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

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