Artificial Neural Networks for Asymmetric Selective Harmonic Current Mitigation-PWM in Active Power Filters to Meet Power Quality Standards

Abstract

The main objective of an active power filter (APF) is to control the harmonics of nonlinear loads in power systems. In addition, the reactive power (fundamental component of the AC power) at the point of common coupling (PCC) can be compensated by using an APF. This paper investigates a technique for the modulation technique of the active power filters. Using the artificial neural network (ANN) technique, real-time fundamental and harmonic compensations can be achieved for the low-frequency modulation techniques such as asymmetric selective harmonic elimination/mitigation-pulse width modulation (ASHE/ASHM-PWM) and asymmetric selective harmonic current mitigation-PWM (ASHCM-PWM). This means that different phases and magnitudes of the fundamental and harmonics for the voltage of the converter can be obtained in real time by using the proposed technique. Furthermore, in the paper, a guideline is proposed for generating ANN training data for the ASHCM-PWM technique. Simulation and experimental results are conducted on a 7-level (3-cell) cascaded H-bridge (CHB) active power filter to evaluate the advantages and effectiveness of the proposed ANN-based technique.