Application of dynamic time-frequency analysis for power quality event classification and recognition

The power quality issues have emerged as an important research field for electric market and customers. The power quality disturbances and the resulting problems are the consequences of the increasing use of solid state switching devices, nonlinear and power electronically switched loads, unbalanced power systems and data processing equipment, as well as industrial plant rectifiers and inverters. A novel approach based on wavelet transformation with neural network is presented to investigate the voltage swell fault, which can acquire the qualitative and quantitative results. The advantage of the wavelet transformation is in achieving flexible frequency resolution, thus making it able to extract both high-frequency and low-frequency components from the power quality disturbances. By means of signal singularity detection analysis, the wavelet transformation can accurately detect and locate the transient voltage waveform. The improved training algorithm is utilized to complete the neural network parameters initialization and classification performance, and the main component of the transient signal is obtained from the power quality disturbance with four-level decomposition. In order to satisfy power system observation, the power quality monitor configuration method is proposed. The effectiveness of the proposed approach was ascertained using power quality disturbance with simulation analysis.