http://iet.metastore.ingenta.com
1887

Hybrid feature selection approach for power transformer fault diagnosis based on support vector machine and genetic algorithm

Hybrid feature selection approach for power transformer fault diagnosis based on support vector machine and genetic algorithm

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Generation, Transmission & Distribution — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

To further improve fault diagnosis accuracy, a new hybrid feature selection approach combined with a genetic algorithm (GA) and support vector machine (SVM) is presented in this study. Adaptive synthetic technique and arctangent transformation method are adopted to improve the statistical property of the training set (IEC TC10 dataset). Five filter methods based on different evaluation metrics are employed to rank 48 input features derived from dissolved gas analysis (DGA). Then, feature combination methods are applied to aggregate feature ranks and form a lower-dimension candidate feature subset. The GA–SVM model is implemented to optimise parameters and select optimal feature subsets. 5-fold cross-validation accuracy of the GA-SVM is used to evaluate fault diagnosis capability of feature subsets and finally, a novel subset is determined as the optimal feature subset. Accuracy comparison manifests the superiority of the optimal feature subsets over that of conventional approaches. Besides, generalisation and robustness of the optimal subset are validated by testing DGA samples from the local power utility. Results indicate that the optimal feature subset obtained by the proposed method can significantly improve the accuracies of power transformer fault diagnosis.

References

    1. 1)
      • 1. Sun, H. C., Huang, Y. C., Huang, C.M.: ‘A review of dissolved gas analysis in power transformers’, Energy Proc., 2012, 14, pp. 12201225.
    2. 2)
      • 2. IEC 60597: ‘Guide for the sampling of gases and of oil-filled electrical equipment and for the analysis of free and dissolved gas’, 2005.
    3. 3)
      • 3. IEC 599: ‘Interpretation of the analysis of gases in transformers and other oil-filled electrical equipment in service’, 1991.
    4. 4)
      • 4. Rogers, R.R.: ‘IEEE and IEC codes to interpret incipient faults in transformers using gas in oil analysis’, IEEE Trans. Electr. Insul., 1978, 13, (5), pp. 348354.
    5. 5)
      • 5. IEEE C57.104: ‘IEEE guide for the interpretation of gases generated in oil-immersed transformer’, 2008.
    6. 6)
      • 6. Duval, M.: ‘A review of faults detectable by gas-in-oil analysis in transformers’, IEEE Electr. Insul. Mag., 2002, 18, (3), pp. 817.
    7. 7)
      • 7. Li, S.B., Wu, G. N., Gao, B., et al: ‘Interpretation of DGA for transformer fault diagnosis with complementary SaE-ELM and arctangent transform’, IEEE Trans. Dielectr. Electr. Insul., 2016, 23, (1), pp. 586595.
    8. 8)
      • 8. Mollmann, A., Pahlavanpour, B.: ‘New guideline for interpretation of dissolved gas analysis in oil filled transformers’, Electra, 1999, 86, pp. 3151.
    9. 9)
      • 9. Fei, S.W., Liu, C. L., Miao, Y. B.: ‘Support vector machine with genetic algorithm for forecasting of key-gas ratios in oil-immersed transformer’, Expert Syst. Appl., 2009, 36, pp. 63266331.
    10. 10)
      • 10. Hazlee, A.L., Chai, X.R., Ab, H.A.B.: ‘Hybrid modified evolutionary particle swarm optimisation-time varying acceleration coefficient-artificial neural network for power transformer fault diagnosis’, Measurements, 2016, 90, pp. 94102.
    11. 11)
      • 11. Zheng, H.B., Liao, R.J., Grzybowski, S., et al: ‘Fault diagnosis of power transformers using multi-class least square support vector machines classifiers with particle swarm optimisation’, IET Electr. Power Appl., 2011, 5, (9), pp. 691696.
    12. 12)
      • 12. Noori, M., Effatnejad, R., Hajihosseini, P.: ‘Using dissolved gas analysis results to detect and isolate the internal faults of power transformers by applying a fuzzy logic method’, IET Gener. Transm. Distrib., 2017, 11, (10), pp. 27212729.
    13. 13)
      • 13. Fan, J.M., Wang, F., Sun, Q., et al: ‘Hybrid RVM-ANFIS algorithm for transformer fault diagnosis’, IET Gener. Transm. Distrib., 2017, 11, (14), pp. 36373643.
    14. 14)
      • 14. Sun, H.C., Huang, Y.C., Huang, C.M.: ‘Fault diagnosis of power transformers using computational intelligence: a review’, Energy Proc., 2012, 14, pp. 12261231.
    15. 15)
      • 15. Hasmat, M., Sukumar, M., Alok, P.K.: ‘Selection of most relevant input parameters using Waikato environment for knowledge analysis for gene expression programming based power transformer fault diagnosis’, Electr. Power Compon. Syst., 2014, 42, (16), pp. 18491861.
    16. 16)
      • 16. Li, J. Z., Zhang, Q. G., Wang, L., et al: ‘Optimal dissolved gas ratios selected by genetic algorithm for power transformer fault diagnosis based on support vector machine’, IEEE Trans. Dielectr. Electr. Insul., 2016, 23, (2), pp. 11981206.
    17. 17)
      • 17. Wei, C.H., Tang, W.H., Wu, Q.H.: ‘Dissolved gas analysis method based on novel feature prioritisation and support vector machine’, IET Electr. Power Appl., 2014, 8, (8), pp. 320328.
    18. 18)
      • 18. Farhad, D.S., Tang, W.H., Wu, H.: ‘Feature selection in power transformer fault diagnosis based on dissolved gas analysis’. Conf. of 4th IEEE PES Innovative Smart Grid Technologies Europe. Copenhagen, Denmark, October 2013, pp. 15.
    19. 19)
      • 19. Irungu, G.K., Akumu, A.O., Munda, J.L.: ‘A new fault diagnostic technique in oil-filled electrical equipment: the dual of Duval triangle’, IEEE Trans. Dielectr. Electr. Insul., 2016, 23, (6), pp. 34053410.
    20. 20)
      • 20. Opeyemi, O., Cai, H.B., Choo, K.R., et al: ‘Ensemble-based multi-filer feature selection method for DDoS detector in cloud computing’, EURASIP J. Wirel. Commun. Netw., 2016, 2016, (1), pp. 110.
    21. 21)
      • 21. Yin, Z.Y., Hou, J.: ‘Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes’, Neurocomputing, 2016, 174, pp. 643650.
    22. 22)
      • 22. Manuel, F.D., Eva, C., Senen, B., et al: ‘Do we need hundreds of classifiers to solve real world classification problems?’, J. Mach. Learn. Res., 2014, 15, pp. 31333181.
    23. 23)
      • 23. Kim, J., Geem, Z.W.: ‘Optimal scheduling for maintenance period of generating using units using a hybrid scatter-genetic algorithm’, IET Gener. Transm. Distrib., 2015, 9, (1), pp. 2230.
    24. 24)
      • 24. Ghadiri, A., Haghifam, M.R., Larimi, S.M.M.: ‘Comprehensive approach for hybrid AC/DC distribution network planning using genetic algorithm’, IET Gener. Transm. Distrib., 2017, 11, (16), pp. 38923902.
    25. 25)
      • 25. Goldberg, D.E.: ‘Genetic algorithm in search, optimization and machine learning’ (Addison-Wesley Publishing Company, New York, 1989).
    26. 26)
      • 26. Hui, H.H., Hsieh, C.W., Lu, M.D.: ‘Hybrid feature selection by combing filters and wrappers’, Expert Syst. Appl., 2011, 38, pp. 81448150.
    27. 27)
      • 27. Vipin, K., Sonajharia, M.: ‘Feature selection: a literature review’, Smart Comput. Rev., 2014, 4, (3), pp. 211229.
    28. 28)
      • 28. Yvan, S., Inaki, I., Pedro, L.: ‘A review of feature selection techniques in bioinformatics’, Bioinformatics, 2007, 23, (19), pp. 25072517.
    29. 29)
      • 29. Yang, P.Y., Zhou, B.B., Zhang, Z. L., et al: ‘A multi-filter enhanced genetic ensemble system for gene selection and sample classification of microarray data’, BMC Bioinf., 2010, 11, pp. 112.
    30. 30)
      • 30. Jovic, A., Brkic, K., Bogunovic, N.: ‘A review of feature selection methods with applications’. Mipro Proc., 2015, pp. 16.
    31. 31)
      • 31. Lv, G.Y., Cheng, H.Z., Zhai, H.B., et al: ‘Fault diagnosis of power transformer based on multi-layer SVM classifier’, Electr. Power Syst. Res., 2005, 75, pp. 915.
    32. 32)
      • 32. He, H.B., Edwardo, A.G.: ‘Learning from imbalanced data’, IEEE Trans. Knowl. Data Eng., 2009, 21, (9), pp. 12631284.
    33. 33)
      • 33. Wilker, A., Taghi, K., Jason, V.H.: ‘Ensemble feature ranking methods for data intensive computing applications’ (Handbook of Data Intensive Computing, Springer, 2011), pp. 349376.
    34. 34)
      • 34. Yi, C., Ma, H., Tapan, S.: ‘Improvement of power transformer insulation diagnosis using oil characteristics data pre-processed by SMOTE Boost technique’, IEEE Trans. Dielectr. Electr. Insul., 2014, 21, (5), pp. 23632373.
    35. 35)
      • 35. Michel, D., Alfonso, D.: ‘Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases’, IEEE Electr. Insul. Mag., 2001, 17, (2), pp. 3141.
    36. 36)
      • 36. Selim, K., Akif, D.: ‘Diagnosis of power transformer faults based on multi-layer support vector machine hybridized with optimization methods’, Electr. Power Compon. Syst., 2016, 44, (19), pp. 21722184.
    37. 37)
      • 37. Chih, C.C., Chih, J.L.: ‘LIBSVM: a library of support vector machines’, ACM Trans. Intell. Syst. Technol., 2011, 2, (3), pp. 127.
    38. 38)
      • 38. Piotr, M., Yann, L.C.: ‘Statistical machine learning and dissolve gas analysis: a review’, IEEE Trans. Power Deliv., 2012, 27, (4), pp. 17911799.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-gtd.2018.5482
Loading

Related content

content/journals/10.1049/iet-gtd.2018.5482
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address