A Method for Monitoring Voltage Disturbances Based on Discrete Wavelet Transform and Adaptive Linear Neural Network
Dinh Thanh Viet, Nguyễn Hữu Hiếu, Ngo Minh Khoa · International Review of Electrical Engineering (IREE) · 2016
This paper proposes a method to monitor, detect and classify voltage disturbances including voltage sag, voltage swell, voltage interruption, and long duration voltage variations. The detail coefficient in discrete wavelet transform is used to extract the start and end times of the voltage disturbance. The decomposed level of multi-resolution analysis in discrete wavelet transform is calculated according to the sampling frequency of the voltage signal for determining the approximation coefficient that only contains the fundamental frequency band. Then an adaptive linear neural network is used to estimate the voltage magnitude from the approximation coefficient. Finally, the disturbance will be classified into groups of voltage disturbances based on the characteristics according to the rules in IEEE Std. 1159-2009. The voltage waveforms based on theoretical signal models and actual voltage waveforms which recorded by power quality monitoring equipment are applied to evaluate the proposed method. The simulation results show that the proposed method can detect and classify voltage disturbances better than traditional methods based on root mean square and conventional adaptive linear neural network techniques.