A power harmonic detection method based on Wavelet Neural Network

Harmonic detection technology is one of the key technologies used for active power filter (APF), and its development has determined the development of APF technology. It is difficult to detect the harmonic accurately because of the features of power network harmonic, such as inherent nonlinear, random, distribution, non-stationary and the complexity of impact factors, so the study of the power system harmonic´s detection methods is very important. This paper proposes a harmonic detection method based on wavelet neural network combining wavelet with neural network, and designs for the wavelet neural network. The simulation results show that this method can detect the power network harmonic accurately and real-time.