Neural network controlled three-phase four-wire shunt active power filter

A three-phase four-wire shunt active power filter for harmonic mitigation a nd reactive power compensation in power systems supplying nonlinear loads i s presented. Three adaptive linear neurons are used to tackle the desired t hree-phase filter current templates. Another feedforvard three-layer neural network is adopted to control the output filter compensating currents onli ne. This is accomplished by producing the appropriate switching patterns of the converter's legs IGBTs. Adequate tracking of the filter current refere nces is obtained by this method. The active filter injects the current requ ired to compensate for the harmonic and reactive components of the line cur rents. Simulation results of the proposed active filter indicate a remarkab le improvement in the source current waveforms. This is reflected in the en hancement of the unified power quality index defined. Also, the filter has exhibited quite a high dynamic response for step variations in the load cur rent, assuring its potential for real-time applications.