Power fault using signal analysis with complex window and pattern recognition approach

In power system network, the voltage and current signal exhibit fluctuations in amplitude, phase, and frequency due to nonlinear devices utilized for power generation, transmission and distribution. The power quality problems can cause electric equipment malfunction and consume great electric energy. Therefore, it is necessary to monitor these disturbances. A novel approach is put forward to detect and analyze voltage stability by combining wavelet transform with pattern recognition technique. In signal denoising process, the statistic rule is proposed to determine the threshold of each order of wavelet space, which can determine the decomposition level adaptively, increasing the signal-noise-ratio. The wavelet transform coefficients as feature vector are presented for extracting disturbance signal. The effectiveness of training algorithm for pattern recognition is described, which can be realized by feature vector acquisition. The method incorporates the advantages of morphological filter and multi-scale wavelet transform to extract signal feature meanwhile restraining various noises. The simulation results prove that the proposed method is correct and effective for voltage stability analysis.