA method is effective in selecting good gas features. The performance of prediction of gas values is significantly improved.


Oil-immersed power transformer Dissolved gases analysis Grey relational analysis Gaussian process regression 



All authors contributed equally the same to this article which is supported by National Natural Science Foundations of China (61503252 and 61473194), China Postdoctoral Science Foundation (2016T90799), Guangdong Province Fund(2014GKXM054) and Shenzhen—Hong Kong Technology Cooperation Fund(SGLH20161209101100926).


  1. 1.
    (2009) IEEE guide for the interpretation of gases generated in oil-immersed transformers, pp 1–36Google Scholar
  2. 2.
    Rogers RR (1978) IEEE and IEC codes to interpret incipient faults in transformers, using gas in oil analysis. IEEE Trans Electr Insul 13(5):349–354CrossRefGoogle Scholar
  3. 3.
    Mirowski P, LeCun Y (2012) Statistical Machine Learning and Dissolved Gas Analysis: A Review. IEEE Trans Power Deliv 27(4):1791–1799CrossRefGoogle Scholar
  4. 4.
    Lin CE, Ling JM, Huang CL (1993) An expert ssystem for transformer fault diagnosis using dissolved gas analysis. IEEE Trans Power Deliv 8(1):231–238Google Scholar
  5. 5.
    Su Q, Lai LL, Austin P (2000) A fuzzy dissolved gas analysis method for the diagnosis of multiple incipient faults in a transformer. Int Conf Adv Power Syst Control Oper Manag 2:343–348Google Scholar
  6. 6.
    Richardson ZJ, Fitch J, Tang WH, Goulermas JY, Wu QH (2008) A probabilistic classifier for transformer dissolved gas analysis with a particle swarm optimizer. IEEE Trans Power Deliv 23(2):751–759CrossRefGoogle Scholar
  7. 7.
    Dong LX, Xiao DM, Liang YS, Liu YL (2008) Rough set and fuzzy wavelet neural network integrated with least square weighted fusion algorithm based fault diagnosis research for power transformers. Electr Power Syst Res 78(1):129–136CrossRefGoogle Scholar
  8. 8.
    Yang Z, Tang WH, Shintemirov A, Wu QH (2009) Association rule mining-based dissolved gas analysis for fault diagnosis of power transformers. IEEE Trans Syst Man Cybern Part C 39(6):597–610Google Scholar
  9. 9.
    Li, J., Zhang Q, Wang K, Wang J, Zhou T, Zhang Y (2016) Optimal dissolved gas ratios selected by genetic algorithm for power transformer fault diagnosis based on support vector machine. IEEE Tran Dielectr Electr Insul 23(2):1198–1206Google Scholar
  10. 10.
    Shintemirov A, Tang WH, Wu QH (2009) Power transformer fault classification based on dissolved gas analysis by implementing bootstrap and genetic programming. IEEE Trans Syst Man Cybern Part C 39(1):69–79CrossRefGoogle Scholar
  11. 11.
    Ghoneim SSM, Taha IBM, Elkalashy NI (2016) Integrated ANN-based proactive fault diagnostic scheme for power transformers using dissolved gas analysis. IEEE Trans Dielectr Electr Insul 23(3):1838–1845CrossRefGoogle Scholar
  12. 12.
    Samaher AJ, Sarvesh R, Ahmed P, Ibrahim AS (2015) Design and evaluation of a hybrid system for detection and prediction of faults in electrical transformers. Int J Electr Power Energy Syst 67:324–335CrossRefGoogle Scholar
  13. 13.
    Wang MH (2003) A novel extension method for transformer fault diagnosis. IEEE Trans Power Deliv 18(1):164–169CrossRefGoogle Scholar
  14. 14.
    Wang MH, Hung CP (2003) Novel grey model for the prediction of trend of dissolved gases in oil-filled power apparatus. Electr Power Syst Res 67(1):53–58CrossRefGoogle Scholar
  15. 15.
    Wang MH (2004) Grey-extension method for incipient fault forecasting of oilimmersed power transformer. Electr Power Comp Syst 32(10):959–975CrossRefGoogle Scholar
  16. 16.
    Fei SW, Sun Y (2008) Forecasting dissolved gases content in power transformer oil based on support vector machine with genetic algorithm. Electr Power Syst Res 78(3):507–514CrossRefGoogle Scholar
  17. 17.
    Liao RJ, Zheng HB, Grzybowski S, Yang LJ, Tang C, Zhang YY (2011) 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 5(2):230–237CrossRefGoogle Scholar
  18. 18.
    Liao RJ, Zheng HB, Grzybowski S, Yang LJ (2011) Particle swarm optimization-least squares support vector regression based forecasting model on dissolved gases in oil-filled power transformers. Electr Power Syst Res 81(12):2074–2080CrossRefGoogle Scholar
  19. 19.
    Liao RJ, Bian JP, Yang LJ, Grzybowski S, Wang YY, Li J (2012) Forecasting dissolved gases content in power transformer oil based on weakening buffer operator and least square support vector machine—Markov. IET Gener Transm Distr 6(2):142–151Google Scholar
  20. 20.
    He YL, Wang XZ, Huang JZX (2016) Fuzzy nonlinear regression analysis using a random weight network. Inf Sci 364–365:222–240CrossRefGoogle Scholar
  21. 21.
    He YL, Liu JNK, Hu YH, Wang XZ (2015) OWA operator based link prediction ensemble for social network. Expert Syst Appl 42(1):21–50CrossRefGoogle Scholar
  22. 22.
    Wei CH, Tang WH, Wu QH (2014) Dissolved gas analysis method based on novel feature prioritisation and support vector machine. IET Electr Power Appl 8(8):320–328CrossRefGoogle Scholar
  23. 23.
    Wang XZ, He YL, Wang DD (2014) Non-naive Bayesian classifiers for classification problems with continuous attributes. IEEE Trans Cybern 44(1):21–39CrossRefGoogle Scholar
  24. 24.
    Wang XZ, Ha MH (1992) Fuzzy linear regression analysis. Fuzzy Sets Syst 51(2):179–188MathSciNetCrossRefzbMATHGoogle Scholar
  25. 25.
    Chen WG, Long ZZ (2013) Experimental research on air-gap partial discharge properties in transformer oil-paper insulation. IEEE conference on electrical insulation and dielectric phenomena, vol 9, pp 1274–1277Google Scholar
  26. 26.
    Liu S, Forrest J, Yang Y (2011) A brief introduction to grey systems theory. IEEE international conference on grey systems and intelligent services, vol 2, pp 2403–2408Google Scholar
  27. 27.
    Yiyo K, Taho Y, Guan WH (2008) The use of grey relational analysis in solving multiple attribute decision-making problems. Comput Ind Eng 55(1):80–93CrossRefGoogle Scholar
  28. 28.
    Truongm DQ, Ahn KK, Trung NT (2013) Design of an advanced time delay measurement and a smart adaptive unequal interval grey predictor for real-time nonlinear control systems. IEEE Trans Ind Electron 60(10):4574–4589CrossRefGoogle Scholar
  29. 29.
    Brasel E (2000) A new concept for on-line transformer gas monitoring. CIGRE Session, ParisGoogle Scholar
  30. 30.
    Tenbohlen S, Schafer M, Wang Z, Atanasova I (2008) Investigation on sampling, measurement and interpretation of gas-in-oil analysis for power transformers. CIGRE Session, Paris, pp A2–A102Google Scholar
  31. 31.
    Williams CKI, Rasmussen CE (1996) Gaussian processes for regression. Adv Neural Inf Process Sys 8(6):514–520Google Scholar
  32. 32.
    MacKay DJC (1998) Introduction to Gaussian Processes. Neural Netw Mach Learn 168:133–165Google Scholar
  33. 33.
    Rasmussen CE, Williams CKI (2006) Gaussian processes for machine learning. MIT Press, CambridgeGoogle Scholar
  34. 34.
    Li ST (2012) Study of dissolved gas analysis under electrical and thermal stresses for natural esters used in power transformers. University of Manchester, ManchesterGoogle Scholar
  35. 35.
    Zheng RR, Zhao JY, Wu BC (2009) Transformer oil dissolved gas concentration prediction based on genetic algorithm and improved gray verhulst model. International conference on artificial intelligence and computational intelligence, vol 4, pp 575–579Google Scholar
  36. 36.
    Li JQ, Wang DY, Yong J (2011) Forecast of mass concentration of dissolved gas in transformer oil based on combinative forecasting model. Guangdong Electric Power 24(9):19–23Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Shi Xiang Lu
    • 1
  • Guoying Lin
    • 1
  • Huakun que
    • 1
  • Mark Jun Jie Li
    • 2
  • Cheng Hao Wei
    • 2
  • Ji Kui Wang
    • 2
  1. 1.Electric Power Research Institute Guangdong Power GridGuangzhouPeople’s Republic of China
  2. 2.College of Computer Science and Software EngineeringShenzhen UniversityShenzhenPeople’s Republic of China

Personalised recommendations