Application of signal processing and neural network for transient waveform recognition in power system

The electric utilities and end users of power system network have become more concerned about power quality issues due to technical and financial consequences that have resulted from electric power quality disturbances. The power quality monitoring technology has an effective on analyzing power quality related problems. This paper presents a novel study combining wavelet transform with pattern recognition technique to investigate voltage stability using for power quality events. The wavelet transformation possesses capabilities of time and frequency domain localizations, achieving a great impetus in signal singularity detection. The statistics-based denoising method is designed to filter the random noise and impulse noise in power quality disturbance signals, incorporating the advantages of wavelet transform to extract signal feature meanwhile restraining various noises. The wavelet decomposition coefficients as feature vector of neural network are presented for extracting disturbance signal. The neural network provides a means of determining a degree of belief for each identified disturbance waveform. The performance of the proposed approach is studied and a proper combination of wavelet transformation and neural network is identified.