Measurement and Classification of Simultaneous Power Signal Patterns With an S-Transform Variant and Fuzzy Decision Tree

This paper proposes a new scheme for measurement, identification, and classification of various types of power quality (PQ) disturbances. The proposed method employs a fast variant of S-Transform (ST) algorithm for the extraction of relevant features, which are used to distinguish among different PQ events by a fuzzy decision tree (FDT)-based classifier. Various single as well as simultaneous power signal disturbances have been simulated to demonstrate the efficiency of the proposed technique. The simulation result implies that the proposed scheme has a higher recognition rate while classifying simultaneous PQ faults, unlike other methods. The Fast dyadic S-transform (FDST) algorithm for accurate time-frequency localization, Decision Tree algorithms for optimal feature selection, Fuzzy decision rules to complement overlapping patterns, robust performance under different noise conditions and a relatively simple classifier methodology are the strengths of the proposed scheme.