Inter leaved buck converter based active power filter control using artificial neural network

Abstract

This paper present a novel shunt active power filter based on the interleaved buck DC to AC converter. The `shoot through' problem mainly occurs in the conventional active power filter when the same limb of the switches are fired at the simultaneously. The problems encountered with `shoot through' are reduced efficiency, increased temperature in the power switches and electromagnetic interference (EMI). However, the conventional active power filters suffer from `shoot through'. In order to avoid the `shoot through' dead time control could be introduced but it deteriorates the harmonic compensation level. An active power filter based on interleaved buck DC to AC converter with neural network based controller is presented. The compensation process proposed is simple, which is based on sensing line currents and regulating the dc link voltage. Artificial neural network (ANN) control is used to control the dc link voltage in place of the conventional PI controller. The ANN controller trained using data from PI controller. The performance of the ANN controller is compared with the PI controller by MATLAB/Simulink simulation study.