EEMD-ApEn Applied in Power Quality Detection and Classification

Abstract:

Ensemble Empirical Mode DecompositionApproximate Entropy (EEMD-ApEn) is proposed in this paper, which is mainly analyzed the transient pulse and transient oscillation. In order to overcome the modal mixing problems by empirical mode decomposition (EMD), ensemble EMD (EEMD) is used to obtain intrinsic mode functions (IMFs). Then effective IMFs with physical meaning are reconstructed. Finally, the approximate entropy of IMFs and original signal are calculated which are used to be the input feature vectors of the SVM classifier. The stimulant results show that EEMD-ApEn has better performance in detection and classification of transient pulse, transient oscillation, their noisy signal and the composite disturbance signals. The novel method has many advantages, such as simple, strong anti-noise, required fewer features and so on. Therefore the EEMD-ApEn is an effective method for power quality detection and feature vectors extraction.

• Periodical: Applied Mechanics and Materials (Volumes 423-426)
• Pages: 2443-2447
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.423-426.2443
• Online since: September 2013
• Authors: Yu Xiang Su, Guo Ping Liu, Xiao Qun Shen
• Keywords: Approximate Entropy (ApEn), EEMD, Power Quality Detection and Classification, Support Vector Machine (SVM)

References

[1] Xiangning Xiao. Power Quality Analysis and Control [M]. Beijing: China Electric Power Press, pp.1-18 (2009). In Chinese.

[2] Wu Z, Huang N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method [J]. Advances in Adaptive Data Analysis, (2009), 1(01): 1-41.

DOI: 10.1142/s1793536909000047

[3] Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proceedings of the Royal Society of London Series A. Vol. 45, No. 4 (1998), 903-995.

DOI: 10.1098/rspa.1998.0193

[4] Tsa P H, Lin C, Tsao J, et al. Empirical mode decomposition based detrended sample entropy in electroencephalography for Alzheimer's disease[J]. J NEUROSCI METH, (2012).

[5] Steve Pincus. Approximate entropy as a complexity measure. CHAOS 5, (1995), pp.110-117.

[6] James G, Witten D, Hastie T, et al. Support Vector Machines[M]/An Introduction to Statistical Learning. Springer New York, (2013): 337-372.

DOI: 10.1007/978-1-4614-7138-7_9