DESIGN AND ANALYSIS OF THREE PHASE FOUR WIRE SHUNT ACTIVE FILTER WITH NEURAL NETWORK CONTROLLER FOR NONLINEAR LOAD

Author (s) : R.Divya and M.Sneha

---

Abstract :
The use of non-linear loads is expanding day by day. These loads draw harmonic non-sinusoidal currents in the point of common coupling and distribute them through it. The propagation of these currents into the grid affect the power systems thereby to the equipments of other users. As a result, the power quality has become an important issue for both consumers and distributers of electrical power. Active Filters are today the most widely used systems to eliminate harmonics, compensate power factor and correct unbalanced problems in industrial power plants.  This project focuses on the evaluation of active power filter for power quality improvement. In this shunt active filter which is controlled by neural network based controller for harmonic mitigation and power factor enhancements in ac-dc power supply feeding to a nonlinear load .Three phase four wire shunt active filter is used for this analysis. This paper report presents design, simulation and development of shunt active filter for mitigation of power quality problem at ac main. The task of an active filter is to make the line current waveform as close as possible to a sinusoid in phase with the line voltage by injecting the compensation current. The compensation current is estimated using neural network. Here neural network controller for three phase four wire is used to improve the shunt active filter dynamics to minimize the harmonics present in the load current. This new method is for extracting the three-phase reference currents for active power filters and DC link voltage control method. The objectives of using neural network in active filters are to increase the efficiency, stability, accuracy, robustness, tracking ability of the systems of each component. Moreover, minimizing unneeded signal due to the distortion is the ultimate goal in applying neural network to the filter. To investigate the performance of this identification method, the study will be accomplished using simulation with the MATLAB Simulink Power System Toolbox.

Keywords : Shunt Active Filter, Harmonic mitigation, Active Filters

Conference Date : 30/08/2019

Pages : 25-26

Paper ID : 19024