A shunt active power filter with control method based on neural network

This paper presents a shunt active power filter with a control method based on neural networks. The objective of the active power filter is to eliminate harmonics, compensate power factor and correct unbalanced problems. The filter acts as a current source, which is connected in parallel with a nonlinear load and controlled to generate the required compensation currents. The control method of the active power filter is based on a neural network, extracting the fundamental sinusoid from the distorted load current waveform without harmfully phase shift due to adopting electronic bandpass filters, on the other hand, the circuit of this method is simple in structure, easy to adjust, adaptability to load currents, etc. The results of computer simulations and experiments are given, which can confirm the feasibility of the proposed active power filter.