Improvement of Chromatographic Peaks Qualitative Analysis for Power Transformer Base on Decision Tree

  • Jie Shan
  • Cheng-Kuo ChangEmail author
  • Hao-Min Chen
  • Jeng-Shyang Pan
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1107)


The decision tree applied to the chromatographic peak characterization of power transformers in this task. The follows parameters taken as the characteristic attributes of chromatographic peak identification that include peak height, peak width, peak area and peak position. Dichotomy adopted to discretize the continuous attributes to select the nodes by decision tree. From the algorithm, not only ones obtain the adaptive threshold of the characteristic attributes and achieve the correct classification of single effective peaks, but also avoid the errors caused by the simultaneous decision of seven component peaks. The test results shown that the improved algorithm has the advantages of simple principle, good peak drift resistance and false peaks eliminated.


Power transformer Gas chromatography Peak determination Decision tree 


  1. 1.
    Dornerburg, E., Strittmatter, W.: Monitoring oil cooling transformers by gas analysis. Brown Boveri Rev. 61, 238–247 (1974)Google Scholar
  2. 2.
    Liu, Z., Zou, H., Ye, M., et al.: Effect of temperature and buffer solution on migration time window of micellar electrokinetic capillary chromatography. Chromatography 17(2), 147–152 (1999)Google Scholar
  3. 3.
    Colmsjo, A.L.: Chromatographia. Int. J. Sep. Sci. 23(4), 25 (1987)Google Scholar
  4. 4.
    Hu, J., Bao, J., Zhou, F., Luo, H.: An algorithm for transformer chromatographic peak identification based on pattern matching. Power System Autom. 21, 89–91 (2005)Google Scholar
  5. 5.
    Cao, J., Fan, J., An, C.: Application of grey correlation analysis in the identification of transformer oil chromatographic peak. Power Grid Technol. 34(07), 206–210 (2010)Google Scholar
  6. 6.
    Wang, W.: A new optimization method for chromatographic peak identification and characterization of transformer. Meas. Control Technol. 33(3), 94–97 (2014)Google Scholar
  7. 7.
    Ni, Z., Jia, R., Li, L.: Case reasoning based on neural network. Microcomput. Dev. 115, 3–7 (2001)Google Scholar
  8. 8.
    Hu, J., Zhou, F., Bao, J., Luo, Z.: Qualitative algorithm of transformer chromatographic peak based on fuzzy membership function. Autom. Power Syst. 18(70–72), 84 (2005)Google Scholar
  9. 9.
    Chen, S.M., Manalu, G.M.T., Pan, J.S., Liu, H.C.: Fuzzy forecasting based on two-factors second-order fuzzy-trend logical relationship groups and particle swarm optimization techniques. IEEE Trans. Cybern. 43(3), 1102–1117 (2013)CrossRefGoogle Scholar
  10. 10.
    Chen, S.M., Wang, N.Y., Pan, J.S.: Forecasting enrollments using automatic clustering techniques and fuzzy logical relationships. Exp. Syst. Appl. 36(8), 11070–11076 (2009)CrossRefGoogle Scholar
  11. 11.
    Gehrke, J., Ganti, V., Ramakrishnan, R., Loh, W.Y.: Boat—optimistic decision tree construction. Acm Sigmod Rec. 28(2), 169–180 (1999)CrossRefGoogle Scholar
  12. 12.
    Quinlan, J.R.: Programs for Machine Learning (1992)Google Scholar
  13. 13.
    Bian, J., Xu, J.: Video vehicle classification algorithm based on C4.5 decision tree. Microelectron. Comput. 34(5), 104–109 (2017)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.School of Information Science and EngineeringFujian University of TechnologyFuchouChina

Personalised recommendations