Power Quality Event Classification Using Hilbert Huang Transform
The objective of this paper is to develop a method based on combination of empirical-mode decomposition (EMD) and Hilbert transform for power quality events classification. Non-stationary power signal disturbance waveform can be considered as superimposition of various undulating modes and EMD is used to separate out these intrinsic modes known as intrinsic mode functions (IMF). Hilbert transform is applied to all the IMF to achieve instantaneous amplitude and frequency. Relevant feature vectors are extracted to do the automatic classification. Time frequency analysis shows clear visual detection, localization and classification of the different power signal disturbances. A balanced neural tree is used to classify the power signal patterns.
KeywordsNon-Stationary power signals EMD (Empirical Mode Decomposition) Hilbert Transform Balanced Neural Tree
Unable to display preview. Download preview PDF.
- 5.Jayasree, T., Devaraj, D., Sukanesh, R.: Power Quality Disturbance Classification using Hilbert Transform and RBF Networks. Neuro-computing 73, 1451–1456 (2010)Google Scholar
- 8.Maji, P.: Efficient Design of Neural Network Tree using a Single Splitting Criterion. Neuro-computing 71, 787–800 (2008)Google Scholar
- 10.Lau, C., Widrow, B.: Special Issue on Neural Networks. Proceedings of the IEEE 78 (1990)Google Scholar