A Neural Network Adaptive Detecting Approach of Harmonic Current

A neural network adaptive detecting approach of harmonic current for APF (active power filter) is proposed in this paper. It bases on the adaptive noise canceling technology (ANCT). Regarding the fundamental current as noise source, it can be cancelled from the load current, and then the harmonic current is obtained. Artificial neural network (ANN) with two layers is used to cancel the harmonics. The structure of this neural network and the adaptive adjusting algorithm are presented. The study has been carried out through detail digital dynamic simulation using the MATLAB Simulink power system toolbox. The results of simulation show that this approach can detect harmonic components at real time with high precision, little calculation and strong adaptive ability.