Key points are not available for this paper at this time.
This paper presents an empirical wavelet transform (EWT) based approach to perform postmortem analysis of wide-area measurement (WAM) based signals. The commonly used empirical mode decomposition (EMD) has limitations such as mode mixing, sensitivity to noise, and sampling rate. The decomposition provided by EWT is more consistent as compared to EMD. The modes revealed by the EWT help in extracting dynamic patterns of different power system disturbances. The dynamic patterns extracted through EWT-based decomposition are further used as inputs to a data-mining tool known as random forest, to build a wide-area disturbance classifier (WADC) model. The efficient mode extraction quality of the EWT-based signal processing tool is analyzed for WAM data recorded on Northern Grid of Indian Power System. The performance of the WADC is validated on IEEE 39-bus New England test system. The results provide improved performance in terms of decomposition quality and classification accuracy.
Jena et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: