Decision tree-initialised fuzzy rule-based approach for power quality events classification

摘要: The proposed method develops a decision tree (DT)-initialised fuzzy rule base for Power Quality (PQ) event classification. system suffers from different PQ events such as sag, swell, momentary interruptions, impulsive transients, flicker, notch, spike, harmonics and so on. above-mentioned comprise high-frequency low-frequency components. Thus, it is difficult to classify these using traditional approaches. This approach derives various statistical parameters advanced signal processing technique S-transform. After the required features are extracted, DT used build up classification tree. From boundaries, membership functions corresponding developed final DT-fuzzy provides more accurate results compared heuristic rule-based approach. Also, qualitative comparison made between S-transform wavelet transform, where S-transform-based highly improved later including noisy environment.