Discriminant Analysis and Hilbert Huang Based Power Quality Assessment
Stuti Shukla Datta1, Namrata Dhanda2
1Stuti Shukla Datta, Department of Electrical and Electronics Engineering, Amity University Uttar Pradesh, Lucknow Campus, Lucknow, India.
2Namrata Dhanda, Department of Computer Science and Engineering, Amity University Uttar Pradesh, Luknow Campus, Lucknow, India.
Manuscript received on October 01, 2019. | Revised Manuscript received on October 15, 2019. | Manuscript published on October 30, 2019. | PP: 1290-1293 | Volume-9 Issue-1, October 2019. | Retrieval Number: A9635109119/2019©BEIESP | DOI: 10.35940/ijeat.A9635.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This work deals with Hilbert Huang transform and discriminant analysis based assessment of power signals. Hilbert Huang transform is a combination of Empirical mode decomposition (EMD) and Hilbert Transform. EMD is a data assisted processing technique that works on the time scale difference between local extremas (maxima and minima points of a signal). Unlike Fourier Transform, Wavelet Transform and Stockwell Transform, EMD does not employ any basis function or a window function and highly depends on the data of the signal. Power system is a highly vulnerable system subjected to several technical constraints and hence deviation of power signals from their normal level is inevitable. Thus, in order to study the reasons that cause the deviation of normal values, signal processing technique based on EMD is applied to power signals which are obtained by simulating various power scenarios in MATLAB Simulink platform. Decomposed components are then transformed in the frequency domain using Hilbert Transform. Hilbert transform helps in the extraction of features of the signal in consideration. These features are then subjected to discriminant analysis based classifier to identify the class of the raw input. Efficiency of the methodology is evaluated and results obtained are highly promising.
Keywords: Discriminant Analysis, Empirical Mode Decomposition, Hilbert Transform, Power Signals, Signal Processing.