Performance Investigation of Neural-Network-Based Unified Power-Quality Conditioner

The application of artificial intelligence is growing fast in the area of power electronics and drives. The artificial neural network (ANN) is considered as a new tool to design control circuitry for power-quality (PQ) devices. In this paper, the ANN-based controller is designed for the current control of the shunt active power filter and trained offline using data from the conventional proportional-integral controller. A digital-signal-processor-based microcontroller is used for the real-time simulation and implementation of the control algorithm. An exhaustive simulation study is carried out to investigate the performance of the ANN controller and compare its performance with the conventional PI controller results. The system performance is also verified experimentally on a prototype model developed in the laboratory.