A hybrid method based on time frequency analysis and artificial intelligence for classification of power quality events

摘要: Recognition of power quality events by analyzing voltage waveform disturbances is a very important task for system monitoring. This paper presents hybrid intelligent scheme the classification disturbances. The proposed algorithm realized through three main steps: feature extraction, selection and classification. vectors are extracted using S-transform ST Wavelet transform WT which powerful time-frequency analysis tools. In order to avoid large dimension vector, different approaches applied step, namely Sequential Forward Selection SFS, Backward SBS Genetic Algorithm GA. next most meaningful features Probabilistic Neural Network PNN as classifier core. Various transient events, such sag, swell, interruption, harmonics, transient, sag with swell flicker, tested. Sensitivity under noisy conditions investigated in this article. Results show that can detect classify signals, even conditions, high accuracy.