Advertisement

Power Quality Analysis Based on Time Series Similarity and Extreme Learning Machine

  • Meimei Li
  • Shouqing Jia
  • Shuqing Zhang
  • Zheng Gong
  • Guaifu Li
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 857)

Abstract

Aiming at the problem of the existing fault monitoring method such as intensive computation, dependence on the length of data, and difficult of finding out the abnormal situation, a fast and effective method of recognizing power quality fault is proposed in this paper. Confidence intervals are first partitioned by a pre-judgment method based on time series similarity, and the failure characterization is simplified by measuring similarity between the recorded data and normal data template. Then, S-transform analysis and extreme learning machine were combined to identify the fault type. This method could reduce the amount of calculation and number of fault parameters effectively, finding out the monitored fault immediately. The results of simulation show that the method could realize the fault pre-judgment and analysis effectively with the feature of fast and accurate. Experiment analysis to ChengDe Steel Mills proved the feasibility and the superiority of this method.

Keywords

Metrology Analysis of power quality Similarity measure S-transform Extreme learning machine 

References

  1. 1.
    Zygarlicki, J., Mroczka, J.: Variable- frequency prony method in the analysis of electrical power quality. Metrol. Meas. Syst. 19, 39–48 (2012)Google Scholar
  2. 2.
    Belchior, F., Galvão, T.M., Ribeiro, P.F., Márcio Silveira, P.: Comparative analysis of power quality instruments in measuring power under distorted conditions. Int. J. Emerg. Electr. Power Syst. 16(5), 421–429 (2015)Google Scholar
  3. 3.
    Xia, J.S., Zhao, J.Q., Yang, T.: High precision power quality monitoring system. Electron. Meas. Technol. 39(01), 134–141 (2016)Google Scholar
  4. 4.
    Luo, A., Xu, Q.M., Ma, F.J., Chen, Y.D.: Overview of power quality analysis and control technology for the smart grid. J. Mod. Power Syst. Clean Energy 4(1), 1–9 (2016)CrossRefGoogle Scholar
  5. 5.
    Sang, B., Liu, H.W., Yin, Z.Y.: Research of signal power quality disturbance identification and classification. Foreign Electron. Meas. Technol. 35(07), 56–59 (2016)Google Scholar
  6. 6.
    Li, Y.N., Bao, G.Q.: Power quality disturbance signals identification based on wavelet packet and SVM. Electr. Power Sci. Eng. 03, 21–26 (2012)Google Scholar
  7. 7.
    Liu, G.H., Wu, H.X., Shen, Y.: Novel reconstruction method of power quality data based on regularized adaptive matching pursuit algorithm. Chin. J. Sci. Instrum. 36(08), 1838–1844 (2015)Google Scholar
  8. 8.
    Hao, Y., Zhen, D., Chen, Y.L., Ge, J.F., Lai, L.L., Vaccaro, A., Meng, A.: An effective secondary decomposition approach for wind power forecasting using extreme learning machine trained by crisscross optimization. Energy Convers. Manag. 150, 108–121 (2017)CrossRefGoogle Scholar
  9. 9.
    Zhao, L.Q., Xie, N.N., Wu, C.M.: Construction of Daubechies complex wavelets and application in power quality detection. Comput. Eng. Appl. 35, 233–237 (2012)Google Scholar
  10. 10.
    Su, C.L., Yang, M.C., Lin, M.C.: Measurement and analysis of electric power quality for commercial vessels. Adv. Mater. Res. 1566(433), 6262–6266 (2012)CrossRefGoogle Scholar
  11. 11.
    Shin, K.K.: An alternative approach to measure similarity between two deterministic transient signals. J. Sound Vibr. 371, 434–445 (2016)CrossRefGoogle Scholar
  12. 12.
    Kant, S., Mahara, T.: A new similarity measure based on mean measure of divergence for collaborative filtering in sparse environment. Procedia Comput. Sci. 89, 450–456 (2016)CrossRefGoogle Scholar
  13. 13.
    Duraipandy, P., Devaraj, D.: Extreme learning machine approach for on-line voltage stability assessment. In: Panigrahi, B.K., Suganthan, P.N., Das, S., Dash, S.S. (eds.) SEMCCO 2013. LNCS, vol. 8298, pp. 397–405. Springer, Cham (2013).  https://doi.org/10.1007/978-3-319-03756-1_36CrossRefGoogle Scholar
  14. 14.
    Song, H.J., Huang, C.J., Liu, H.C., Chen, T.J., Li, J.L., Luo, Y.: A new power quality disturbance detection method based on the improved LMD. Proc. CSEE 34(10), 1700–1708 (2014)Google Scholar
  15. 15.
    Shen, H.B., Zheng, S.S., Qi, X.M.: The embedded system for power quality detection based on FFT and wavelet theory. J. Sun Yat-Sen University (Natural Science Edition) 53(04), 40–44 (2014)Google Scholar
  16. 16.
    Reddy, J.B., Mohanta, D.K., Karan, B.M.: Power system disturbance recognition using wavelet and S-transform techniques. Int. J. Emerg. Electr. Power Syst. 1(2) (2011)Google Scholar
  17. 17.
    Zheng, J.D., Pan, H.Y., Cheng, J.S.: Generalized analytical made decomposition for non-stationary analysis. Acta Electronica Sin. 44(06), 1458–1464 (2016)Google Scholar
  18. 18.
    Mahela, O.P., Shaik, A.G.: Recognition of power quality disturbances using S-transform based ruled decision tree and fuzzy C-means clustering classifiers. Appl. Soft Comput. 59, 243–257 (2017)CrossRefGoogle Scholar
  19. 19.
    Deng, Y., Yu, C.S.: Application of factor analysis and ELM in analog circuit fault diagnosis. J. Electron. Measur. Instrum. 30(10), 1512–1519 (2016)Google Scholar
  20. 20.
    Zhang, S.Q., Li, P., Shi, R.Y., Hu, Y.T., Jiang, W.L., Liu, Z.Y.: New method for power quality disturbance classification based on modified S transform. Chin. J. Sci. Instrum. 36(04), 927–934 (2015)Google Scholar
  21. 21.
    Chen, S.M., Cheng, S.H., Lan, T.C.: A novel similarity measure between intuitionistic fuzzy sets based on the centroid points of transformed fuzzy numbers with applications to pattern recognition. Inf. Sci. 343–344, 15–40 (2016)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Wefky, A., Espinosa, F., Santiago, L.D., Revenga, P., Lázaro, J.L., Martínez, M., Wang, W.L.: Electrical drive radiated emissions estimation in terms of input control using extreme learning machines. Math. Prob. Eng. 2012 (2012)Google Scholar
  23. 23.
    Zhang, W.H., Huang, N.T., Yang, J.C., Yang, Y.J., Wang, X.K.: Power quality disturbances classification based on generalized S-transform and differential evolution extreme learning machine. Electr. Meas. Instrum. 53(20), 50–55 (2016)Google Scholar
  24. 24.
    Yu, R., Xiang, R., Yao, S.W.: Extreme learning machine for fault diagnosis of rotating machinery. Adv. Mater. Res. 3247(960), 1400–1403 (2014)CrossRefGoogle Scholar
  25. 25.
    Ao, H.H., Chen, S.F., Yang, S.S.: Similarity model based on trend of times series. Electron. Meas. Technol. 39(06), 196–199 (2016)Google Scholar
  26. 26.
    Sun, K., Zhang, J.Z., Zhang, C.X., Hu, J.Y.: Generalized extreme learning machine autoencoder and a new deep neural network. Neurocomputing 230, 374–381 (2016)CrossRefGoogle Scholar
  27. 27.
    Mishra, M., Sahani, M., Rout, P.K.: An islanding detection algorithm for distributed generation based on Hilbert-Huang transform and extreme learning machine. Sustain. Energy Grids Netw. 9, 13–26 (2016)CrossRefGoogle Scholar
  28. 28.
    Zhong, J.Y., Zhang, Y., Wen, F.S., Zhu, H.B., Li, H.C., Fan, H.F.: A fault diagnosing method in power transmission system based on time series similarity matching. Autom. Electr. Power Syst. 39(06), 60–67 (2015)Google Scholar
  29. 29.
    Nayak, P.K., Mishra, S., Dash, P.K., Bisoi, R.J.: Comparison of modified teaching–learning-based optimization and extreme learning machine for classification of multiple power signal disturbances. Neural Comput. Appl. 27(7), 2107–2122 (2016)CrossRefGoogle Scholar
  30. 30.
    Khokhar, S.H., Mohd Zin, A.A., Memon, A.P., Mokhtar, A.S.: A new optimal feature selection algorithm for classification of power quality disturbances using discrete wavelet transform and probabilistic neural network. Measurement (2016).  https://doi.org/10.1016/j.measurement.2016.10.013
  31. 31.
    Ahila, R., Sadasivam, V.: Performance enhancement of extreme learning machine for power system disturbances classification. Soft. Comput. 18(2), 239–253 (2014)CrossRefGoogle Scholar
  32. 32.
    Yang, X.Y., Guan, W.Y., Liu, Y.Q., Xiao, Y.Q.: Prediction intervals forecasts of wind power based on PSO-KELM. Proc. CSEE 35(S1), 146–153 (2015)Google Scholar
  33. 33.
    Suganyadevi, M.V., Babulal, C.K.: Online voltage stability assessment of power system by comparing voltage stability indices and extreme learning machine. In: Panigrahi, B.K., Suganthan, P.N., Das, S., Dash, S.S. (eds.) SEMCCO 2013. LNCS, vol. 8297, pp. 710–724. Springer, Cham (2013).  https://doi.org/10.1007/978-3-319-03753-0_63CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Meimei Li
    • 1
    • 2
  • Shouqing Jia
    • 1
  • Shuqing Zhang
    • 2
  • Zheng Gong
    • 2
  • Guaifu Li
    • 1
  1. 1.Northeastern UniversityQinhuangdaoChina
  2. 2.Yanshan UniversityQinhuangdaoChina

Personalised recommendations